diff options
| author | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2021-02-22 21:35:15 -0800 |
|---|---|---|
| committer | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2021-02-22 21:35:15 -0800 |
| commit | cbecf716ca618fd44feda6bd9a64a8179d031fc5 (patch) | |
| tree | 186c9f69f0d11f773253c440dac85087f67288b7 /tools/perf | |
| parent | 6524d8eac258452e547f8a49c8a965ac6dd8a161 (diff) | |
| parent | 4c47097f8514e4b35a31e04e33172d0193cb38ed (diff) | |
Merge branch 'next' into for-linus
Prepare input updates for 5.12 merge window.
Diffstat (limited to 'tools/perf')
277 files changed, 18688 insertions, 12048 deletions
diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index d3740c8f399ba..079cdfabb3520 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -11,6 +11,7 @@ d create a debug log f synthesize first level cache events m synthesize last level cache events + M synthesize memory events t synthesize TLB events a synthesize remote access events g synthesize a call chain (use with i or x) diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 98efdab5fbd4c..c81d72e3eecf4 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -174,34 +174,36 @@ For each cacheline in the 1) list we display following data: Cacheline - cacheline address (hex number) - Total records - - sum of all cachelines accesses - Rmt/Lcl Hitm - cacheline percentage of all Remote/Local HITM accesses - LLC Load Hitm - Total, Lcl, Rmt + LLC Load Hitm - Total, LclHitm, RmtHitm - count of Total/Local/Remote load HITMs - Store Reference - Total, L1Hit, L1Miss - Total - all store accesses - L1Hit - store accesses that hit L1 - L1Hit - store accesses that missed L1 + Total records + - sum of all cachelines accesses - Load Dram - - count of local and remote DRAM accesses + Total loads + - sum of all load accesses - LLC Ld Miss - - count of all accesses that missed LLC + Total stores + - sum of all store accesses - Total Loads - - sum of all load accesses + Store Reference - L1Hit, L1Miss + L1Hit - store accesses that hit L1 + L1Miss - store accesses that missed L1 Core Load Hit - FB, L1, L2 - count of load hits in FB (Fill Buffer), L1 and L2 cache - LLC Load Hit - Llc, Rmt - - count of LLC and Remote load hits + LLC Load Hit - LlcHit, LclHitm + - count of LLC load accesses, includes LLC hits and LLC HITMs + + RMT Load Hit - RmtHit, RmtHitm + - count of remote load accesses, includes remote hits and remote HITMs + + Load Dram - Lcl, Rmt + - count of local and remote DRAM accesses For each offset in the 2) list we display following data: diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 76408d986aed7..5c379adf83043 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -138,7 +138,7 @@ If you want to add or modify several config items, you can do like To modify the sort order of report functionality in user config file(i.e. `~/.perfconfig`), do - % perf config --user report sort-order=srcline + % perf config --user report.sort-order=srcline To change colors of selected line to other foreground and background colors in system config file (i.e. `$(sysconf)/perfconfig`), do @@ -242,6 +242,11 @@ annotate.*:: These are in control of addresses, jump function, source code in lines of assembly code from a specific program. + annotate.disassembler_style: + Use this to change the default disassembler style to some other value + supported by binutils, such as "intel", see the '-M' option help in the + 'objdump' man page. + annotate.hide_src_code:: If a program which is analyzed has source code, this option lets 'annotate' print a list of assembly code with the source code. diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index f50ca0fef0a4e..be65bd55ab2aa 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -182,6 +182,10 @@ OPTIONS --tid=:: Only diff samples for given thread ID (comma separated list). +--stream:: + Enable hot streams comparison. Stream can be a callchain which is + aggregated by the branch records from samples. + COMPARISON ---------- The comparison is governed by the baseline file. The baseline perf.data diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index 78358af9a1c4f..1e91121bac0f3 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -33,7 +33,8 @@ OPTIONS -F:: --funcs:: - List all available functions to trace. + List available functions to trace. It accepts a pattern to + only list interested functions. -p:: --pid=:: diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt index 70969ea73e018..a8eccff212813 100644 --- a/tools/perf/Documentation/perf-inject.txt +++ b/tools/perf/Documentation/perf-inject.txt @@ -24,8 +24,12 @@ information could make use of this facility. OPTIONS ------- -b:: ---build-ids=:: +--build-ids:: Inject build-ids into the output stream + +--buildid-all: + Inject build-ids of all DSOs into the output stream + -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index d5a266d7f15b5..cd362dc2af07e 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -112,6 +112,32 @@ The flags are "bcrosyiABEx" which stand for branch, call, return, conditional, system, asynchronous, interrupt, transaction abort, trace begin, trace end, and in transaction, respectively. +perf script also supports higher level ways to dump instruction traces: + + perf script --insn-trace --xed + +Dump all instructions. This requires installing the xed tool (see XED below) +Dumping all instructions in a long trace can be fairly slow. It is usually better +to start with higher level decoding, like + + perf script --call-trace + +or + + perf script --call-ret-trace + +and then select a time range of interest. The time range can then be examined +in detail with + + perf script --time starttime,stoptime --insn-trace --xed + +While examining the trace it's also useful to filter on specific CPUs using +the -C option + + perf script --time starttime,stoptime --insn-trace --xed -C 1 + +Dump all instructions in time range on CPU 1. + Another interesting field that is not printed by default is 'ipc' which can be displayed as follows: @@ -558,7 +584,7 @@ The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g Intel PT modes of operation ~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Intel PT can be used in 2 modes: +Intel PT can be used in 3 modes: full-trace mode sample mode snapshot mode @@ -571,7 +597,8 @@ Sample mode attaches a Intel PT sample to other events e.g. perf record --aux-sample -e intel_pt//u -e branch-misses:u -Snapshot mode captures the available data when a signal is sent e.g. +Snapshot mode captures the available data when a signal is sent or "snapshot" +control command is issued. e.g. using a signal perf record -v -e intel_pt//u -S ./loopy 1000000000 & [1] 11435 @@ -582,7 +609,23 @@ Note that the signal sent is SIGUSR2. Note that "Recording AUX area tracing snapshot" is displayed because the -v option is used. -The 2 modes cannot be used together. +The advantage of using "snapshot" control command is that the access is +controlled by access to a FIFO e.g. + + $ mkfifo perf.control + $ mkfifo perf.ack + $ cat perf.ack & + [1] 15235 + $ sudo ~/bin/perf record --control fifo:perf.control,perf.ack -S -e intel_pt//u -- sleep 60 & + [2] 15243 + $ ps -e | grep perf + 15244 pts/1 00:00:00 perf + $ kill -USR2 15244 + bash: kill: (15244) - Operation not permitted + $ echo snapshot > perf.control + ack + +The 3 Intel PT modes of operation cannot be used together. Buffer handling @@ -1093,6 +1136,10 @@ To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g. perf script --itrace=oe +XED +--- + +include::build-xed.txt[] SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 10ed539a8859c..4c7db1da8fccc 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -58,6 +58,7 @@ counted. The following modifiers exist: S - read sample value (PERF_SAMPLE_READ) D - pin the event to the PMU W - group is weak and will fallback to non-group if not schedulable, + e - group or event are exclusive and do not share the PMU The 'p' modifier can be used for specifying how precise the instruction address should be. The 'p' modifier can be specified multiple times: diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index bd50cdff08a88..34cf651ee237a 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -293,6 +293,9 @@ OPTIONS --phys-data:: Record the sample physical addresses. +--data-page-size:: + Record the sampled data address data page size. + -T:: --timestamp:: Record the sample timestamps. Use it with 'perf report -D' to see the @@ -631,43 +634,51 @@ option. The -e option and this one can be mixed and matched. Events can be grouped using the {} notation. endif::HAVE_LIBPFM[] ---control fd:ctl-fd[,ack-fd] -Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, -'disable': disable events). Measurements can be started with events disabled using ---delay=-1 option. Optionally send control command completion ('ack\n') to ack-fd descriptor -to synchronize with the controlling process. Example of bash shell script to enable and -disable events during measurements: +--control=fifo:ctl-fifo[,ack-fifo]:: +--control=fd:ctl-fd[,ack-fd]:: +ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows. +Listen on ctl-fd descriptor for command to control measurement. + +Available commands: + 'enable' : enable events + 'disable' : disable events + 'snapshot': AUX area tracing snapshot). + +Measurements can be started with events disabled using --delay=-1 option. Optionally +send control command completion ('ack\n') to ack-fd descriptor to synchronize with the +controlling process. Example of bash shell script to enable and disable events during +measurements: -#!/bin/bash + #!/bin/bash -ctl_dir=/tmp/ + ctl_dir=/tmp/ -ctl_fifo=${ctl_dir}perf_ctl.fifo -test -p ${ctl_fifo} && unlink ${ctl_fifo} -mkfifo ${ctl_fifo} -exec {ctl_fd}<>${ctl_fifo} + ctl_fifo=${ctl_dir}perf_ctl.fifo + test -p ${ctl_fifo} && unlink ${ctl_fifo} + mkfifo ${ctl_fifo} + exec {ctl_fd}<>${ctl_fifo} -ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo -test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo} -mkfifo ${ctl_ack_fifo} -exec {ctl_fd_ack}<>${ctl_ack_fifo} + ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo + test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo} + mkfifo ${ctl_ack_fifo} + exec {ctl_fd_ack}<>${ctl_ack_fifo} -perf record -D -1 -e cpu-cycles -a \ - --control fd:${ctl_fd},${ctl_fd_ack} \ - -- sleep 30 & -perf_pid=$! + perf record -D -1 -e cpu-cycles -a \ + --control fd:${ctl_fd},${ctl_fd_ack} \ + -- sleep 30 & + perf_pid=$! -sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})" -sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})" + sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})" + sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})" -exec {ctl_fd_ack}>&- -unlink ${ctl_ack_fifo} + exec {ctl_fd_ack}>&- + unlink ${ctl_ack_fifo} -exec {ctl_fd}>&- -unlink ${ctl_fifo} + exec {ctl_fd}>&- + unlink ${ctl_fifo} -wait -n ${perf_pid} -exit $? + wait -n ${perf_pid} + exit $? SEE ALSO diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index d068103690ccc..8f7f4e9605d89 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -150,6 +150,7 @@ OPTIONS - snoop: type of snoop (if any) for the data at the time of the sample - dcacheline: the cacheline the data address is on at the time of the sample - phys_daddr: physical address of data being executed on at the time of sample + - data_page_size: the data page size of data being executed on at the time of sample And the default sort keys are changed to local_weight, mem, sym, dso, symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 4f712fb8f175d..44d37210fc8ff 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -116,8 +116,9 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, - brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode, ipc. + srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, + brstackinsn, brstackoff, callindent, insn, insnlen, synth, phys_addr, + metric, misc, srccode, ipc, data_page_size. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index db420dd75e435..5d4a673d7621a 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -166,6 +166,12 @@ use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'. If wanting to monitor, say, 'cycles' for a cgroup and also for system wide, this command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'. +--for-each-cgroup name:: +Expand event list for each cgroup in "name" (allow multiple cgroups separated +by comma). It also support regex patterns to match multiple groups. This has same +effect that repeating -e option and -G option for each event x name. This option +cannot be used with -G/--cgroup option. + -o file:: --output file:: Print the output into the designated file. @@ -180,43 +186,45 @@ with it. --append may be used here. Examples: 3>results perf stat --log-fd 3 -- $cmd 3>>results perf stat --log-fd 3 --append -- $cmd ---control fd:ctl-fd[,ack-fd] +--control=fifo:ctl-fifo[,ack-fifo]:: +--control=fd:ctl-fd[,ack-fd]:: +ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows. Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events). Measurements can be started with events disabled using --delay=-1 option. Optionally send control command completion ('ack\n') to ack-fd descriptor to synchronize with the controlling process. Example of bash shell script to enable and disable events during measurements: -#!/bin/bash + #!/bin/bash -ctl_dir=/tmp/ + ctl_dir=/tmp/ -ctl_fifo=${ctl_dir}perf_ctl.fifo -test -p ${ctl_fifo} && unlink ${ctl_fifo} -mkfifo ${ctl_fifo} -exec {ctl_fd}<>${ctl_fifo} + ctl_fifo=${ctl_dir}perf_ctl.fifo + test -p ${ctl_fifo} && unlink ${ctl_fifo} + mkfifo ${ctl_fifo} + exec {ctl_fd}<>${ctl_fifo} -ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo -test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo} -mkfifo ${ctl_ack_fifo} -exec {ctl_fd_ack}<>${ctl_ack_fifo} + ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo + test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo} + mkfifo ${ctl_ack_fifo} + exec {ctl_fd_ack}<>${ctl_ack_fifo} -perf stat -D -1 -e cpu-cycles -a -I 1000 \ - --control fd:${ctl_fd},${ctl_fd_ack} \ - -- sleep 30 & -perf_pid=$! + perf stat -D -1 -e cpu-cycles -a -I 1000 \ + --control fd:${ctl_fd},${ctl_fd_ack} \ + -- sleep 30 & + perf_pid=$! -sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})" -sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})" + sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})" + sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})" -exec {ctl_fd_ack}>&- -unlink ${ctl_ack_fifo} + exec {ctl_fd_ack}>&- + unlink ${ctl_ack_fifo} -exec {ctl_fd}>&- -unlink ${ctl_fifo} + exec {ctl_fd}>&- + unlink ${ctl_fifo} -wait -n ${perf_pid} -exit $? + wait -n ${perf_pid} + exit $? --pre:: @@ -309,6 +317,10 @@ small group that need not have multiplexing is lowered. This option forbids the event merging logic from sharing events between groups and may be used to increase accuracy in this case. +--quiet:: +Don't print output. This is useful with perf stat record below to only +write data to the perf.data file. + STAT RECORD ----------- Stores stat data into perf data file. @@ -361,6 +373,11 @@ if the workload is actually bound by the CPU and not by something else. For best results it is usually a good idea to use it with interval mode like -I 1000, as the bottleneck of workloads can change often. +This enables --metric-only, unless overridden with --no-metric-only. + +The following restrictions only apply to older Intel CPUs and Atom, +on newer CPUs (IceLake and later) TopDown can be collected for any thread: + The top down metrics are collected per core instead of per CPU thread. Per core mode is automatically enabled and -a (global monitoring) is needed, requiring root rights or @@ -372,8 +389,6 @@ echo 0 > /proc/sys/kernel/nmi_watchdog for best results. Otherwise the bottlenecks may be inconsistent on workload with changing phases. -This enables --metric-only, unless overridden with --no-metric-only. - To interpret the results it is usually needed to know on which CPUs the workload runs on. If needed the CPUs can be forced using taskset. diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 3f37ded13f8ce..c130a3c46a902 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -12,32 +12,57 @@ SYNOPSIS OPTIONS ------- ---debug:: - Setup debug variable (see list below) in value - range (0, 10). Use like: - --debug verbose # sets verbose = 1 - --debug verbose=2 # sets verbose = 2 - - List of debug variables allowed to set: - verbose - general debug messages - ordered-events - ordered events object debug messages - data-convert - data convert command debug messages - stderr - write debug output (option -v) to stderr - in browser mode - perf-event-open - Print perf_event_open() arguments and - return value - ---buildid-dir:: - Setup buildid cache directory. It has higher priority than - buildid.dir config file option. +-h:: +--help:: + Run perf help command. -v:: --version:: - Display perf version. + Display perf version. --h:: ---help:: - Run perf help command. +-vv:: + Print the compiled-in status of libraries. + +--exec-path:: + Display or set exec path. + +--html-path:: + Display html documentation path. + +-p:: +--paginate:: + Set up pager. + +--no-pager:: + Do not set pager. + +--buildid-dir:: + Setup buildid cache directory. It has higher priority + than buildid.dir config file option. + +--list-cmds:: + List the most commonly used perf commands. + +--list-opts:: + List available perf options. + +--debugfs-dir:: + Set debugfs directory or set environment variable PERF_DEBUGFS_DIR. + +--debug:: + Setup debug variable (see list below) in value + range (0, 10). Use like: + --debug verbose # sets verbose = 1 + --debug verbose=2 # sets verbose = 2 + + List of debug variables allowed to set: + verbose - general debug messages + ordered-events - ordered events object debug messages + data-convert - data convert command debug messages + stderr - write debug output (option -v) to stderr + in browser mode + perf-event-open - Print perf_event_open() arguments and + return value DESCRIPTION ----------- diff --git a/tools/perf/Documentation/topdown.txt b/tools/perf/Documentation/topdown.txt new file mode 100644 index 0000000000000..3c39bb3dc5fae --- /dev/null +++ b/tools/perf/Documentation/topdown.txt @@ -0,0 +1,256 @@ +Using TopDown metrics in user space +----------------------------------- + +Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown +methology to break down CPU pipeline execution into 4 bottlenecks: +frontend bound, backend bound, bad speculation, retiring. + +For more details on Topdown see [1][5] + +Traditionally this was implemented by events in generic counters +and specific formulas to compute the bottlenecks. + +perf stat --topdown implements this. + +Full Top Down includes more levels that can break down the +bottlenecks further. This is not directly implemented in perf, +but available in other tools that can run on top of perf, +such as toplev[2] or vtune[3] + +New Topdown features in Ice Lake +=============================== + +With Ice Lake CPUs the TopDown metrics are directly available as +fixed counters and do not require generic counters. This allows +to collect TopDown always in addition to other events. + +% perf stat -a --topdown -I1000 +# time retiring bad speculation frontend bound backend bound + 1.001281330 23.0% 15.3% 29.6% 32.1% + 2.003009005 5.0% 6.8% 46.6% 41.6% + 3.004646182 6.7% 6.7% 46.0% 40.6% + 4.006326375 5.0% 6.4% 47.6% 41.0% + 5.007991804 5.1% 6.3% 46.3% 42.3% + 6.009626773 6.2% 7.1% 47.3% 39.3% + 7.011296356 4.7% 6.7% 46.2% 42.4% + 8.012951831 4.7% 6.7% 47.5% 41.1% +... + +This also enables measuring TopDown per thread/process instead +of only per core. + +Using TopDown through RDPMC in applications on Ice Lake +====================================================== + +For more fine grained measurements it can be useful to +access the new directly from user space. This is more complicated, +but drastically lowers overhead. + +On Ice Lake, there is a new fixed counter 3: SLOTS, which reports +"pipeline SLOTS" (cycles multiplied by core issue width) and a +metric register that reports slots ratios for the different bottleneck +categories. + +The metrics counter is CPU model specific and is not available on older +CPUs. + +Example code +============ + +Library functions to do the functionality described below +is also available in libjevents [4] + +The application opens a group with fixed counter 3 (SLOTS) and any +metric event, and allow user programs to read the performance counters. + +Fixed counter 3 is mapped to a pseudo event event=0x00, umask=04, +so the perf_event_attr structure should be initialized with +{ .config = 0x0400, .type = PERF_TYPE_RAW } +The metric events are mapped to the pseudo event event=0x00, umask=0x8X. +For example, the perf_event_attr structure can be initialized with +{ .config = 0x8000, .type = PERF_TYPE_RAW } for Retiring metric event +The Fixed counter 3 must be the leader of the group. + +#include <linux/perf_event.h> +#include <sys/syscall.h> +#include <unistd.h> + +/* Provide own perf_event_open stub because glibc doesn't */ +__attribute__((weak)) +int perf_event_open(struct perf_event_attr *attr, pid_t pid, + int cpu, int group_fd, unsigned long flags) +{ + return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); +} + +/* Open slots counter file descriptor for current task. */ +struct perf_event_attr slots = { + .type = PERF_TYPE_RAW, + .size = sizeof(struct perf_event_attr), + .config = 0x400, + .exclude_kernel = 1, +}; + +int slots_fd = perf_event_open(&slots, 0, -1, -1, 0); +if (slots_fd < 0) + ... error ... + +/* + * Open metrics event file descriptor for current task. + * Set slots event as the leader of the group. + */ +struct perf_event_attr metrics = { + .type = PERF_TYPE_RAW, + .size = sizeof(struct perf_event_attr), + .config = 0x8000, + .exclude_kernel = 1, +}; + +int metrics_fd = perf_event_open(&metrics, 0, -1, slots_fd, 0); +if (metrics_fd < 0) + ... error ... + + +The RDPMC instruction (or _rdpmc compiler intrinsic) can now be used +to read slots and the topdown metrics at different points of the program: + +#include <stdint.h> +#include <x86intrin.h> + +#define RDPMC_FIXED (1 << 30) /* return fixed counters */ +#define RDPMC_METRIC (1 << 29) /* return metric counters */ + +#define FIXED_COUNTER_SLOTS 3 +#define METRIC_COUNTER_TOPDOWN_L1 0 + +static inline uint64_t read_slots(void) +{ + return _rdpmc(RDPMC_FIXED | FIXED_COUNTER_SLOTS); +} + +static inline uint64_t read_metrics(void) +{ + return _rdpmc(RDPMC_METRIC | METRIC_COUNTER_TOPDOWN_L1); +} + +Then the program can be instrumented to read these metrics at different +points. + +It's not a good idea to do this with too short code regions, +as the parallelism and overlap in the CPU program execution will +cause too much measurement inaccuracy. For example instrumenting +individual basic blocks is definitely too fine grained. + +Decoding metrics values +======================= + +The value reported by read_metrics() contains four 8 bit fields +that represent a scaled ratio that represent the Level 1 bottleneck. +All four fields add up to 0xff (= 100%) + +The binary ratios in the metric value can be converted to float ratios: + +#define GET_METRIC(m, i) (((m) >> (i*8)) & 0xff) + +#define TOPDOWN_RETIRING(val) ((float)GET_METRIC(val, 0) / 0xff) +#define TOPDOWN_BAD_SPEC(val) ((float)GET_METRIC(val, 1) / 0xff) +#define TOPDOWN_FE_BOUND(val) ((float)GET_METRIC(val, 2) / 0xff) +#define TOPDOWN_BE_BOUND(val) ((float)GET_METRIC(val, 3) / 0xff) + +and then converted to percent for printing. + +The ratios in the metric accumulate for the time when the counter +is enabled. For measuring programs it is often useful to measure +specific sections. For this it is needed to deltas on metrics. + +This can be done by scaling the metrics with the slots counter +read at the same time. + +Then it's possible to take deltas of these slots counts +measured at different points, and determine the metrics +for that time period. + + slots_a = read_slots(); + metric_a = read_metrics(); + + ... larger code region ... + + slots_b = read_slots() + metric_b = read_metrics() + + # compute scaled metrics for measurement a + retiring_slots_a = GET_METRIC(metric_a, 0) * slots_a + bad_spec_slots_a = GET_METRIC(metric_a, 1) * slots_a + fe_bound_slots_a = GET_METRIC(metric_a, 2) * slots_a + be_bound_slots_a = GET_METRIC(metric_a, 3) * slots_a + + # compute delta scaled metrics between b and a + retiring_slots = GET_METRIC(metric_b, 0) * slots_b - retiring_slots_a + bad_spec_slots = GET_METRIC(metric_b, 1) * slots_b - bad_spec_slots_a + fe_bound_slots = GET_METRIC(metric_b, 2) * slots_b - fe_bound_slots_a + be_bound_slots = GET_METRIC(metric_b, 3) * slots_b - be_bound_slots_a + +Later the individual ratios for the measurement period can be recreated +from these counts. + + slots_delta = slots_b - slots_a + retiring_ratio = (float)retiring_slots / slots_delta + bad_spec_ratio = (float)bad_spec_slots / slots_delta + fe_bound_ratio = (float)fe_bound_slots / slots_delta + be_bound_ratio = (float)be_bound_slots / slota_delta + + printf("Retiring %.2f%% Bad Speculation %.2f%% FE Bound %.2f%% BE Bound %.2f%%\n", + retiring_ratio * 100., + bad_spec_ratio * 100., + fe_bound_ratio * 100., + be_bound_ratio * 100.); + +Resetting metrics counters +========================== + +Since the individual metrics are only 8bit they lose precision for +short regions over time because the number of cycles covered by each +fraction bit shrinks. So the counters need to be reset regularly. + +When using the kernel perf API the kernel resets on every read. +So as long as the reading is at reasonable intervals (every few +seconds) the precision is good. + +When using perf stat it is recommended to always use the -I option, +with no longer interval than a few seconds + + perf stat -I 1000 --topdown ... + +For user programs using RDPMC directly the counter can +be reset explicitly using ioctl: + + ioctl(perf_fd, PERF_EVENT_IOC_RESET, 0); + +This "opens" a new measurement period. + +A program using RDPMC for TopDown should schedule such a reset +regularly, as in every few seconds. + +Limits on Ice Lake +================== + +Four pseudo TopDown metric events are exposed for the end-users, +topdown-retiring, topdown-bad-spec, topdown-fe-bound and topdown-be-bound. +They can be used to collect the TopDown value under the following +rules: +- All the TopDown metric events must be in a group with the SLOTS event. +- The SLOTS event must be the leader of the group. +- The PERF_FORMAT_GROUP flag must be applied for each TopDown metric + events + +The SLOTS event and the TopDown metric events can be counting members of +a sampling read group. Since the SLOTS event must be the leader of a TopDown +group, the second event of the group is the sampling event. +For example, perf record -e '{slots, $sampling_event, topdown-retiring}:S' + + +[1] https://software.intel.com/en-us/top-down-microarchitecture-analysis-method-win +[2] https://github.com/andikleen/pmu-tools/wiki/toplev-manual +[3] https://software.intel.com/en-us/intel-vtune-amplifier-xe +[4] https://github.com/andikleen/pmu-tools/tree/master/jevents +[5] https://sites.google.com/site/analysismethods/yasin-pubs diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 190be4fa5c218..ce8516e4de34f 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -16,7 +16,7 @@ $(shell printf "" > $(OUTPUT).config-detected) detected = $(shell echo "$(1)=y" >> $(OUTPUT).config-detected) detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected) -CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS) +CFLAGS := $(EXTRA_CFLAGS) $(filter-out -Wnested-externs,$(EXTRA_WARNINGS)) include $(srctree)/tools/scripts/Makefile.arch @@ -223,14 +223,17 @@ endif # Try different combinations to accommodate systems that only have # python[2][-config] in weird combinations but always preferring -# python2 and python2-config as per pep-0394. If we catch a -# python[-config] in version 3, the version check will kill it. -PYTHON2 := $(if $(call get-executable,python2),python2,python) -override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2)) -PYTHON2_CONFIG := \ +# python2 and python2-config as per pep-0394. If python2 or python +# aren't found, then python3 is used. +PYTHON_AUTO := python +PYTHON_AUTO := $(if $(call get-executable,python3),python3,$(PYTHON_AUTO)) +PYTHON_AUTO := $(if $(call get-executable,python),python,$(PYTHON_AUTO)) +PYTHON_AUTO := $(if $(call get-executable,python2),python2,$(PYTHON_AUTO)) +override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON_AUTO)) +PYTHON_AUTO_CONFIG := \ $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config) override PYTHON_CONFIG := \ - $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG)) + $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON_AUTO_CONFIG)) grep-libs = $(filter -l%,$(1)) strip-libs = $(filter-out -l%,$(1)) @@ -483,10 +486,6 @@ ifndef NO_LIBELF EXTLIBS += -lelf $(call detected,CONFIG_LIBELF) - ifeq ($(feature-libelf-mmap), 1) - CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT - endif - ifeq ($(feature-libelf-getphdrnum), 1) CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT endif @@ -724,12 +723,14 @@ ifndef NO_SLANG endif endif -ifndef NO_GTK2 +ifdef GTK2 FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) + $(call feature_check,gtk2) ifneq ($(feature-gtk2), 1) msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); NO_GTK2 := 1 else + $(call feature_check,gtk2-infobar) ifeq ($(feature-gtk2-infobar), 1) GTK_CFLAGS := -DHAVE_GTK_INFO_BAR_SUPPORT endif @@ -748,6 +749,7 @@ else PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) @@ -825,6 +827,12 @@ else $(call feature_check,disassembler-four-args) endif +ifeq ($(feature-libbfd-buildid), 1) + CFLAGS += -DHAVE_LIBBFD_BUILDID_SUPPORT +else + msg := $(warning Old version of libbfd/binutils things like PE executable profiling will not be available); +endif + ifdef NO_DEMANGLE CFLAGS += -DNO_DEMANGLE else diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 6031167939ae6..62f3deb1d3a8b 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -48,7 +48,7 @@ include ../scripts/utilities.mak # # Define NO_SLANG if you do not want TUI support. # -# Define NO_GTK2 if you do not want GTK+ GUI support. +# Define GTK2 if you want GTK+ GUI support. # # Define NO_DEMANGLE if you do not want C++ symbol demangling. # @@ -175,10 +175,6 @@ endef LD += $(EXTRA_LDFLAGS) -HOSTCC ?= gcc -HOSTLD ?= ld -HOSTAR ?= ar - PKG_CONFIG = $(CROSS_COMPILE)pkg-config LLVM_CONFIG ?= llvm-config @@ -386,7 +382,7 @@ ifneq ($(OUTPUT),) CFLAGS += -I$(OUTPUT) endif -ifndef NO_GTK2 +ifdef GTK2 ALL_PROGRAMS += $(OUTPUT)libperf-gtk.so GTK_IN := $(OUTPUT)gtk-in.o endif @@ -537,6 +533,12 @@ mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh $(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl) $(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@ +mremap_flags_array := $(beauty_outdir)/mremap_flags_array.c +mremap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mremap_flags.sh + +$(mremap_flags_array): $(linux_uapi_dir)/mman.h $(mremap_flags_tbl) + $(Q)$(SHELL) '$(mremap_flags_tbl)' $(linux_uapi_dir) > $@ + mount_flags_array := $(beauty_outdir)/mount_flags_array.c mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh @@ -549,6 +551,13 @@ move_mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/move_mount_flags.sh $(move_mount_flags_array): $(linux_uapi_dir)/fs.h $(move_mount_flags_tbl) $(Q)$(SHELL) '$(move_mount_flags_tbl)' $(linux_uapi_dir) > $@ + +mmap_prot_array := $(beauty_outdir)/mmap_prot_array.c +mmap_prot_tbl := $(srctree)/tools/perf/trace/beauty/mmap_prot.sh + +$(mmap_prot_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_prot_tbl) + $(Q)$(SHELL) '$(mmap_prot_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@ + prctl_option_array := $(beauty_outdir)/prctl_option_array.c prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/ prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh @@ -710,6 +719,8 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(vhost_virtio_ioctl_array) \ $(madvise_behavior_array) \ $(mmap_flags_array) \ + $(mmap_prot_array) \ + $(mremap_flags_array) \ $(mount_flags_array) \ $(move_mount_flags_array) \ $(perf_ioctl_array) \ @@ -886,7 +897,7 @@ check: $(OUTPUT)common-cmds.h ### Installation rules -ifndef NO_GTK2 +ifdef GTK2 install-gtk: $(OUTPUT)libperf-gtk.so $(call QUIET_INSTALL, 'GTK UI') \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \ @@ -961,6 +972,7 @@ install-tests: all install-gtk $(call QUIET_INSTALL, tests) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ + $(INSTALL) tests/pe-file.exe* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \ @@ -1007,6 +1019,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(fspick_arrays) \ $(OUTPUT)$(madvise_behavior_array) \ $(OUTPUT)$(mmap_flags_array) \ + $(OUTPUT)$(mmap_prot_array) \ + $(OUTPUT)$(mremap_flags_array) \ $(OUTPUT)$(mount_flags_array) \ $(OUTPUT)$(move_mount_flags_array) \ $(OUTPUT)$(drm_ioctl_array) \ diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index cad7bf7834138..bd446aba64f72 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -395,7 +395,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * To obtain the auxtrace buffer file descriptor, the auxtrace * event must come first. */ - perf_evlist__to_front(evlist, cs_etm_evsel); + evlist__to_front(evlist, cs_etm_evsel); /* * In the case of per-cpu mmaps, we need the CPU on the @@ -420,7 +420,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, goto out; tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index dbef716a19135..fab3095fb5d08 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -4,6 +4,7 @@ PERF_HAVE_DWARF_REGS := 1 endif PERF_HAVE_JITDUMP := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 +HAVE_KVM_STAT_SUPPORT := 1 # # Syscall table generation for perf diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index 5c13438c7bd42..ead2f2275eee7 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -1,6 +1,8 @@ perf-y += header.o perf-y += machine.o perf-y += perf_regs.o +perf-y += tsc.o +perf-y += kvm-stat.o perf-$(CONFIG_DWARF) += dwarf-regs.o perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o @@ -8,4 +10,4 @@ perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \ ../../arm/util/auxtrace.o \ ../../arm/util/cs-etm.o \ - arm-spe.o + arm-spe.o mem-events.o diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index e3593063b3d17..414c8a5584b13 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -118,7 +118,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, * To obtain the auxtrace buffer file descriptor, the auxtrace event * must come first. */ - perf_evlist__to_front(evlist, arm_spe_evsel); + evlist__to_front(evlist, arm_spe_evsel); evsel__set_sample_bit(arm_spe_evsel, CPU); evsel__set_sample_bit(arm_spe_evsel, TIME); @@ -130,7 +130,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, return err; tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; diff --git a/tools/perf/arch/arm64/util/arm64_exception_types.h b/tools/perf/arch/arm64/util/arm64_exception_types.h new file mode 100644 index 0000000000000..27c981ebe4012 --- /dev/null +++ b/tools/perf/arch/arm64/util/arm64_exception_types.h @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef ARCH_PERF_ARM64_EXCEPTION_TYPES_H +#define ARCH_PERF_ARM64_EXCEPTION_TYPES_H + +/* Per asm/virt.h */ +#define HVC_STUB_ERR 0xbadca11 + +/* Per asm/kvm_asm.h */ +#define ARM_EXCEPTION_IRQ 0 +#define ARM_EXCEPTION_EL1_SERROR 1 +#define ARM_EXCEPTION_TRAP 2 +#define ARM_EXCEPTION_IL 3 +/* The hyp-stub will return this for any kvm_call_hyp() call */ +#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR + +#define kvm_arm_exception_type \ + {ARM_EXCEPTION_IRQ, "IRQ" }, \ + {ARM_EXCEPTION_EL1_SERROR, "SERROR" }, \ + {ARM_EXCEPTION_TRAP, "TRAP" }, \ + {ARM_EXCEPTION_IL, "ILLEGAL" }, \ + {ARM_EXCEPTION_HYP_GONE, "HYP_GONE" } + +/* Per asm/esr.h */ +#define ESR_ELx_EC_UNKNOWN (0x00) +#define ESR_ELx_EC_WFx (0x01) +/* Unallocated EC: 0x02 */ +#define ESR_ELx_EC_CP15_32 (0x03) +#define ESR_ELx_EC_CP15_64 (0x04) +#define ESR_ELx_EC_CP14_MR (0x05) +#define ESR_ELx_EC_CP14_LS (0x06) +#define ESR_ELx_EC_FP_ASIMD (0x07) +#define ESR_ELx_EC_CP10_ID (0x08) /* EL2 only */ +#define ESR_ELx_EC_PAC (0x09) /* EL2 and above */ +/* Unallocated EC: 0x0A - 0x0B */ +#define ESR_ELx_EC_CP14_64 (0x0C) +/* Unallocated EC: 0x0d */ +#define ESR_ELx_EC_ILL (0x0E) +/* Unallocated EC: 0x0F - 0x10 */ +#define ESR_ELx_EC_SVC32 (0x11) +#define ESR_ELx_EC_HVC32 (0x12) /* EL2 only */ +#define ESR_ELx_EC_SMC32 (0x13) /* EL2 and above */ +/* Unallocated EC: 0x14 */ +#define ESR_ELx_EC_SVC64 (0x15) +#define ESR_ELx_EC_HVC64 (0x16) /* EL2 and above */ +#define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */ +#define ESR_ELx_EC_SYS64 (0x18) +#define ESR_ELx_EC_SVE (0x19) +#define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ +/* Unallocated EC: 0x1b - 0x1E */ +#define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ +#define ESR_ELx_EC_IABT_LOW (0x20) +#define ESR_ELx_EC_IABT_CUR (0x21) +#define ESR_ELx_EC_PC_ALIGN (0x22) +/* Unallocated EC: 0x23 */ +#define ESR_ELx_EC_DABT_LOW (0x24) +#define ESR_ELx_EC_DABT_CUR (0x25) +#define ESR_ELx_EC_SP_ALIGN (0x26) +/* Unallocated EC: 0x27 */ +#define ESR_ELx_EC_FP_EXC32 (0x28) +/* Unallocated EC: 0x29 - 0x2B */ +#define ESR_ELx_EC_FP_EXC64 (0x2C) +/* Unallocated EC: 0x2D - 0x2E */ +#define ESR_ELx_EC_SERROR (0x2F) +#define ESR_ELx_EC_BREAKPT_LOW (0x30) +#define ESR_ELx_EC_BREAKPT_CUR (0x31) +#define ESR_ELx_EC_SOFTSTP_LOW (0x32) +#define ESR_ELx_EC_SOFTSTP_CUR (0x33) +#define ESR_ELx_EC_WATCHPT_LOW (0x34) +#define ESR_ELx_EC_WATCHPT_CUR (0x35) +/* Unallocated EC: 0x36 - 0x37 */ +#define ESR_ELx_EC_BKPT32 (0x38) +/* Unallocated EC: 0x39 */ +#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */ +/* Unallocated EC: 0x3B */ +#define ESR_ELx_EC_BRK64 (0x3C) +/* Unallocated EC: 0x3D - 0x3F */ +#define ESR_ELx_EC_MAX (0x3F) + +#define ECN(x) { ESR_ELx_EC_##x, #x } + +#define kvm_arm_exception_class \ + ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \ + ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(PAC), ECN(CP14_64), \ + ECN(SVC64), ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(SVE), \ + ECN(IMP_DEF), ECN(IABT_LOW), ECN(IABT_CUR), \ + ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \ + ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \ + ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \ + ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ + ECN(BKPT32), ECN(VECTOR32), ECN(BRK64) + +#endif /* ARCH_PERF_ARM64_EXCEPTION_TYPES_H */ diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c new file mode 100644 index 0000000000000..50376b9062c1b --- /dev/null +++ b/tools/perf/arch/arm64/util/kvm-stat.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <memory.h> +#include "../../util/evsel.h" +#include "../../util/kvm-stat.h" +#include "arm64_exception_types.h" +#include "debug.h" + +define_exit_reasons_table(arm64_exit_reasons, kvm_arm_exception_type); +define_exit_reasons_table(arm64_trap_exit_reasons, kvm_arm_exception_class); + +const char *kvm_trap_exit_reason = "esr_ec"; +const char *vcpu_id_str = "id"; +const int decode_str_len = 20; +const char *kvm_exit_reason = "ret"; +const char *kvm_entry_trace = "kvm:kvm_entry"; +const char *kvm_exit_trace = "kvm:kvm_exit"; + +const char *kvm_events_tp[] = { + "kvm:kvm_entry", + "kvm:kvm_exit", + NULL, +}; + +static void 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); + key->exit_reasons = arm64_exit_reasons; + + /* + * TRAP exceptions carry exception class info in esr_ec field + * and, hence, we need to use a different exit_reasons table to + * properly decode event's est_ec. + */ + if (key->key == ARM_EXCEPTION_TRAP) { + key->key = evsel__intval(evsel, sample, kvm_trap_exit_reason); + key->exit_reasons = arm64_trap_exit_reasons; + } +} + +static bool event_begin(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return !strcmp(evsel->name, kvm_entry_trace); +} + +static bool event_end(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + if (!strcmp(evsel->name, kvm_exit_trace)) { + event_get_key(evsel, sample, key); + return true; + } + return false; +} + +static struct kvm_events_ops exit_events = { + .is_begin_event = event_begin, + .is_end_event = event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +struct kvm_reg_events_ops kvm_reg_events_ops[] = { + { + .name = "vmexit", + .ops = &exit_events, + }, + { NULL }, +}; + +const char * const kvm_skip_events[] = { + NULL, +}; + +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) +{ + kvm->exit_reasons_isa = "arm64"; + return 0; +} diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c new file mode 100644 index 0000000000000..2a24973726712 --- /dev/null +++ b/tools/perf/arch/arm64/util/mem-events.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "map_symbol.h" +#include "mem-events.h" + +#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } + +static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { + E("spe-load", "arm_spe_0/ts_enable=1,load_filter=1,store_filter=0,min_latency=%u/", "arm_spe_0"), + E("spe-store", "arm_spe_0/ts_enable=1,load_filter=0,store_filter=1/", "arm_spe_0"), + E("spe-ldst", "arm_spe_0/ts_enable=1,load_filter=1,store_filter=1,min_latency=%u/", "arm_spe_0"), +}; + +static char mem_ev_name[100]; + +struct perf_mem_event *perf_mem_events__ptr(int i) +{ + if (i >= PERF_MEM_EVENTS__MAX) + return NULL; + + return &perf_mem_events[i]; +} + +char *perf_mem_events__name(int i) +{ + struct perf_mem_event *e = perf_mem_events__ptr(i); + + if (i >= PERF_MEM_EVENTS__MAX) + return NULL; + + if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE) + scnprintf(mem_ev_name, sizeof(mem_ev_name), + e->name, perf_mem_events__loads_ldlat); + else /* PERF_MEM_EVENTS__STORE */ + scnprintf(mem_ev_name, sizeof(mem_ev_name), e->name); + + return mem_ev_name; +} diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c index 2833e101a7c64..54efa12fdbea3 100644 --- a/tools/perf/arch/arm64/util/perf_regs.c +++ b/tools/perf/arch/arm64/util/perf_regs.c @@ -2,5 +2,38 @@ #include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { + SMPL_REG(x0, PERF_REG_ARM64_X0), + SMPL_REG(x1, PERF_REG_ARM64_X1), + SMPL_REG(x2, PERF_REG_ARM64_X2), + SMPL_REG(x3, PERF_REG_ARM64_X3), + SMPL_REG(x4, PERF_REG_ARM64_X4), + SMPL_REG(x5, PERF_REG_ARM64_X5), + SMPL_REG(x6, PERF_REG_ARM64_X6), + SMPL_REG(x7, PERF_REG_ARM64_X7), + SMPL_REG(x8, PERF_REG_ARM64_X8), + SMPL_REG(x9, PERF_REG_ARM64_X9), + SMPL_REG(x10, PERF_REG_ARM64_X10), + SMPL_REG(x11, PERF_REG_ARM64_X11), + SMPL_REG(x12, PERF_REG_ARM64_X12), + SMPL_REG(x13, PERF_REG_ARM64_X13), + SMPL_REG(x14, PERF_REG_ARM64_X14), + SMPL_REG(x15, PERF_REG_ARM64_X15), + SMPL_REG(x16, PERF_REG_ARM64_X16), + SMPL_REG(x17, PERF_REG_ARM64_X17), + SMPL_REG(x18, PERF_REG_ARM64_X18), + SMPL_REG(x19, PERF_REG_ARM64_X19), + SMPL_REG(x20, PERF_REG_ARM64_X20), + SMPL_REG(x21, PERF_REG_ARM64_X21), + SMPL_REG(x22, PERF_REG_ARM64_X22), + SMPL_REG(x23, PERF_REG_ARM64_X23), + SMPL_REG(x24, PERF_REG_ARM64_X24), + SMPL_REG(x25, PERF_REG_ARM64_X25), + SMPL_REG(x26, PERF_REG_ARM64_X26), + SMPL_REG(x27, PERF_REG_ARM64_X27), + SMPL_REG(x28, PERF_REG_ARM64_X28), + SMPL_REG(x29, PERF_REG_ARM64_X29), + SMPL_REG(lr, PERF_REG_ARM64_LR), + SMPL_REG(sp, PERF_REG_ARM64_SP), + SMPL_REG(pc, PERF_REG_ARM64_PC), SMPL_REG_END }; diff --git a/tools/perf/arch/arm64/util/tsc.c b/tools/perf/arch/arm64/util/tsc.c new file mode 100644 index 0000000000000..cc85bd9e73f1e --- /dev/null +++ b/tools/perf/arch/arm64/util/tsc.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/types.h> + +#include "../../../util/tsc.h" + +u64 rdtsc(void) +{ + u64 val; + + /* + * According to ARM DDI 0487F.c, from Armv8.0 to Armv8.5 inclusive, the + * system counter is at least 56 bits wide; from Armv8.6, the counter + * must be 64 bits wide. So the system counter could be less than 64 + * bits wide and it is attributed with the flag 'cap_user_time_short' + * is true. + */ + asm volatile("mrs %0, cntvct_el0" : "=r" (val)); + + return val; +} diff --git a/tools/perf/arch/mips/Build b/tools/perf/arch/mips/Build index 1bb8bf6d7fd4c..e4e5f33c84d86 100644 --- a/tools/perf/arch/mips/Build +++ b/tools/perf/arch/mips/Build @@ -1 +1 @@ -# empty +perf-y += util/ diff --git a/tools/perf/arch/mips/annotate/instructions.c b/tools/perf/arch/mips/annotate/instructions.c new file mode 100644 index 0000000000000..340993f2a897a --- /dev/null +++ b/tools/perf/arch/mips/annotate/instructions.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 + +static +struct ins_ops *mips__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + if (!strncmp(name, "bal", 3) || + !strncmp(name, "bgezal", 6) || + !strncmp(name, "bltzal", 6) || + !strncmp(name, "bgtzal", 6) || + !strncmp(name, "blezal", 6) || + !strncmp(name, "beqzal", 6) || + !strncmp(name, "bnezal", 6) || + !strncmp(name, "bgtzl", 5) || + !strncmp(name, "bltzl", 5) || + !strncmp(name, "bgezl", 5) || + !strncmp(name, "blezl", 5) || + !strncmp(name, "jialc", 5) || + !strncmp(name, "beql", 4) || + !strncmp(name, "bnel", 4) || + !strncmp(name, "jal", 3)) + ops = &call_ops; + else if (!strncmp(name, "jr", 2)) + ops = &ret_ops; + else if (name[0] == 'j' || name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +static +int mips__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + if (!arch->initialized) { + arch->associate_instruction_ops = mips__associate_ins_ops; + arch->initialized = true; + arch->objdump.comment_char = '#'; + } + + return 0; +} diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index e58d00d62f021..840ea0e59287d 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -14,7 +14,6 @@ PERF_HAVE_JITDUMP := 1 out := $(OUTPUT)arch/powerpc/include/generated/asm header32 := $(out)/syscalls_32.c header64 := $(out)/syscalls_64.c -syskrn := $(srctree)/arch/powerpc/kernel/syscalls/syscall.tbl sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls sysdef := $(sysprf)/syscall.tbl systbl := $(sysprf)/mksyscalltbl @@ -23,15 +22,9 @@ systbl := $(sysprf)/mksyscalltbl _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header64): $(sysdef) $(systbl) - @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ - (diff -B $(sysdef) $(syskrn) >/dev/null) \ - || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true $(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@ $(header32): $(sysdef) $(systbl) - @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ - (diff -B $(sysdef) $(syskrn) >/dev/null) \ - || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true $(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@ clean:: diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 3ca6fe057a0b1..f744eb5cba887 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -9,7 +9,9 @@ # 0 nospu restart_syscall sys_restart_syscall 1 nospu exit sys_exit -2 nospu fork ppc_fork +2 32 fork ppc_fork sys_fork +2 64 fork sys_fork +2 spu fork sys_ni_syscall 3 common read sys_read 4 common write sys_write 5 common open sys_open compat_sys_open @@ -32,7 +34,7 @@ 18 spu oldstat sys_ni_syscall 19 common lseek sys_lseek compat_sys_lseek 20 common getpid sys_getpid -21 nospu mount sys_mount compat_sys_mount +21 nospu mount sys_mount 22 32 umount sys_oldumount 22 64 umount sys_ni_syscall 22 spu umount sys_ni_syscall @@ -158,7 +160,9 @@ 119 32 sigreturn sys_sigreturn compat_sys_sigreturn 119 64 sigreturn sys_ni_syscall 119 spu sigreturn sys_ni_syscall -120 nospu clone ppc_clone +120 32 clone ppc_clone sys_clone +120 64 clone sys_clone +120 spu clone sys_ni_syscall 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common modify_ldt sys_ni_syscall @@ -189,8 +193,8 @@ 142 common _newselect sys_select compat_sys_select 143 common flock sys_flock 144 common msync sys_msync -145 common readv sys_readv compat_sys_readv -146 common writev sys_writev compat_sys_writev +145 common readv sys_readv +146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync 149 nospu _sysctl sys_ni_syscall @@ -240,7 +244,9 @@ 186 spu sendfile sys_sendfile64 187 common getpmsg sys_ni_syscall 188 common putpmsg sys_ni_syscall -189 nospu vfork ppc_vfork +189 32 vfork ppc_vfork sys_vfork +189 64 vfork sys_vfork +189 spu vfork sys_ni_syscall 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit 191 common readahead sys_readahead compat_sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 @@ -316,8 +322,8 @@ 248 32 clock_nanosleep sys_clock_nanosleep_time32 248 64 clock_nanosleep sys_clock_nanosleep 248 spu clock_nanosleep sys_clock_nanosleep -249 32 swapcontext ppc_swapcontext ppc32_swapcontext -249 64 swapcontext ppc64_swapcontext +249 32 swapcontext ppc_swapcontext compat_sys_swapcontext +249 64 swapcontext sys_swapcontext 249 spu swapcontext sys_ni_syscall 250 common tgkill sys_tgkill 251 32 utimes sys_utimes_time32 @@ -363,7 +369,7 @@ 282 common unshare sys_unshare 283 common splice sys_splice 284 common tee sys_tee -285 common vmsplice sys_vmsplice compat_sys_vmsplice +285 common vmsplice sys_vmsplice 286 common openat sys_openat compat_sys_openat 287 common mkdirat sys_mkdirat 288 common mknodat sys_mknodat @@ -443,8 +449,8 @@ 348 common syncfs sys_syncfs 349 common sendmmsg sys_sendmmsg compat_sys_sendmmsg 350 common setns sys_setns -351 nospu process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv -352 nospu process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +351 nospu process_vm_readv sys_process_vm_readv +352 nospu process_vm_writev sys_process_vm_writev 353 nospu finit_module sys_finit_module 354 nospu kcmp sys_kcmp 355 common sched_setattr sys_sched_setattr @@ -456,7 +462,7 @@ 361 common bpf sys_bpf 362 nospu execveat sys_execveat compat_sys_execveat 363 32 switch_endian sys_ni_syscall -363 64 switch_endian ppc_switch_endian +363 64 switch_endian sys_switch_endian 363 spu switch_endian sys_ni_syscall 364 common userfaultfd sys_userfaultfd 365 common membarrier sys_membarrier @@ -516,6 +522,12 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -435 nospu clone3 ppc_clone3 +435 32 clone3 ppc_clone3 sys_clone3 +435 64 clone3 sys_clone3 +435 spu clone3 sys_ni_syscall +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 diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 1a950171a66fa..58b2d610aadbf 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -40,8 +40,11 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused) return bufp; } -int arch_get_runtimeparam(void) +int arch_get_runtimeparam(struct pmu_event *pe) { int count; - return sysfs__read_int("/devices/hv_24x7/interface/sockets", &count) < 0 ? 1 : count; + char path[PATH_MAX] = "/devices/hv_24x7/interface/"; + + atoi(pe->aggr_mode) == PerChip ? strcat(path, "sockets") : strcat(path, "coresperchip"); + return sysfs__read_int(path, &count) < 0 ? 1 : count; } diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 6ac8887be7c94..74bffbea03e20 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -12,7 +12,6 @@ PERF_HAVE_JITDUMP := 1 out := $(OUTPUT)arch/s390/include/generated/asm header := $(out)/syscalls_64.c -syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls sysdef := $(sysprf)/syscall.tbl systbl := $(sysprf)/mksyscalltbl @@ -21,9 +20,6 @@ systbl := $(sysprf)/mksyscalltbl _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) - @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ - (diff -B $(sysdef) $(syskrn) >/dev/null) \ - || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ clean:: diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 6a0bbea225db0..d443423495e56 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -15,86 +15,86 @@ 5 common open sys_open compat_sys_open 6 common close sys_close sys_close 7 common restart_syscall sys_restart_syscall sys_restart_syscall -8 common creat sys_creat compat_sys_creat -9 common link sys_link compat_sys_link -10 common unlink sys_unlink compat_sys_unlink +8 common creat sys_creat sys_creat +9 common link sys_link sys_link +10 common unlink sys_unlink sys_unlink 11 common execve sys_execve compat_sys_execve -12 common chdir sys_chdir compat_sys_chdir -13 32 time - compat_sys_time -14 common mknod sys_mknod compat_sys_mknod -15 common chmod sys_chmod compat_sys_chmod -16 32 lchown - compat_sys_s390_lchown16 +12 common chdir sys_chdir sys_chdir +13 32 time - sys_time32 +14 common mknod sys_mknod sys_mknod +15 common chmod sys_chmod sys_chmod +16 32 lchown - sys_lchown16 19 common lseek sys_lseek compat_sys_lseek 20 common getpid sys_getpid sys_getpid -21 common mount sys_mount compat_sys_mount -22 common umount sys_oldumount compat_sys_oldumount -23 32 setuid - compat_sys_s390_setuid16 -24 32 getuid - compat_sys_s390_getuid16 -25 32 stime - compat_sys_stime +21 common mount sys_mount sys_mount +22 common umount sys_oldumount sys_oldumount +23 32 setuid - sys_setuid16 +24 32 getuid - sys_getuid16 +25 32 stime - sys_stime32 26 common ptrace sys_ptrace compat_sys_ptrace 27 common alarm sys_alarm sys_alarm 29 common pause sys_pause sys_pause -30 common utime sys_utime compat_sys_utime -33 common access sys_access compat_sys_access +30 common utime sys_utime sys_utime32 +33 common access sys_access sys_access 34 common nice sys_nice sys_nice 36 common sync sys_sync sys_sync 37 common kill sys_kill sys_kill -38 common rename sys_rename compat_sys_rename -39 common mkdir sys_mkdir compat_sys_mkdir -40 common rmdir sys_rmdir compat_sys_rmdir +38 common rename sys_rename sys_rename +39 common mkdir sys_mkdir sys_mkdir +40 common rmdir sys_rmdir sys_rmdir 41 common dup sys_dup sys_dup -42 common pipe sys_pipe compat_sys_pipe +42 common pipe sys_pipe sys_pipe 43 common times sys_times compat_sys_times -45 common brk sys_brk compat_sys_brk -46 32 setgid - compat_sys_s390_setgid16 -47 32 getgid - compat_sys_s390_getgid16 -48 common signal sys_signal compat_sys_signal -49 32 geteuid - compat_sys_s390_geteuid16 -50 32 getegid - compat_sys_s390_getegid16 -51 common acct sys_acct compat_sys_acct -52 common umount2 sys_umount compat_sys_umount +45 common brk sys_brk sys_brk +46 32 setgid - sys_setgid16 +47 32 getgid - sys_getgid16 +48 common signal sys_signal sys_signal +49 32 geteuid - sys_geteuid16 +50 32 getegid - sys_getegid16 +51 common acct sys_acct sys_acct +52 common umount2 sys_umount sys_umount 54 common ioctl sys_ioctl compat_sys_ioctl 55 common fcntl sys_fcntl compat_sys_fcntl 57 common setpgid sys_setpgid sys_setpgid 60 common umask sys_umask sys_umask -61 common chroot sys_chroot compat_sys_chroot +61 common chroot sys_chroot sys_chroot 62 common ustat sys_ustat compat_sys_ustat 63 common dup2 sys_dup2 sys_dup2 64 common getppid sys_getppid sys_getppid 65 common getpgrp sys_getpgrp sys_getpgrp 66 common setsid sys_setsid sys_setsid 67 common sigaction sys_sigaction compat_sys_sigaction -70 32 setreuid - compat_sys_s390_setreuid16 -71 32 setregid - compat_sys_s390_setregid16 -72 common sigsuspend sys_sigsuspend compat_sys_sigsuspend +70 32 setreuid - sys_setreuid16 +71 32 setregid - sys_setregid16 +72 common sigsuspend sys_sigsuspend sys_sigsuspend 73 common sigpending sys_sigpending compat_sys_sigpending -74 common sethostname sys_sethostname compat_sys_sethostname +74 common sethostname sys_sethostname sys_sethostname 75 common setrlimit sys_setrlimit compat_sys_setrlimit 76 32 getrlimit - compat_sys_old_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 32 getgroups - compat_sys_s390_getgroups16 -81 32 setgroups - compat_sys_s390_setgroups16 -83 common symlink sys_symlink compat_sys_symlink -85 common readlink sys_readlink compat_sys_readlink -86 common uselib sys_uselib compat_sys_uselib -87 common swapon sys_swapon compat_sys_swapon -88 common reboot sys_reboot compat_sys_reboot +80 32 getgroups - sys_getgroups16 +81 32 setgroups - sys_setgroups16 +83 common symlink sys_symlink sys_symlink +85 common readlink sys_readlink sys_readlink +86 common uselib sys_uselib sys_uselib +87 common swapon sys_swapon sys_swapon +88 common reboot sys_reboot sys_reboot 89 common readdir - compat_sys_old_readdir 90 common mmap sys_old_mmap compat_sys_s390_old_mmap -91 common munmap sys_munmap compat_sys_munmap +91 common munmap sys_munmap sys_munmap 92 common truncate sys_truncate compat_sys_truncate 93 common ftruncate sys_ftruncate compat_sys_ftruncate 94 common fchmod sys_fchmod sys_fchmod -95 32 fchown - compat_sys_s390_fchown16 +95 32 fchown - sys_fchown16 96 common getpriority sys_getpriority sys_getpriority 97 common setpriority sys_setpriority sys_setpriority 99 common statfs sys_statfs compat_sys_statfs 100 common fstatfs sys_fstatfs compat_sys_fstatfs 101 32 ioperm - - 102 common socketcall sys_socketcall compat_sys_socketcall -103 common syslog sys_syslog compat_sys_syslog +103 common syslog sys_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 @@ -104,76 +104,76 @@ 111 common vhangup sys_vhangup sys_vhangup 112 common idle - - 114 common wait4 sys_wait4 compat_sys_wait4 -115 common swapoff sys_swapoff compat_sys_swapoff +115 common swapoff sys_swapoff sys_swapoff 116 common sysinfo sys_sysinfo compat_sys_sysinfo 117 common ipc sys_s390_ipc compat_sys_s390_ipc 118 common fsync sys_fsync sys_fsync 119 common sigreturn sys_sigreturn compat_sys_sigreturn -120 common clone sys_clone compat_sys_clone -121 common setdomainname sys_setdomainname compat_sys_setdomainname -122 common uname sys_newuname compat_sys_newuname -124 common adjtimex sys_adjtimex compat_sys_adjtimex -125 common mprotect sys_mprotect compat_sys_mprotect +120 common clone sys_clone sys_clone +121 common setdomainname sys_setdomainname sys_setdomainname +122 common uname sys_newuname sys_newuname +124 common adjtimex sys_adjtimex sys_adjtimex_time32 +125 common mprotect sys_mprotect sys_mprotect 126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask 127 common create_module - - -128 common init_module sys_init_module compat_sys_init_module -129 common delete_module sys_delete_module compat_sys_delete_module +128 common init_module sys_init_module sys_init_module +129 common delete_module sys_delete_module sys_delete_module 130 common get_kernel_syms - - -131 common quotactl sys_quotactl compat_sys_quotactl +131 common quotactl sys_quotactl sys_quotactl 132 common getpgid sys_getpgid sys_getpgid 133 common fchdir sys_fchdir sys_fchdir -134 common bdflush sys_bdflush compat_sys_bdflush -135 common sysfs sys_sysfs compat_sys_sysfs +134 common bdflush sys_bdflush sys_bdflush +135 common sysfs sys_sysfs sys_sysfs 136 common personality sys_s390_personality sys_s390_personality 137 common afs_syscall - - -138 32 setfsuid - compat_sys_s390_setfsuid16 -139 32 setfsgid - compat_sys_s390_setfsgid16 -140 32 _llseek - compat_sys_llseek +138 32 setfsuid - sys_setfsuid16 +139 32 setfsgid - sys_setfsgid16 +140 32 _llseek - sys_llseek 141 common getdents sys_getdents compat_sys_getdents 142 32 _newselect - compat_sys_select 142 64 select sys_select - 143 common flock sys_flock sys_flock -144 common msync sys_msync compat_sys_msync -145 common readv sys_readv compat_sys_readv -146 common writev sys_writev compat_sys_writev +144 common msync sys_msync sys_msync +145 common readv sys_readv sys_readv +146 common writev sys_writev sys_writev 147 common getsid sys_getsid sys_getsid 148 common fdatasync sys_fdatasync sys_fdatasync 149 common _sysctl - - -150 common mlock sys_mlock compat_sys_mlock -151 common munlock sys_munlock compat_sys_munlock +150 common mlock sys_mlock sys_mlock +151 common munlock sys_munlock sys_munlock 152 common mlockall sys_mlockall sys_mlockall 153 common munlockall sys_munlockall sys_munlockall -154 common sched_setparam sys_sched_setparam compat_sys_sched_setparam -155 common sched_getparam sys_sched_getparam compat_sys_sched_getparam -156 common sched_setscheduler sys_sched_setscheduler compat_sys_sched_setscheduler +154 common sched_setparam sys_sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler sys_sched_setscheduler 157 common sched_getscheduler sys_sched_getscheduler sys_sched_getscheduler 158 common sched_yield sys_sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep compat_sys_nanosleep -163 common mremap sys_mremap compat_sys_mremap -164 32 setresuid - compat_sys_s390_setresuid16 -165 32 getresuid - compat_sys_s390_getresuid16 +161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep sys_nanosleep_time32 +163 common mremap sys_mremap sys_mremap +164 32 setresuid - sys_setresuid16 +165 32 getresuid - sys_getresuid16 167 common query_module - - -168 common poll sys_poll compat_sys_poll +168 common poll sys_poll sys_poll 169 common nfsservctl - - -170 32 setresgid - compat_sys_s390_setresgid16 -171 32 getresgid - compat_sys_s390_getresgid16 -172 common prctl sys_prctl compat_sys_prctl +170 32 setresgid - sys_setresgid16 +171 32 getresgid - sys_getresgid16 +172 common prctl sys_prctl sys_prctl 173 common rt_sigreturn sys_rt_sigreturn 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 compat_sys_rt_sigtimedwait +177 common rt_sigtimedwait sys_rt_sigtimedwait 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_s390_pread64 181 common pwrite64 sys_pwrite64 compat_sys_s390_pwrite64 -182 32 chown - compat_sys_s390_chown16 -183 common getcwd sys_getcwd compat_sys_getcwd -184 common capget sys_capget compat_sys_capget -185 common capset sys_capset compat_sys_capset +182 32 chown - sys_chown16 +183 common getcwd sys_getcwd sys_getcwd +184 common capget sys_capget sys_capget +185 common capset sys_capset sys_capset 186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack 187 common sendfile sys_sendfile64 compat_sys_sendfile 188 common getpmsg - - @@ -187,7 +187,7 @@ 195 32 stat64 - compat_sys_s390_stat64 196 32 lstat64 - compat_sys_s390_lstat64 197 32 fstat64 - compat_sys_s390_fstat64 -198 32 lchown32 - compat_sys_lchown +198 32 lchown32 - sys_lchown 198 64 lchown sys_lchown - 199 32 getuid32 - sys_getuid 199 64 getuid sys_getuid - @@ -201,21 +201,21 @@ 203 64 setreuid sys_setreuid - 204 32 setregid32 - sys_setregid 204 64 setregid sys_setregid - -205 32 getgroups32 - compat_sys_getgroups +205 32 getgroups32 - sys_getgroups 205 64 getgroups sys_getgroups - -206 32 setgroups32 - compat_sys_setgroups +206 32 setgroups32 - sys_setgroups 206 64 setgroups sys_setgroups - 207 32 fchown32 - sys_fchown 207 64 fchown sys_fchown - 208 32 setresuid32 - sys_setresuid 208 64 setresuid sys_setresuid - -209 32 getresuid32 - compat_sys_getresuid +209 32 getresuid32 - sys_getresuid 209 64 getresuid sys_getresuid - 210 32 setresgid32 - sys_setresgid 210 64 setresgid sys_setresgid - -211 32 getresgid32 - compat_sys_getresgid +211 32 getresgid32 - sys_getresgid 211 64 getresgid sys_getresgid - -212 32 chown32 - compat_sys_chown +212 32 chown32 - sys_chown 212 64 chown sys_chown - 213 32 setuid32 - sys_setuid 213 64 setuid sys_setuid - @@ -225,166 +225,222 @@ 215 64 setfsuid sys_setfsuid - 216 32 setfsgid32 - sys_setfsgid 216 64 setfsgid sys_setfsgid - -217 common pivot_root sys_pivot_root compat_sys_pivot_root -218 common mincore sys_mincore compat_sys_mincore -219 common madvise sys_madvise compat_sys_madvise -220 common getdents64 sys_getdents64 compat_sys_getdents64 +217 common pivot_root sys_pivot_root sys_pivot_root +218 common mincore sys_mincore sys_mincore +219 common madvise sys_madvise sys_madvise +220 common getdents64 sys_getdents64 sys_getdents64 221 32 fcntl64 - compat_sys_fcntl64 222 common readahead sys_readahead compat_sys_s390_readahead 223 32 sendfile64 - compat_sys_sendfile64 -224 common setxattr sys_setxattr compat_sys_setxattr -225 common lsetxattr sys_lsetxattr compat_sys_lsetxattr -226 common fsetxattr sys_fsetxattr compat_sys_fsetxattr -227 common getxattr sys_getxattr compat_sys_getxattr -228 common lgetxattr sys_lgetxattr compat_sys_lgetxattr -229 common fgetxattr sys_fgetxattr compat_sys_fgetxattr -230 common listxattr sys_listxattr compat_sys_listxattr -231 common llistxattr sys_llistxattr compat_sys_llistxattr -232 common flistxattr sys_flistxattr compat_sys_flistxattr -233 common removexattr sys_removexattr compat_sys_removexattr -234 common lremovexattr sys_lremovexattr compat_sys_lremovexattr -235 common fremovexattr sys_fremovexattr compat_sys_fremovexattr +224 common setxattr sys_setxattr sys_setxattr +225 common lsetxattr sys_lsetxattr sys_lsetxattr +226 common fsetxattr sys_fsetxattr sys_fsetxattr +227 common getxattr sys_getxattr sys_getxattr +228 common lgetxattr sys_lgetxattr sys_lgetxattr +229 common fgetxattr sys_fgetxattr sys_fgetxattr +230 common listxattr sys_listxattr sys_listxattr +231 common llistxattr sys_llistxattr sys_llistxattr +232 common flistxattr sys_flistxattr sys_flistxattr +233 common removexattr sys_removexattr sys_removexattr +234 common lremovexattr sys_lremovexattr sys_lremovexattr +235 common fremovexattr sys_fremovexattr sys_fremovexattr 236 common gettid sys_gettid sys_gettid 237 common tkill sys_tkill sys_tkill -238 common futex sys_futex compat_sys_futex +238 common futex sys_futex sys_futex_time32 239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity 241 common tgkill sys_tgkill sys_tgkill 243 common io_setup sys_io_setup compat_sys_io_setup -244 common io_destroy sys_io_destroy compat_sys_io_destroy -245 common io_getevents sys_io_getevents compat_sys_io_getevents +244 common io_destroy sys_io_destroy sys_io_destroy +245 common io_getevents sys_io_getevents sys_io_getevents_time32 246 common io_submit sys_io_submit compat_sys_io_submit -247 common io_cancel sys_io_cancel compat_sys_io_cancel +247 common io_cancel sys_io_cancel sys_io_cancel 248 common exit_group sys_exit_group sys_exit_group 249 common epoll_create sys_epoll_create sys_epoll_create -250 common epoll_ctl sys_epoll_ctl compat_sys_epoll_ctl -251 common epoll_wait sys_epoll_wait compat_sys_epoll_wait -252 common set_tid_address sys_set_tid_address compat_sys_set_tid_address +250 common epoll_ctl sys_epoll_ctl sys_epoll_ctl +251 common epoll_wait sys_epoll_wait sys_epoll_wait +252 common set_tid_address sys_set_tid_address sys_set_tid_address 253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64 254 common timer_create sys_timer_create compat_sys_timer_create -255 common timer_settime sys_timer_settime compat_sys_timer_settime -256 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +255 common timer_settime sys_timer_settime sys_timer_settime32 +256 common timer_gettime sys_timer_gettime sys_timer_gettime32 257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun 258 common timer_delete sys_timer_delete sys_timer_delete -259 common clock_settime sys_clock_settime compat_sys_clock_settime -260 common clock_gettime sys_clock_gettime compat_sys_clock_gettime -261 common clock_getres sys_clock_getres compat_sys_clock_getres -262 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +259 common clock_settime sys_clock_settime sys_clock_settime32 +260 common clock_gettime sys_clock_gettime sys_clock_gettime32 +261 common clock_getres sys_clock_getres sys_clock_getres_time32 +262 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 264 32 fadvise64_64 - compat_sys_s390_fadvise64_64 265 common statfs64 sys_statfs64 compat_sys_statfs64 266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 -267 common remap_file_pages sys_remap_file_pages compat_sys_remap_file_pages +267 common remap_file_pages sys_remap_file_pages sys_remap_file_pages 268 common mbind sys_mbind compat_sys_mbind 269 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy 270 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy 271 common mq_open sys_mq_open compat_sys_mq_open -272 common mq_unlink sys_mq_unlink compat_sys_mq_unlink -273 common mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend -274 common mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +272 common mq_unlink sys_mq_unlink sys_mq_unlink +273 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 +274 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 275 common mq_notify sys_mq_notify compat_sys_mq_notify 276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 277 common kexec_load sys_kexec_load compat_sys_kexec_load -278 common add_key sys_add_key compat_sys_add_key -279 common request_key sys_request_key compat_sys_request_key +278 common add_key sys_add_key sys_add_key +279 common request_key sys_request_key sys_request_key 280 common keyctl sys_keyctl compat_sys_keyctl 281 common waitid sys_waitid compat_sys_waitid 282 common ioprio_set sys_ioprio_set sys_ioprio_set 283 common ioprio_get sys_ioprio_get sys_ioprio_get 284 common inotify_init sys_inotify_init sys_inotify_init -285 common inotify_add_watch sys_inotify_add_watch compat_sys_inotify_add_watch +285 common inotify_add_watch sys_inotify_add_watch sys_inotify_add_watch 286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch 287 common migrate_pages sys_migrate_pages compat_sys_migrate_pages 288 common openat sys_openat compat_sys_openat -289 common mkdirat sys_mkdirat compat_sys_mkdirat -290 common mknodat sys_mknodat compat_sys_mknodat -291 common fchownat sys_fchownat compat_sys_fchownat -292 common futimesat sys_futimesat compat_sys_futimesat +289 common mkdirat sys_mkdirat sys_mkdirat +290 common mknodat sys_mknodat sys_mknodat +291 common fchownat sys_fchownat sys_fchownat +292 common futimesat sys_futimesat sys_futimesat_time32 293 32 fstatat64 - compat_sys_s390_fstatat64 293 64 newfstatat sys_newfstatat - -294 common unlinkat sys_unlinkat compat_sys_unlinkat -295 common renameat sys_renameat compat_sys_renameat -296 common linkat sys_linkat compat_sys_linkat -297 common symlinkat sys_symlinkat compat_sys_symlinkat -298 common readlinkat sys_readlinkat compat_sys_readlinkat -299 common fchmodat sys_fchmodat compat_sys_fchmodat -300 common faccessat sys_faccessat compat_sys_faccessat -301 common pselect6 sys_pselect6 compat_sys_pselect6 -302 common ppoll sys_ppoll compat_sys_ppoll -303 common unshare sys_unshare compat_sys_unshare +294 common unlinkat sys_unlinkat sys_unlinkat +295 common renameat sys_renameat sys_renameat +296 common linkat sys_linkat sys_linkat +297 common symlinkat sys_symlinkat sys_symlinkat +298 common readlinkat sys_readlinkat sys_readlinkat +299 common fchmodat sys_fchmodat sys_fchmodat +300 common faccessat sys_faccessat sys_faccessat +301 common pselect6 sys_pselect6 compat_sys_pselect6_time32 +302 common ppoll sys_ppoll compat_sys_ppoll_time32 +303 common unshare sys_unshare sys_unshare 304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list 305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list -306 common splice sys_splice compat_sys_splice +306 common splice sys_splice sys_splice 307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range -308 common tee sys_tee compat_sys_tee -309 common vmsplice sys_vmsplice compat_sys_vmsplice +308 common tee sys_tee sys_tee +309 common vmsplice sys_vmsplice sys_vmsplice 310 common move_pages sys_move_pages compat_sys_move_pages -311 common getcpu sys_getcpu compat_sys_getcpu +311 common getcpu sys_getcpu sys_getcpu 312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -313 common utimes sys_utimes compat_sys_utimes +313 common utimes sys_utimes sys_utimes_time32 314 common fallocate sys_fallocate compat_sys_s390_fallocate -315 common utimensat sys_utimensat compat_sys_utimensat +315 common utimensat sys_utimensat sys_utimensat_time32 316 common signalfd sys_signalfd compat_sys_signalfd 317 common timerfd - - 318 common eventfd sys_eventfd sys_eventfd 319 common timerfd_create sys_timerfd_create sys_timerfd_create -320 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime -321 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +320 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 +321 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 322 common signalfd4 sys_signalfd4 compat_sys_signalfd4 323 common eventfd2 sys_eventfd2 sys_eventfd2 324 common inotify_init1 sys_inotify_init1 sys_inotify_init1 -325 common pipe2 sys_pipe2 compat_sys_pipe2 +325 common pipe2 sys_pipe2 sys_pipe2 326 common dup3 sys_dup3 sys_dup3 327 common epoll_create1 sys_epoll_create1 sys_epoll_create1 328 common preadv sys_preadv compat_sys_preadv 329 common pwritev sys_pwritev compat_sys_pwritev 330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo -331 common perf_event_open sys_perf_event_open compat_sys_perf_event_open +331 common perf_event_open sys_perf_event_open sys_perf_event_open 332 common fanotify_init sys_fanotify_init sys_fanotify_init 333 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark -334 common prlimit64 sys_prlimit64 compat_sys_prlimit64 -335 common name_to_handle_at sys_name_to_handle_at compat_sys_name_to_handle_at +334 common prlimit64 sys_prlimit64 sys_prlimit64 +335 common name_to_handle_at sys_name_to_handle_at sys_name_to_handle_at 336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -337 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +337 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 338 common syncfs sys_syncfs sys_syncfs 339 common setns sys_setns sys_setns -340 common process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv -341 common process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +340 common process_vm_readv sys_process_vm_readv sys_process_vm_readv +341 common process_vm_writev sys_process_vm_writev sys_process_vm_writev 342 common s390_runtime_instr sys_s390_runtime_instr sys_s390_runtime_instr -343 common kcmp sys_kcmp compat_sys_kcmp -344 common finit_module sys_finit_module compat_sys_finit_module -345 common sched_setattr sys_sched_setattr compat_sys_sched_setattr -346 common sched_getattr sys_sched_getattr compat_sys_sched_getattr -347 common renameat2 sys_renameat2 compat_sys_renameat2 -348 common seccomp sys_seccomp compat_sys_seccomp -349 common getrandom sys_getrandom compat_sys_getrandom -350 common memfd_create sys_memfd_create compat_sys_memfd_create -351 common bpf sys_bpf compat_sys_bpf -352 common s390_pci_mmio_write sys_s390_pci_mmio_write compat_sys_s390_pci_mmio_write -353 common s390_pci_mmio_read sys_s390_pci_mmio_read compat_sys_s390_pci_mmio_read +343 common kcmp sys_kcmp sys_kcmp +344 common finit_module sys_finit_module sys_finit_module +345 common sched_setattr sys_sched_setattr sys_sched_setattr +346 common sched_getattr sys_sched_getattr sys_sched_getattr +347 common renameat2 sys_renameat2 sys_renameat2 +348 common seccomp sys_seccomp sys_seccomp +349 common getrandom sys_getrandom sys_getrandom +350 common memfd_create sys_memfd_create sys_memfd_create +351 common bpf sys_bpf sys_bpf +352 common s390_pci_mmio_write sys_s390_pci_mmio_write sys_s390_pci_mmio_write +353 common s390_pci_mmio_read sys_s390_pci_mmio_read sys_s390_pci_mmio_read 354 common execveat sys_execveat compat_sys_execveat 355 common userfaultfd sys_userfaultfd sys_userfaultfd 356 common membarrier sys_membarrier sys_membarrier -357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg 359 common socket sys_socket sys_socket -360 common socketpair sys_socketpair compat_sys_socketpair -361 common bind sys_bind compat_sys_bind -362 common connect sys_connect compat_sys_connect +360 common socketpair sys_socketpair sys_socketpair +361 common bind sys_bind sys_bind +362 common connect sys_connect sys_connect 363 common listen sys_listen sys_listen -364 common accept4 sys_accept4 compat_sys_accept4 +364 common accept4 sys_accept4 sys_accept4 365 common getsockopt sys_getsockopt sys_getsockopt 366 common setsockopt sys_setsockopt sys_setsockopt -367 common getsockname sys_getsockname compat_sys_getsockname -368 common getpeername sys_getpeername compat_sys_getpeername -369 common sendto sys_sendto compat_sys_sendto +367 common getsockname sys_getsockname sys_getsockname +368 common getpeername sys_getpeername sys_getpeername +369 common sendto sys_sendto sys_sendto 370 common sendmsg sys_sendmsg compat_sys_sendmsg 371 common recvfrom sys_recvfrom compat_sys_recvfrom 372 common recvmsg sys_recvmsg compat_sys_recvmsg 373 common shutdown sys_shutdown sys_shutdown -374 common mlock2 sys_mlock2 compat_sys_mlock2 -375 common copy_file_range sys_copy_file_range compat_sys_copy_file_range +374 common mlock2 sys_mlock2 sys_mlock2 +375 common copy_file_range sys_copy_file_range sys_copy_file_range 376 common preadv2 sys_preadv2 compat_sys_preadv2 377 common pwritev2 sys_pwritev2 compat_sys_pwritev2 -378 common s390_guarded_storage sys_s390_guarded_storage compat_sys_s390_guarded_storage -379 common statx sys_statx compat_sys_statx -380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi +378 common s390_guarded_storage sys_s390_guarded_storage sys_s390_guarded_storage +379 common statx sys_statx sys_statx +380 common s390_sthyi sys_s390_sthyi sys_s390_sthyi +381 common kexec_file_load sys_kexec_file_load sys_kexec_file_load +382 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +383 common rseq sys_rseq sys_rseq +384 common pkey_mprotect sys_pkey_mprotect sys_pkey_mprotect +385 common pkey_alloc sys_pkey_alloc sys_pkey_alloc +386 common pkey_free sys_pkey_free sys_pkey_free +# room for arch specific syscalls +392 64 semtimedop sys_semtimedop - +393 common semget sys_semget sys_semget +394 common semctl sys_semctl compat_sys_semctl +395 common shmget sys_shmget sys_shmget +396 common shmctl sys_shmctl compat_sys_shmctl +397 common shmat sys_shmat compat_sys_shmat +398 common shmdt sys_shmdt sys_shmdt +399 common msgget sys_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 +404 32 clock_settime64 - sys_clock_settime +405 32 clock_adjtime64 - sys_clock_adjtime +406 32 clock_getres_time64 - sys_clock_getres +407 32 clock_nanosleep_time64 - sys_clock_nanosleep +408 32 timer_gettime64 - sys_timer_gettime +409 32 timer_settime64 - sys_timer_settime +410 32 timerfd_gettime64 - sys_timerfd_gettime +411 32 timerfd_settime64 - sys_timerfd_settime +412 32 utimensat_time64 - sys_utimensat +413 32 pselect6_time64 - compat_sys_pselect6_time64 +414 32 ppoll_time64 - compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 - sys_io_pgetevents +417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 - sys_mq_timedsend +419 32 mq_timedreceive_time64 - sys_mq_timedreceive +420 32 semtimedop_time64 - sys_semtimedop +421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 - sys_futex +423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree sys_open_tree +429 common move_mount sys_move_mount sys_move_mount +430 common fsopen sys_fsopen sys_fsopen +431 common fsconfig sys_fsconfig sys_fsconfig +432 common fsmount sys_fsmount sys_fsmount +433 common fspick sys_fspick sys_fspick +434 common pidfd_open sys_pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 sys_clone3 +436 common close_range sys_close_range sys_close_range +437 common openat2 sys_openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 7eb5621c021d8..24ea12ec7e02b 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -110,6 +110,7 @@ static struct ins x86__instructions[] = { { .name = "por", .ops = &mov_ops, }, { .name = "rclb", .ops = &mov_ops, }, { .name = "rcll", .ops = &mov_ops, }, + { .name = "ret", .ops = &ret_ops, }, { .name = "retq", .ops = &ret_ops, }, { .name = "sbb", .ops = &mov_ops, }, { .name = "sbbl", .ops = &mov_ops, }, diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index f30d6ae9a6883..78672124d28be 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -361,18 +361,20 @@ 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 # -# x32-specific system call numbers start at 512 to avoid cache impact -# for native 64-bit operation. The __x32_compat_sys stubs are created -# on-the-fly for compat_sys_*() compatibility system calls if X86_X32 -# is defined. +# Due to a historical design error, certain syscalls are numbered differently +# in x32 as compared to native x86_64. These syscalls have numbers 512-547. +# Do not add new syscalls to this range. Numbers 548 and above are available +# for non-x32 use. # 512 x32 rt_sigaction compat_sys_rt_sigaction 513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn 514 x32 ioctl compat_sys_ioctl -515 x32 readv compat_sys_readv -516 x32 writev compat_sys_writev +515 x32 readv sys_readv +516 x32 writev sys_writev 517 x32 recvfrom compat_sys_recvfrom 518 x32 sendmsg compat_sys_sendmsg 519 x32 recvmsg compat_sys_recvmsg @@ -388,15 +390,15 @@ 529 x32 waitid compat_sys_waitid 530 x32 set_robust_list compat_sys_set_robust_list 531 x32 get_robust_list compat_sys_get_robust_list -532 x32 vmsplice compat_sys_vmsplice +532 x32 vmsplice sys_vmsplice 533 x32 move_pages compat_sys_move_pages 534 x32 preadv compat_sys_preadv64 535 x32 pwritev compat_sys_pwritev64 536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo 537 x32 recvmmsg compat_sys_recvmmsg_time64 538 x32 sendmmsg compat_sys_sendmmsg -539 x32 process_vm_readv compat_sys_process_vm_readv -540 x32 process_vm_writev compat_sys_process_vm_writev +539 x32 process_vm_readv sys_process_vm_readv +540 x32 process_vm_writev sys_process_vm_writev 541 x32 setsockopt sys_setsockopt 542 x32 getsockopt sys_getsockopt 543 x32 io_setup compat_sys_io_setup @@ -404,3 +406,5 @@ 545 x32 execveat compat_sys_execveat 546 x32 preadv2 compat_sys_preadv64v2 547 x32 pwritev2 compat_sys_pwritev64v2 +# This is the end of the legacy x32 range. Numbers 548 and above are +# not special and are not to be used for x32-specific syscalls. diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index c41c5affe4be7..6a54b94f1c25b 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -7,7 +7,6 @@ struct test; /* Tests */ int test__rdpmc(struct test *test __maybe_unused, int subtest); -int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); int test__intel_pt_pkt_decoder(struct test *test, int subtest); int test__bp_modify(struct test *test, int subtest); diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 2997c506550c1..36d4f248b51db 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -3,6 +3,5 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o perf-y += arch-tests.o perf-y += rdpmc.o -perf-y += perf-time-to-tsc.o perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o perf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index 6763135aec17b..bc25d727b4e9a 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -8,10 +8,6 @@ struct test arch_tests[] = { .desc = "x86 rdpmc", .func = test__rdpmc, }, - { - .desc = "Convert perf time to TSC", - .func = test__perf_time_to_tsc, - }, #ifdef HAVE_DWARF_UNWIND_SUPPORT { .desc = "DWARF unwind", diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 4e40402a4f81c..478078fb0f221 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -38,6 +38,13 @@ static int sample_ustack(struct perf_sample *sample, stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); +#ifdef MEMORY_SANITIZER + /* + * Copying the stack may copy msan poison, avoid false positives in the + * unwinder by removing the poison here. + */ + __msan_unpoison(buf, stack_size); +#endif stack->data = (char *) buf; stack->size = stack_size; return 0; diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 3ec562a2aabaa..27dd8cf9e0609 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -52,7 +52,7 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt evlist = evlist__new(); if (!evlist) { - pr_debug("perf_evlist__new failed\n"); + pr_debug("evlist__new failed\n"); return TEST_FAIL; } diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 47f9c56e744f8..347c39b960eba 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -3,7 +3,7 @@ perf-y += tsc.o perf-y += pmu.o perf-y += kvm-stat.o perf-y += perf_regs.o -perf-y += group.o +perf-y += topdown.o perf-y += machine.o perf-y += event.o diff --git a/tools/perf/arch/x86/util/group.c b/tools/perf/arch/x86/util/group.c deleted file mode 100644 index e2f8034b89733..0000000000000 --- a/tools/perf/arch/x86/util/group.c +++ /dev/null @@ -1,28 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <stdio.h> -#include "api/fs/fs.h" -#include "util/group.h" - -/* - * Check whether we can use a group for top down. - * Without a group may get bad results due to multiplexing. - */ -bool arch_topdown_check_group(bool *warn) -{ - int n; - - if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0) - return false; - if (n > 0) { - *warn = true; - return false; - } - return true; -} - -void arch_topdown_group_warn(void) -{ - fprintf(stderr, - "nmi_watchdog enabled with topdown. May give wrong results.\n" - "Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n"); -} diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 0dc09b5809c12..4a76d49d25d60 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -218,7 +218,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, * To obtain the auxtrace buffer file descriptor, the auxtrace event * must come first. */ - perf_evlist__to_front(evlist, intel_bts_evsel); + evlist__to_front(evlist, intel_bts_evsel); /* * In the case of per-cpu mmaps, we need the CPU on the * AUX event. @@ -238,7 +238,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 082e5f2a415a3..a6420c6479597 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -416,7 +416,7 @@ static int intel_pt_track_switches(struct evlist *evlist) struct evsel *evsel; int err; - if (!perf_evlist__can_select_event(evlist, sched_switch)) + if (!evlist__can_select_event(evlist, sched_switch)) return -EPERM; err = parse_events(evlist, sched_switch, NULL); @@ -846,7 +846,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * To obtain the auxtrace buffer file descriptor, the auxtrace * event must come first. */ - perf_evlist__to_front(evlist, intel_pt_evsel); + evlist__to_front(evlist, intel_pt_evsel); /* * In the case of per-cpu mmaps, we need the CPU on the * AUX event. @@ -865,7 +865,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c new file mode 100644 index 0000000000000..2f3d96aa92a58 --- /dev/null +++ b/tools/perf/arch/x86/util/topdown.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include "api/fs/fs.h" +#include "util/pmu.h" +#include "util/topdown.h" + +/* + * Check whether we can use a group for top down. + * Without a group may get bad results due to multiplexing. + */ +bool arch_topdown_check_group(bool *warn) +{ + int n; + + if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0) + return false; + if (n > 0) { + *warn = true; + return false; + } + return true; +} + +void arch_topdown_group_warn(void) +{ + fprintf(stderr, + "nmi_watchdog enabled with topdown. May give wrong results.\n" + "Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n"); +} + +#define TOPDOWN_SLOTS 0x0400 + +static bool is_topdown_slots_event(struct evsel *counter) +{ + if (!counter->pmu_name) + return false; + + if (strcmp(counter->pmu_name, "cpu")) + return false; + + if (counter->core.attr.config == TOPDOWN_SLOTS) + return true; + + return false; +} + +/* + * Check whether a topdown group supports sample-read. + * + * Only Topdown metic supports sample-read. The slots + * event must be the leader of the topdown group. + */ + +bool arch_topdown_sample_read(struct evsel *leader) +{ + if (!pmu_have_event("cpu", "slots")) + return false; + + if (is_topdown_slots_event(leader)) + return true; + + return false; +} diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 2f55afb14e1f5..559365f8fe52f 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -1,45 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#include <stdbool.h> -#include <errno.h> - -#include <linux/stddef.h> -#include <linux/perf_event.h> - #include <linux/types.h> -#include <asm/barrier.h> -#include "../../../util/debug.h" -#include "../../../util/event.h" -#include "../../../util/synthetic-events.h" -#include "../../../util/tsc.h" - -int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, - struct perf_tsc_conversion *tc) -{ - bool cap_user_time_zero; - u32 seq; - int i = 0; - - while (1) { - seq = pc->lock; - rmb(); - tc->time_mult = pc->time_mult; - tc->time_shift = pc->time_shift; - tc->time_zero = pc->time_zero; - cap_user_time_zero = pc->cap_user_time_zero; - rmb(); - if (pc->lock == seq && !(seq & 1)) - break; - if (++i > 10000) { - pr_debug("failed to get perf_event_mmap_page lock\n"); - return -EINVAL; - } - } - if (!cap_user_time_zero) - return -EOPNOTSUPP; - - return 0; -} +#include "../../../util/tsc.h" u64 rdtsc(void) { @@ -49,36 +11,3 @@ u64 rdtsc(void) return low | ((u64)high) << 32; } - -int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, - struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - union perf_event event = { - .time_conv = { - .header = { - .type = PERF_RECORD_TIME_CONV, - .size = sizeof(struct perf_record_time_conv), - }, - }, - }; - struct perf_tsc_conversion tc; - int err; - - if (!pc) - return 0; - err = perf_read_tsc_conversion(pc, &tc); - if (err == -EOPNOTSUPP) - return 0; - if (err) - return err; - - pr_debug2("Synthesizing TSC conversion information\n"); - - event.time_conv.time_mult = tc.time_mult; - event.time_conv.time_shift = tc.time_shift; - event.time_conv.time_zero = tc.time_zero; - - return process(tool, &event, NULL, machine); -} diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index dd68a40a790c5..e43f46931b41b 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -12,8 +12,8 @@ perf-y += epoll-ctl.o perf-y += synthesize.o perf-y += kallsyms-parse.o perf-y += find-bit-bench.o +perf-y += inject-buildid.o -perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 2804812d4154c..eac36afab2b39 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -47,6 +47,7 @@ int bench_epoll_wait(int argc, const char **argv); int bench_epoll_ctl(int argc, const char **argv); int bench_synthesize(int argc, const char **argv); int bench_kallsyms_parse(int argc, const char **argv); +int bench_inject_build_id(int argc, const char **argv); #define BENCH_FORMAT_DEFAULT_STR "default" #define BENCH_FORMAT_DEFAULT 0 diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c new file mode 100644 index 0000000000000..280227e3ffd7a --- /dev/null +++ b/tools/perf/bench/inject-buildid.c @@ -0,0 +1,476 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdlib.h> +#include <stddef.h> +#include <ftw.h> +#include <fcntl.h> +#include <errno.h> +#include <unistd.h> +#include <pthread.h> +#include <sys/mman.h> +#include <sys/wait.h> +#include <linux/kernel.h> +#include <linux/time64.h> +#include <linux/list.h> +#include <linux/err.h> +#include <internal/lib.h> +#include <subcmd/parse-options.h> + +#include "bench.h" +#include "util/data.h" +#include "util/stat.h" +#include "util/debug.h" +#include "util/event.h" +#include "util/symbol.h" +#include "util/session.h" +#include "util/build-id.h" +#include "util/synthetic-events.h" + +#define MMAP_DEV_MAJOR 8 +#define DSO_MMAP_RATIO 4 + +static unsigned int iterations = 100; +static unsigned int nr_mmaps = 100; +static unsigned int nr_samples = 100; /* samples per mmap */ + +static u64 bench_sample_type; +static u16 bench_id_hdr_size; + +struct bench_data { + int pid; + int input_pipe[2]; + int output_pipe[2]; + pthread_t th; +}; + +struct bench_dso { + struct list_head list; + char *name; + int ino; +}; + +static int nr_dsos; +static struct bench_dso *dsos; + +extern int cmd_inject(int argc, const char *argv[]); + +static const struct option options[] = { + OPT_UINTEGER('i', "iterations", &iterations, + "Number of iterations used to compute average (default: 100)"), + OPT_UINTEGER('m', "nr-mmaps", &nr_mmaps, + "Number of mmap events for each iteration (default: 100)"), + OPT_UINTEGER('n', "nr-samples", &nr_samples, + "Number of sample events per mmap event (default: 100)"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show iteration count, DSO name, etc)"), + OPT_END() +}; + +static const char *const bench_usage[] = { + "perf bench internals inject-build-id <options>", + NULL +}; + +/* + * Helper for collect_dso that adds the given file as a dso to dso_list + * if it contains a build-id. Stops after collecting 4 times more than + * we need (for MMAP2 events). + */ +static int add_dso(const char *fpath, const struct stat *sb __maybe_unused, + int typeflag, struct FTW *ftwbuf __maybe_unused) +{ + struct bench_dso *dso = &dsos[nr_dsos]; + struct build_id bid; + + if (typeflag == FTW_D || typeflag == FTW_SL) + return 0; + + if (filename__read_build_id(fpath, &bid) < 0) + return 0; + + dso->name = realpath(fpath, NULL); + if (dso->name == NULL) + return -1; + + dso->ino = nr_dsos++; + pr_debug2(" Adding DSO: %s\n", fpath); + + /* stop if we collected enough DSOs */ + if ((unsigned int)nr_dsos == DSO_MMAP_RATIO * nr_mmaps) + return 1; + + return 0; +} + +static void collect_dso(void) +{ + dsos = calloc(nr_mmaps * DSO_MMAP_RATIO, sizeof(*dsos)); + if (dsos == NULL) { + printf(" Memory allocation failed\n"); + exit(1); + } + + if (nftw("/usr/lib/", add_dso, 10, FTW_PHYS) < 0) + return; + + pr_debug(" Collected %d DSOs\n", nr_dsos); +} + +static void release_dso(void) +{ + int i; + + for (i = 0; i < nr_dsos; i++) { + struct bench_dso *dso = &dsos[i]; + + free(dso->name); + } + free(dsos); +} + +/* Fake address used by mmap and sample events */ +static u64 dso_map_addr(struct bench_dso *dso) +{ + return 0x400000ULL + dso->ino * 8192ULL; +} + +static u32 synthesize_attr(struct bench_data *data) +{ + union perf_event event; + + memset(&event, 0, sizeof(event.attr) + sizeof(u64)); + + event.header.type = PERF_RECORD_HEADER_ATTR; + event.header.size = sizeof(event.attr) + sizeof(u64); + + event.attr.attr.type = PERF_TYPE_SOFTWARE; + event.attr.attr.config = PERF_COUNT_SW_TASK_CLOCK; + event.attr.attr.exclude_kernel = 1; + event.attr.attr.sample_id_all = 1; + event.attr.attr.sample_type = bench_sample_type; + + return writen(data->input_pipe[1], &event, event.header.size); +} + +static u32 synthesize_fork(struct bench_data *data) +{ + union perf_event event; + + memset(&event, 0, sizeof(event.fork) + bench_id_hdr_size); + + event.header.type = PERF_RECORD_FORK; + event.header.misc = PERF_RECORD_MISC_FORK_EXEC; + event.header.size = sizeof(event.fork) + bench_id_hdr_size; + + event.fork.ppid = 1; + event.fork.ptid = 1; + event.fork.pid = data->pid; + event.fork.tid = data->pid; + + return writen(data->input_pipe[1], &event, event.header.size); +} + +static u32 synthesize_mmap(struct bench_data *data, struct bench_dso *dso, + u64 timestamp) +{ + union perf_event event; + size_t len = offsetof(struct perf_record_mmap2, filename); + u64 *id_hdr_ptr = (void *)&event; + int ts_idx; + + len += roundup(strlen(dso->name) + 1, 8) + bench_id_hdr_size; + + memset(&event, 0, min(len, sizeof(event.mmap2))); + + event.header.type = PERF_RECORD_MMAP2; + event.header.misc = PERF_RECORD_MISC_USER; + event.header.size = len; + + event.mmap2.pid = data->pid; + event.mmap2.tid = data->pid; + event.mmap2.maj = MMAP_DEV_MAJOR; + event.mmap2.ino = dso->ino; + + strcpy(event.mmap2.filename, dso->name); + + event.mmap2.start = dso_map_addr(dso); + event.mmap2.len = 4096; + event.mmap2.prot = PROT_EXEC; + + if (len > sizeof(event.mmap2)) { + /* write mmap2 event first */ + writen(data->input_pipe[1], &event, len - bench_id_hdr_size); + /* zero-fill sample id header */ + memset(id_hdr_ptr, 0, bench_id_hdr_size); + /* put timestamp in the right position */ + ts_idx = (bench_id_hdr_size / sizeof(u64)) - 2; + id_hdr_ptr[ts_idx] = timestamp; + writen(data->input_pipe[1], id_hdr_ptr, bench_id_hdr_size); + } else { + ts_idx = (len / sizeof(u64)) - 2; + id_hdr_ptr[ts_idx] = timestamp; + writen(data->input_pipe[1], &event, len); + } + return len; +} + +static u32 synthesize_sample(struct bench_data *data, struct bench_dso *dso, + u64 timestamp) +{ + union perf_event event; + struct perf_sample sample = { + .tid = data->pid, + .pid = data->pid, + .ip = dso_map_addr(dso), + .time = timestamp, + }; + + event.header.type = PERF_RECORD_SAMPLE; + event.header.misc = PERF_RECORD_MISC_USER; + event.header.size = perf_event__sample_event_size(&sample, bench_sample_type, 0); + + perf_event__synthesize_sample(&event, bench_sample_type, 0, &sample); + + return writen(data->input_pipe[1], &event, event.header.size); +} + +static u32 synthesize_flush(struct bench_data *data) +{ + struct perf_event_header header = { + .size = sizeof(header), + .type = PERF_RECORD_FINISHED_ROUND, + }; + + return writen(data->input_pipe[1], &header, header.size); +} + +static void *data_reader(void *arg) +{ + struct bench_data *data = arg; + char buf[8192]; + int flag; + int n; + + flag = fcntl(data->output_pipe[0], F_GETFL); + fcntl(data->output_pipe[0], F_SETFL, flag | O_NONBLOCK); + + /* read out data from child */ + while (true) { + n = read(data->output_pipe[0], buf, sizeof(buf)); + if (n > 0) + continue; + if (n == 0) + break; + + if (errno != EINTR && errno != EAGAIN) + break; + + usleep(100); + } + + close(data->output_pipe[0]); + return NULL; +} + +static int setup_injection(struct bench_data *data, bool build_id_all) +{ + int ready_pipe[2]; + int dev_null_fd; + char buf; + + if (pipe(ready_pipe) < 0) + return -1; + + if (pipe(data->input_pipe) < 0) + return -1; + + if (pipe(data->output_pipe) < 0) + return -1; + + data->pid = fork(); + if (data->pid < 0) + return -1; + + if (data->pid == 0) { + const char **inject_argv; + int inject_argc = 2; + + close(data->input_pipe[1]); + close(data->output_pipe[0]); + close(ready_pipe[0]); + + dup2(data->input_pipe[0], STDIN_FILENO); + close(data->input_pipe[0]); + dup2(data->output_pipe[1], STDOUT_FILENO); + close(data->output_pipe[1]); + + dev_null_fd = open("/dev/null", O_WRONLY); + if (dev_null_fd < 0) + exit(1); + + dup2(dev_null_fd, STDERR_FILENO); + + if (build_id_all) + inject_argc++; + + inject_argv = calloc(inject_argc + 1, sizeof(*inject_argv)); + if (inject_argv == NULL) + exit(1); + + inject_argv[0] = strdup("inject"); + inject_argv[1] = strdup("-b"); + if (build_id_all) + inject_argv[2] = strdup("--buildid-all"); + + /* signal that we're ready to go */ + close(ready_pipe[1]); + + cmd_inject(inject_argc, inject_argv); + + exit(0); + } + + pthread_create(&data->th, NULL, data_reader, data); + + close(ready_pipe[1]); + close(data->input_pipe[0]); + close(data->output_pipe[1]); + + /* wait for child ready */ + if (read(ready_pipe[0], &buf, 1) < 0) + return -1; + close(ready_pipe[0]); + + return 0; +} + +static int inject_build_id(struct bench_data *data, u64 *max_rss) +{ + int status; + unsigned int i, k; + struct rusage rusage; + u64 len = 0; + + /* this makes the child to run */ + if (perf_header__write_pipe(data->input_pipe[1]) < 0) + return -1; + + len += synthesize_attr(data); + len += synthesize_fork(data); + + for (i = 0; i < nr_mmaps; i++) { + int idx = rand() % (nr_dsos - 1); + struct bench_dso *dso = &dsos[idx]; + u64 timestamp = rand() % 1000000; + + pr_debug2(" [%d] injecting: %s\n", i+1, dso->name); + len += synthesize_mmap(data, dso, timestamp); + + for (k = 0; k < nr_samples; k++) + len += synthesize_sample(data, dso, timestamp + k * 1000); + + if ((i + 1) % 10 == 0) + len += synthesize_flush(data); + } + + /* tihs makes the child to finish */ + close(data->input_pipe[1]); + + wait4(data->pid, &status, 0, &rusage); + *max_rss = rusage.ru_maxrss; + + pr_debug(" Child %d exited with %d\n", data->pid, status); + + return 0; +} + +static void do_inject_loop(struct bench_data *data, bool build_id_all) +{ + unsigned int i; + struct stats time_stats, mem_stats; + double time_average, time_stddev; + double mem_average, mem_stddev; + + init_stats(&time_stats); + init_stats(&mem_stats); + + pr_debug(" Build-id%s injection benchmark\n", build_id_all ? "-all" : ""); + + for (i = 0; i < iterations; i++) { + struct timeval start, end, diff; + u64 runtime_us, max_rss; + + pr_debug(" Iteration #%d\n", i+1); + + if (setup_injection(data, build_id_all) < 0) { + printf(" Build-id injection setup failed\n"); + break; + } + + gettimeofday(&start, NULL); + if (inject_build_id(data, &max_rss) < 0) { + printf(" Build-id injection failed\n"); + break; + } + + gettimeofday(&end, NULL); + timersub(&end, &start, &diff); + runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; + update_stats(&time_stats, runtime_us); + update_stats(&mem_stats, max_rss); + + pthread_join(data->th, NULL); + } + + time_average = avg_stats(&time_stats) / USEC_PER_MSEC; + time_stddev = stddev_stats(&time_stats) / USEC_PER_MSEC; + printf(" Average build-id%s injection took: %.3f msec (+- %.3f msec)\n", + build_id_all ? "-all" : "", time_average, time_stddev); + + /* each iteration, it processes MMAP2 + BUILD_ID + nr_samples * SAMPLE */ + time_average = avg_stats(&time_stats) / (nr_mmaps * (nr_samples + 2)); + time_stddev = stddev_stats(&time_stats) / (nr_mmaps * (nr_samples + 2)); + printf(" Average time per event: %.3f usec (+- %.3f usec)\n", + time_average, time_stddev); + + mem_average = avg_stats(&mem_stats); + mem_stddev = stddev_stats(&mem_stats); + printf(" Average memory usage: %.0f KB (+- %.0f KB)\n", + mem_average, mem_stddev); +} + +static int do_inject_loops(struct bench_data *data) +{ + + srand(time(NULL)); + symbol__init(NULL); + + bench_sample_type = PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_IP; + bench_sample_type |= PERF_SAMPLE_TID | PERF_SAMPLE_TIME; + bench_id_hdr_size = 32; + + collect_dso(); + if (nr_dsos == 0) { + printf(" Cannot collect DSOs for injection\n"); + return -1; + } + + do_inject_loop(data, false); + do_inject_loop(data, true); + + release_dso(); + return 0; +} + +int bench_inject_build_id(int argc, const char **argv) +{ + struct bench_data data; + + argc = parse_options(argc, argv, options, bench_usage, 0); + if (argc) { + usage_with_options(bench_usage, options); + exit(EXIT_FAILURE); + } + + return do_inject_loops(&data); +} + diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 9ad015a1e2024..6eb45a2aa8db3 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,6 +2,9 @@ /* Various wrappers to make the kernel .S file build in user-space: */ +// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c deleted file mode 100644 index 4130734dde84b..0000000000000 --- a/tools/perf/bench/mem-memcpy-x86-64-lib.c +++ /dev/null @@ -1,24 +0,0 @@ -/* - * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy - * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy' - * happy. - */ -#include <linux/types.h> - -unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt); -unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len); - -unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len) -{ - for (; len; --len, to++, from++) { - /* - * Call the assembly routine back directly since - * memcpy_mcsafe() may silently fallback to memcpy. - */ - unsigned long rem = __memcpy_mcsafe(to, from, 1); - - if (rem) - break; - } - return len; -} diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index d550bd5261629..6f093c483842e 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ #define altinstr_replacement text #define globl p2align 4; .globl diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index f85bceccc4594..11726ec6285f3 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -137,12 +137,13 @@ struct global_info { u8 *data; pthread_mutex_t startup_mutex; + pthread_cond_t startup_cond; int nr_tasks_started; - pthread_mutex_t startup_done_mutex; - pthread_mutex_t start_work_mutex; + pthread_cond_t start_work_cond; int nr_tasks_working; + bool start_work; pthread_mutex_t stop_work_mutex; u64 bytes_done; @@ -483,6 +484,18 @@ static void init_global_mutex(pthread_mutex_t *mutex) pthread_mutex_init(mutex, &attr); } +/* + * Return a process-shared (global) condition variable: + */ +static void init_global_cond(pthread_cond_t *cond) +{ + pthread_condattr_t attr; + + pthread_condattr_init(&attr); + pthread_condattr_setpshared(&attr, PTHREAD_PROCESS_SHARED); + pthread_cond_init(cond, &attr); +} + static int parse_cpu_list(const char *arg) { p0.cpu_list_str = strdup(arg); @@ -1136,15 +1149,18 @@ static void *worker_thread(void *__tdata) if (g->p.serialize_startup) { pthread_mutex_lock(&g->startup_mutex); g->nr_tasks_started++; + /* The last thread wakes the main process. */ + if (g->nr_tasks_started == g->p.nr_tasks) + pthread_cond_signal(&g->startup_cond); + pthread_mutex_unlock(&g->startup_mutex); /* Here we will wait for the main process to start us all at once: */ pthread_mutex_lock(&g->start_work_mutex); + g->start_work = false; g->nr_tasks_working++; - - /* Last one wake the main process: */ - if (g->nr_tasks_working == g->p.nr_tasks) - pthread_mutex_unlock(&g->startup_done_mutex); + while (!g->start_work) + pthread_cond_wait(&g->start_work_cond, &g->start_work_mutex); pthread_mutex_unlock(&g->start_work_mutex); } @@ -1441,8 +1457,9 @@ static int init(void) /* Startup serialization: */ init_global_mutex(&g->start_work_mutex); + init_global_cond(&g->start_work_cond); init_global_mutex(&g->startup_mutex); - init_global_mutex(&g->startup_done_mutex); + init_global_cond(&g->startup_cond); init_global_mutex(&g->stop_work_mutex); init_thread_data(); @@ -1502,9 +1519,6 @@ static int __bench_numa(const char *name) pids = zalloc(g->p.nr_proc * sizeof(*pids)); pid = -1; - /* All threads try to acquire it, this way we can wait for them to start up: */ - pthread_mutex_lock(&g->start_work_mutex); - if (g->p.serialize_startup) { tprintf(" #\n"); tprintf(" # Startup synchronization: ..."); fflush(stdout); @@ -1526,22 +1540,29 @@ static int __bench_numa(const char *name) pids[i] = pid; } - /* Wait for all the threads to start up: */ - while (g->nr_tasks_started != g->p.nr_tasks) - usleep(USEC_PER_MSEC); - - BUG_ON(g->nr_tasks_started != g->p.nr_tasks); if (g->p.serialize_startup) { + bool threads_ready = false; double startup_sec; - pthread_mutex_lock(&g->startup_done_mutex); + /* + * Wait for all the threads to start up. The last thread will + * signal this process. + */ + pthread_mutex_lock(&g->startup_mutex); + while (g->nr_tasks_started != g->p.nr_tasks) + pthread_cond_wait(&g->startup_cond, &g->startup_mutex); - /* This will start all threads: */ - pthread_mutex_unlock(&g->start_work_mutex); + pthread_mutex_unlock(&g->startup_mutex); - /* This mutex is locked - the last started thread will wake us: */ - pthread_mutex_lock(&g->startup_done_mutex); + /* Wait for all threads to be at the start_work_cond. */ + while (!threads_ready) { + pthread_mutex_lock(&g->start_work_mutex); + threads_ready = (g->nr_tasks_working == g->p.nr_tasks); + pthread_mutex_unlock(&g->start_work_mutex); + if (!threads_ready) + usleep(1); + } gettimeofday(&stop, NULL); @@ -1555,7 +1576,11 @@ static int __bench_numa(const char *name) tprintf(" #\n"); start = stop; - pthread_mutex_unlock(&g->startup_done_mutex); + /* Start all threads running. */ + pthread_mutex_lock(&g->start_work_mutex); + g->start_work = true; + pthread_mutex_unlock(&g->start_work_mutex); + pthread_cond_broadcast(&g->start_work_cond); } else { gettimeofday(&start, NULL); } diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 4940d10074c3e..a23ba6bb99b6e 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -412,7 +412,7 @@ static int __cmd_annotate(struct perf_annotate *ann) if (dump_trace) { perf_session__fprintf_nr_events(session, stdout); - perf_evlist__fprintf_nr_events(session->evlist, stdout); + evlist__fprintf_nr_events(session->evlist, stdout); goto out; } @@ -598,7 +598,7 @@ int cmd_annotate(int argc, const char **argv) HEADER_BRANCH_STACK); if (annotate.group_set) - perf_evlist__force_leader(annotate.session->evlist); + evlist__force_leader(annotate.session->evlist); ret = symbol__annotation_init(); if (ret < 0) diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 4f176039fc8f4..62a7b7420a448 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -87,6 +87,7 @@ static struct bench epoll_benchmarks[] = { static struct bench internals_benchmarks[] = { { "synthesize", "Benchmark perf event synthesis", bench_synthesize }, { "kallsyms-parse", "Benchmark kallsyms parsing", bench_kallsyms_parse }, + { "inject-build-id", "Benchmark build-id injection", bench_inject_build_id }, { NULL, NULL, NULL } }; diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 39efa51d7fb3d..a25411926e485 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -174,19 +174,19 @@ static int build_id_cache__add_kcore(const char *filename, bool force) static int build_id_cache__add_file(const char *filename, struct nsinfo *nsi) { char sbuild_id[SBUILD_ID_SIZE]; - u8 build_id[BUILD_ID_SIZE]; + struct build_id bid; int err; struct nscookie nsc; nsinfo__mountns_enter(nsi, &nsc); - err = filename__read_build_id(filename, &build_id, sizeof(build_id)); + err = filename__read_build_id(filename, &bid); nsinfo__mountns_exit(&nsc); if (err < 0) { pr_debug("Couldn't read a build-id in %s\n", filename); return -1; } - build_id__sprintf(build_id, sizeof(build_id), sbuild_id); + build_id__sprintf(&bid, sbuild_id); err = build_id_cache__add_s(sbuild_id, filename, nsi, false, false); pr_debug("Adding %s %s: %s\n", sbuild_id, filename, @@ -196,21 +196,21 @@ static int build_id_cache__add_file(const char *filename, struct nsinfo *nsi) static int build_id_cache__remove_file(const char *filename, struct nsinfo *nsi) { - u8 build_id[BUILD_ID_SIZE]; char sbuild_id[SBUILD_ID_SIZE]; + struct build_id bid; struct nscookie nsc; int err; nsinfo__mountns_enter(nsi, &nsc); - err = filename__read_build_id(filename, &build_id, sizeof(build_id)); + err = filename__read_build_id(filename, &bid); nsinfo__mountns_exit(&nsc); if (err < 0) { pr_debug("Couldn't read a build-id in %s\n", filename); return -1; } - build_id__sprintf(build_id, sizeof(build_id), sbuild_id); + build_id__sprintf(&bid, sbuild_id); err = build_id_cache__remove_s(sbuild_id); pr_debug("Removing %s %s: %s\n", sbuild_id, filename, err ? "FAIL" : "Ok"); @@ -274,17 +274,16 @@ static int build_id_cache__purge_all(void) static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) { char filename[PATH_MAX]; - u8 build_id[BUILD_ID_SIZE]; + struct build_id bid; if (dso__build_id_filename(dso, filename, sizeof(filename), false) && - filename__read_build_id(filename, build_id, - sizeof(build_id)) != sizeof(build_id)) { + filename__read_build_id(filename, &bid) == -1) { if (errno == ENOENT) return false; pr_warning("Problems with %s file, consider removing it from the cache\n", filename); - } else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) { + } else if (memcmp(dso->bid.data, bid.data, bid.size)) { pr_warning("Problems with %s file, consider removing it from the cache\n", filename); } @@ -300,14 +299,14 @@ static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *f static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi) { - u8 build_id[BUILD_ID_SIZE]; char sbuild_id[SBUILD_ID_SIZE]; + struct build_id bid; struct nscookie nsc; int err; nsinfo__mountns_enter(nsi, &nsc); - err = filename__read_build_id(filename, &build_id, sizeof(build_id)); + err = filename__read_build_id(filename, &bid); nsinfo__mountns_exit(&nsc); if (err < 0) { pr_debug("Couldn't read a build-id in %s\n", filename); @@ -315,7 +314,7 @@ static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi) } err = 0; - build_id__sprintf(build_id, sizeof(build_id), sbuild_id); + build_id__sprintf(&bid, sbuild_id); if (build_id_cache__cached(sbuild_id)) err = build_id_cache__remove_s(sbuild_id); diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 5938b100eaf4c..c5babeaa3b389 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -369,6 +369,10 @@ static struct perf_c2c c2c = { .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, + .attr = perf_event__process_attr, + .auxtrace_info = perf_event__process_auxtrace_info, + .auxtrace = perf_event__process_auxtrace, + .auxtrace_error = perf_event__process_auxtrace_error, .ordered_events = true, .ordering_requires_timestamps = true, }, @@ -652,45 +656,6 @@ STAT_FN(ld_l2hit) STAT_FN(ld_llchit) STAT_FN(rmt_hit) -static uint64_t llc_miss(struct c2c_stats *stats) -{ - uint64_t llcmiss; - - llcmiss = stats->lcl_dram + - stats->rmt_dram + - stats->rmt_hitm + - stats->rmt_hit; - - return llcmiss; -} - -static int -ld_llcmiss_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct c2c_hist_entry *c2c_he; - int width = c2c_width(fmt, hpp, he->hists); - - c2c_he = container_of(he, struct c2c_hist_entry, he); - - return scnprintf(hpp->buf, hpp->size, "%*lu", width, - llc_miss(&c2c_he->stats)); -} - -static int64_t -ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused, - struct hist_entry *left, struct hist_entry *right) -{ - struct c2c_hist_entry *c2c_left; - struct c2c_hist_entry *c2c_right; - - c2c_left = container_of(left, struct c2c_hist_entry, he); - c2c_right = container_of(right, struct c2c_hist_entry, he); - - return (uint64_t) llc_miss(&c2c_left->stats) - - (uint64_t) llc_miss(&c2c_right->stats); -} - static uint64_t total_records(struct c2c_stats *stats) { uint64_t lclmiss, ldcnt, total; @@ -1328,7 +1293,7 @@ static struct c2c_dimension dim_iaddr = { }; static struct c2c_dimension dim_tot_hitm = { - .header = HEADER_SPAN("----- LLC Load Hitm -----", "Total", 2), + .header = HEADER_SPAN("------- Load Hitm -------", "Total", 2), .name = "tot_hitm", .cmp = tot_hitm_cmp, .entry = tot_hitm_entry, @@ -1336,7 +1301,7 @@ static struct c2c_dimension dim_tot_hitm = { }; static struct c2c_dimension dim_lcl_hitm = { - .header = HEADER_SPAN_LOW("Lcl"), + .header = HEADER_SPAN_LOW("LclHitm"), .name = "lcl_hitm", .cmp = lcl_hitm_cmp, .entry = lcl_hitm_entry, @@ -1344,7 +1309,7 @@ static struct c2c_dimension dim_lcl_hitm = { }; static struct c2c_dimension dim_rmt_hitm = { - .header = HEADER_SPAN_LOW("Rmt"), + .header = HEADER_SPAN_LOW("RmtHitm"), .name = "rmt_hitm", .cmp = rmt_hitm_cmp, .entry = rmt_hitm_entry, @@ -1367,16 +1332,16 @@ static struct c2c_dimension dim_cl_lcl_hitm = { .width = 7, }; -static struct c2c_dimension dim_stores = { - .header = HEADER_SPAN("---- Store Reference ----", "Total", 2), - .name = "stores", +static struct c2c_dimension dim_tot_stores = { + .header = HEADER_BOTH("Total", "Stores"), + .name = "tot_stores", .cmp = store_cmp, .entry = store_entry, .width = 7, }; static struct c2c_dimension dim_stores_l1hit = { - .header = HEADER_SPAN_LOW("L1Hit"), + .header = HEADER_SPAN("---- Stores ----", "L1Hit", 1), .name = "stores_l1hit", .cmp = st_l1hit_cmp, .entry = st_l1hit_entry, @@ -1432,7 +1397,7 @@ static struct c2c_dimension dim_ld_l2hit = { }; static struct c2c_dimension dim_ld_llchit = { - .header = HEADER_SPAN("-- LLC Load Hit --", "Llc", 1), + .header = HEADER_SPAN("- LLC Load Hit --", "LclHit", 1), .name = "ld_lclhit", .cmp = ld_llchit_cmp, .entry = ld_llchit_entry, @@ -1440,21 +1405,13 @@ static struct c2c_dimension dim_ld_llchit = { }; static struct c2c_dimension dim_ld_rmthit = { - .header = HEADER_SPAN_LOW("Rmt"), + .header = HEADER_SPAN("- RMT Load Hit --", "RmtHit", 1), .name = "ld_rmthit", .cmp = rmt_hit_cmp, .entry = rmt_hit_entry, .width = 8, }; -static struct c2c_dimension dim_ld_llcmiss = { - .header = HEADER_BOTH("LLC", "Ld Miss"), - .name = "ld_llcmiss", - .cmp = ld_llcmiss_cmp, - .entry = ld_llcmiss_entry, - .width = 7, -}; - static struct c2c_dimension dim_tot_recs = { .header = HEADER_BOTH("Total", "records"), .name = "tot_recs", @@ -1486,7 +1443,7 @@ static struct c2c_dimension dim_percent_hitm = { }; static struct c2c_dimension dim_percent_rmt_hitm = { - .header = HEADER_SPAN("----- HITM -----", "Rmt", 1), + .header = HEADER_SPAN("----- HITM -----", "RmtHitm", 1), .name = "percent_rmt_hitm", .cmp = percent_rmt_hitm_cmp, .entry = percent_rmt_hitm_entry, @@ -1495,7 +1452,7 @@ static struct c2c_dimension dim_percent_rmt_hitm = { }; static struct c2c_dimension dim_percent_lcl_hitm = { - .header = HEADER_SPAN_LOW("Lcl"), + .header = HEADER_SPAN_LOW("LclHitm"), .name = "percent_lcl_hitm", .cmp = percent_lcl_hitm_cmp, .entry = percent_lcl_hitm_entry, @@ -1648,7 +1605,7 @@ static struct c2c_dimension *dimensions[] = { &dim_rmt_hitm, &dim_cl_lcl_hitm, &dim_cl_rmt_hitm, - &dim_stores, + &dim_tot_stores, &dim_stores_l1hit, &dim_stores_l1miss, &dim_cl_stores_l1hit, @@ -1658,7 +1615,6 @@ static struct c2c_dimension *dimensions[] = { &dim_ld_l2hit, &dim_ld_llchit, &dim_ld_rmthit, - &dim_ld_llcmiss, &dim_tot_recs, &dim_tot_loads, &dim_percent_hitm, @@ -2726,6 +2682,12 @@ static int setup_coalesce(const char *coalesce, bool no_source) static int perf_c2c__report(int argc, const char **argv) { + struct itrace_synth_opts itrace_synth_opts = { + .set = true, + .mem = true, /* Only enable memory event */ + .default_no_sample = true, + }; + struct perf_session *session; struct ui_progress prog; struct perf_data data = { @@ -2805,6 +2767,8 @@ static int perf_c2c__report(int argc, const char **argv) goto out; } + session->itrace_synth_opts = &itrace_synth_opts; + err = setup_nodes(session); if (err) { pr_err("Failed setup nodes\n"); @@ -2846,15 +2810,16 @@ static int perf_c2c__report(int argc, const char **argv) "dcacheline," "dcacheline_node," "dcacheline_count," - "tot_recs," "percent_hitm," "tot_hitm,lcl_hitm,rmt_hitm," - "stores,stores_l1hit,stores_l1miss," - "dram_lcl,dram_rmt," - "ld_llcmiss," + "tot_recs," "tot_loads," + "tot_stores," + "stores_l1hit,stores_l1miss," "ld_fbhit,ld_l1hit,ld_l2hit," - "ld_lclhit,ld_rmthit", + "ld_lclhit,lcl_hitm," + "ld_rmthit,rmt_hitm," + "dram_lcl,dram_rmt", c2c.display == DISPLAY_TOT ? "tot_hitm" : c2c.display == DISPLAY_LCL ? "lcl_hitm" : "rmt_hitm" ); @@ -2914,9 +2879,10 @@ static int perf_c2c__record(int argc, const char **argv) int ret; bool all_user = false, all_kernel = false; bool event_set = false; + struct perf_mem_event *e; struct option options[] = { OPT_CALLBACK('e', "event", &event_set, "event", - "event selector. Use 'perf mem record -e list' to list available events", + "event selector. Use 'perf c2c record -e list' to list available events", parse_record_events), OPT_BOOLEAN('u', "all-user", &all_user, "collect only user level data"), OPT_BOOLEAN('k', "all-kernel", &all_kernel, "collect only kernel level data"), @@ -2941,11 +2907,24 @@ static int perf_c2c__record(int argc, const char **argv) rec_argv[i++] = "record"; if (!event_set) { - perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; - perf_mem_events[PERF_MEM_EVENTS__STORE].record = true; + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE); + /* + * The load and store operations are required, use the event + * PERF_MEM_EVENTS__LOAD_STORE if it is supported. + */ + if (e->tag) { + e->record = true; + } else { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + e->record = true; + + e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE); + e->record = true; + } } - if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + if (e->record) rec_argv[i++] = "-W"; rec_argv[i++] = "-d"; @@ -2953,12 +2932,13 @@ static int perf_c2c__record(int argc, const char **argv) rec_argv[i++] = "--sample-cpu"; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - if (!perf_mem_events[j].record) + e = perf_mem_events__ptr(j); + if (!e->record) continue; - if (!perf_mem_events[j].supported) { + if (!e->supported) { pr_err("failed: event '%s' not supported\n", - perf_mem_events[j].name); + perf_mem_events__name(j)); free(rec_argv); return -1; } diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index f8c9bdd8269af..8f6c784ce629c 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -25,6 +25,7 @@ #include "util/map.h" #include "util/spark.h" #include "util/block-info.h" +#include "util/stream.h" #include <linux/err.h> #include <linux/zalloc.h> #include <subcmd/pager.h> @@ -42,6 +43,7 @@ struct perf_diff { int range_size; int range_num; bool has_br_stack; + bool stream; }; /* Diff command specific HPP columns. */ @@ -72,6 +74,7 @@ struct data__file { struct perf_data data; int idx; struct hists *hists; + struct evlist_streams *evlist_streams; struct diff_hpp_fmt fmt[PERF_HPP_DIFF__MAX_INDEX]; }; @@ -106,6 +109,7 @@ enum { COMPUTE_DELTA_ABS, COMPUTE_CYCLES, COMPUTE_MAX, + COMPUTE_STREAM, /* After COMPUTE_MAX to avoid use current compute arrays */ }; const char *compute_names[COMPUTE_MAX] = { @@ -393,6 +397,11 @@ static int diff__process_sample_event(struct perf_tool *tool, struct perf_diff *pdiff = container_of(tool, struct perf_diff, tool); struct addr_location al; struct hists *hists = evsel__hists(evsel); + struct hist_entry_iter iter = { + .evsel = evsel, + .sample = sample, + .ops = &hist_iter_normal, + }; int ret = -1; if (perf_time__ranges_skip_sample(pdiff->ptime_range, pdiff->range_num, @@ -411,14 +420,8 @@ static int diff__process_sample_event(struct perf_tool *tool, goto out_put; } - if (compute != COMPUTE_CYCLES) { - if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample, - true)) { - pr_warning("problem incrementing symbol period, " - "skipping event\n"); - goto out_put; - } - } else { + switch (compute) { + case COMPUTE_CYCLES: if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL, NULL, NULL, sample, true)) { pr_warning("problem incrementing symbol period, " @@ -428,6 +431,23 @@ static int diff__process_sample_event(struct perf_tool *tool, hist__account_cycles(sample->branch_stack, &al, sample, false, NULL); + break; + + case COMPUTE_STREAM: + if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH, + NULL)) { + pr_debug("problem adding hist entry, skipping event\n"); + goto out_put; + } + break; + + default: + if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample, + true)) { + pr_warning("problem incrementing symbol period, " + "skipping event\n"); + goto out_put; + } } /* @@ -474,7 +494,7 @@ static struct evsel *evsel_match(struct evsel *evsel, return NULL; } -static void perf_evlist__collapse_resort(struct evlist *evlist) +static void evlist__collapse_resort(struct evlist *evlist) { struct evsel *evsel; @@ -996,10 +1016,55 @@ static void data_process(void) } } +static int process_base_stream(struct data__file *data_base, + struct data__file *data_pair, + const char *title __maybe_unused) +{ + struct evlist *evlist_base = data_base->session->evlist; + struct evlist *evlist_pair = data_pair->session->evlist; + struct evsel *evsel_base, *evsel_pair; + struct evsel_streams *es_base, *es_pair; + + evlist__for_each_entry(evlist_base, evsel_base) { + evsel_pair = evsel_match(evsel_base, evlist_pair); + if (!evsel_pair) + continue; + + es_base = evsel_streams__entry(data_base->evlist_streams, + evsel_base->idx); + if (!es_base) + return -1; + + es_pair = evsel_streams__entry(data_pair->evlist_streams, + evsel_pair->idx); + if (!es_pair) + return -1; + + evsel_streams__match(es_base, es_pair); + evsel_streams__report(es_base, es_pair); + } + + return 0; +} + +static void stream_process(void) +{ + /* + * Stream comparison only supports two data files. + * perf.data.old and perf.data. data__files[0] is perf.data.old, + * data__files[1] is perf.data. + */ + process_base_stream(&data__files[0], &data__files[1], + "# Output based on old perf data:\n#\n"); +} + static void data__free(struct data__file *d) { int col; + if (d->evlist_streams) + evlist_streams__delete(d->evlist_streams); + for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) { struct diff_hpp_fmt *fmt = &d->fmt[col]; @@ -1149,13 +1214,25 @@ static int __cmd_diff(void) goto out_delete; } - perf_evlist__collapse_resort(d->session->evlist); + evlist__collapse_resort(d->session->evlist); if (pdiff.ptime_range) zfree(&pdiff.ptime_range); + + if (compute == COMPUTE_STREAM) { + d->evlist_streams = evlist__create_streams( + d->session->evlist, 5); + if (!d->evlist_streams) { + ret = -ENOMEM; + goto out_delete; + } + } } - data_process(); + if (compute == COMPUTE_STREAM) + stream_process(); + else + data_process(); out_delete: data__for_each_file(i, d) { @@ -1228,6 +1305,8 @@ static const struct option options[] = { "only consider symbols in these pids"), OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]", "only consider symbols in these tids"), + OPT_BOOLEAN(0, "stream", &pdiff.stream, + "Enable hot streams comparison."), OPT_END() }; @@ -1887,6 +1966,9 @@ int cmd_diff(int argc, const char **argv) if (cycles_hist && (compute != COMPUTE_CYCLES)) usage_with_options(diff_usage, options); + if (pdiff.stream) + compute = COMPUTE_STREAM; + symbol__annotation_init(); if (symbol__init(NULL) < 0) @@ -1898,13 +1980,26 @@ int cmd_diff(int argc, const char **argv) if (check_file_brstack() < 0) return -1; - if (compute == COMPUTE_CYCLES && !pdiff.has_br_stack) + if ((compute == COMPUTE_CYCLES || compute == COMPUTE_STREAM) + && !pdiff.has_br_stack) { return -1; + } - if (ui_init() < 0) - return -1; + if (compute == COMPUTE_STREAM) { + symbol_conf.show_branchflag_count = true; + symbol_conf.disable_add2line_warn = true; + callchain_param.mode = CHAIN_FLAT; + callchain_param.key = CCKEY_SRCLINE; + callchain_param.branch_callstack = 1; + symbol_conf.use_callchain = true; + callchain_register_param(&callchain_param); + sort_order = "srcline,symbol,dso"; + } else { + if (ui_init() < 0) + return -1; - sort__mode = SORT_MODE__DIFF; + sort__mode = SORT_MODE__DIFF; + } if (setup_sorting(NULL) < 0) usage_with_options(diff_usage, options); diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index 98e9928012519..4617b32c9c978 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -17,6 +17,14 @@ #include "util/data.h" #include "util/debug.h" #include <linux/err.h> +#include "util/tool.h" + +static int process_header_feature(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused) +{ + session_done = 1; + return 0; +} static int __cmd_evlist(const char *file_name, struct perf_attr_details *details) { @@ -27,12 +35,20 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details .mode = PERF_DATA_MODE_READ, .force = details->force, }; + struct perf_tool tool = { + /* only needed for pipe mode */ + .attr = perf_event__process_attr, + .feature = process_header_feature, + }; bool has_tracepoint = false; - session = perf_session__new(&data, 0, NULL); + session = perf_session__new(&data, 0, &tool); if (IS_ERR(session)) return PTR_ERR(session); + if (data.is_pipe) + perf_session__process_events(session); + evlist__for_each_entry(session->evlist, pos) { evsel__fprintf(pos, details, stdout); diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 1d44bc2f63d85..d49448a1060c9 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -25,6 +25,7 @@ #include "target.h" #include "cpumap.h" #include "thread_map.h" +#include "strfilter.h" #include "util/cap.h" #include "util/config.h" #include "util/units.h" @@ -36,7 +37,6 @@ struct perf_ftrace { struct evlist *evlist; struct target target; const char *tracer; - bool list_avail_functions; struct list_head filters; struct list_head notrace; struct list_head graph_funcs; @@ -67,7 +67,7 @@ static void sig_handler(int sig __maybe_unused) } /* - * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since + * evlist__prepare_workload will send a SIGUSR1 if the fork fails, since * we asked by setting its exec_error to the function below, * ftrace__workload_exec_failed_signal. * @@ -181,6 +181,40 @@ out: return ret; } +static int read_tracing_file_by_line(const char *name, + void (*cb)(char *str, void *arg), + void *cb_arg) +{ + char *line = NULL; + size_t len = 0; + char *file; + FILE *fp; + + file = get_tracing_file(name); + if (!file) { + pr_debug("cannot get tracing file: %s\n", name); + return -1; + } + + fp = fopen(file, "r"); + if (fp == NULL) { + pr_debug("cannot open tracing file: %s\n", name); + put_tracing_file(file); + return -1; + } + + while (getline(&line, &len, fp) != -1) { + cb(line, cb_arg); + } + + if (line) + free(line); + + fclose(fp); + put_tracing_file(file); + return 0; +} + static int write_tracing_file_int(const char *name, int value) { char buf[16]; @@ -557,9 +591,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) signal(SIGCHLD, sig_handler); signal(SIGPIPE, sig_handler); - if (ftrace->list_avail_functions) - return read_tracing_file_to_stdout("available_filter_functions"); - if (reset_tracing_files(ftrace) < 0) { pr_err("failed to reset ftrace\n"); goto out; @@ -569,9 +600,8 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) if (write_tracing_file("trace", "0") < 0) goto out; - if (argc && perf_evlist__prepare_workload(ftrace->evlist, - &ftrace->target, argv, false, - ftrace__workload_exec_failed_signal) < 0) { + if (argc && evlist__prepare_workload(ftrace->evlist, &ftrace->target, argv, false, + ftrace__workload_exec_failed_signal) < 0) { goto out; } @@ -613,7 +643,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) } } - perf_evlist__start_workload(ftrace->evlist); + evlist__start_workload(ftrace->evlist); if (ftrace->initial_delay) { usleep(ftrace->initial_delay * 1000); @@ -683,6 +713,46 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb) return -1; } +static void list_function_cb(char *str, void *arg) +{ + struct strfilter *filter = (struct strfilter *)arg; + + if (strfilter__compare(filter, str)) + printf("%s", str); +} + +static int opt_list_avail_functions(const struct option *opt __maybe_unused, + const char *str, int unset) +{ + struct strfilter *filter; + const char *err = NULL; + int ret; + + if (unset || !str) + return -1; + + filter = strfilter__new(str, &err); + if (!filter) + return err ? -EINVAL : -ENOMEM; + + ret = strfilter__or(filter, str, &err); + if (ret == -EINVAL) { + pr_err("Filter parse error at %td.\n", err - str + 1); + pr_err("Source: \"%s\"\n", str); + pr_err(" %*c\n", (int)(err - str + 1), '^'); + strfilter__delete(filter); + return ret; + } + + ret = read_tracing_file_by_line("available_filter_functions", + list_function_cb, filter); + strfilter__delete(filter); + if (ret < 0) + return ret; + + exit(0); +} + static int parse_filter_func(const struct option *opt, const char *str, int unset __maybe_unused) { @@ -817,8 +887,9 @@ int cmd_ftrace(int argc, const char **argv) const struct option ftrace_options[] = { OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", "Tracer to use: function_graph(default) or function"), - OPT_BOOLEAN('F', "funcs", &ftrace.list_avail_functions, - "Show available functions to filter"), + OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]", + "Show available functions to filter", + opt_list_avail_functions, "*"), OPT_STRING('p', "pid", &ftrace.target.pid, "pid", "Trace on existing process id"), /* TODO: Add short option -t after -t/--tracer can be removed. */ @@ -886,7 +957,7 @@ int cmd_ftrace(int argc, const char **argv) goto out_delete_filters; } - ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target); + ret = evlist__create_maps(ftrace.evlist, &ftrace.target); if (ret < 0) goto out_delete_evlist; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 6d2f410d773ad..43937f4b399ad 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -10,6 +10,7 @@ #include "util/color.h" #include "util/dso.h" +#include "util/vdso.h" #include "util/evlist.h" #include "util/evsel.h" #include "util/map.h" @@ -23,9 +24,11 @@ #include "util/symbol.h" #include "util/synthetic-events.h" #include "util/thread.h" -#include <linux/err.h> +#include "util/namespaces.h" +#include <linux/err.h> #include <subcmd/parse-options.h> +#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include <linux/list.h> #include <errno.h> @@ -35,6 +38,7 @@ struct perf_inject { struct perf_tool tool; struct perf_session *session; bool build_ids; + bool build_id_all; bool sched_stat; bool have_auxtrace; bool strip; @@ -54,6 +58,9 @@ struct event_entry { union perf_event event[]; }; +static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool, + struct machine *machine, u8 cpumode, u32 flags); + static int output_bytes(struct perf_inject *inject, void *buf, size_t sz) { ssize_t size; @@ -97,6 +104,13 @@ static int perf_event__repipe_op2_synth(struct perf_session *session, return perf_event__repipe_synth(session->tool, event); } +static int perf_event__repipe_op4_synth(struct perf_session *session, + union perf_event *event, + u64 data __maybe_unused) +{ + return perf_event__repipe_synth(session->tool, event); +} + static int perf_event__repipe_attr(struct perf_tool *tool, union perf_event *event, struct evlist **pevlist) @@ -115,6 +129,13 @@ static int perf_event__repipe_attr(struct perf_tool *tool, return perf_event__repipe_synth(tool, event); } +static int perf_event__repipe_event_update(struct perf_tool *tool, + union perf_event *event, + struct evlist **pevlist __maybe_unused) +{ + return perf_event__repipe_synth(tool, event); +} + #ifdef HAVE_AUXTRACE_SUPPORT static int copy_bytes(struct perf_inject *inject, int fd, off_t size) @@ -303,6 +324,68 @@ static int perf_event__jit_repipe_mmap(struct perf_tool *tool, } #endif +static struct dso *findnew_dso(int pid, int tid, const char *filename, + struct dso_id *id, struct machine *machine) +{ + struct thread *thread; + struct nsinfo *nsi = NULL; + struct nsinfo *nnsi; + struct dso *dso; + bool vdso; + + thread = machine__findnew_thread(machine, pid, tid); + if (thread == NULL) { + pr_err("cannot find or create a task %d/%d.\n", tid, pid); + return NULL; + } + + vdso = is_vdso_map(filename); + nsi = nsinfo__get(thread->nsinfo); + + if (vdso) { + /* The vdso maps are always on the host and not the + * container. Ensure that we don't use setns to look + * them up. + */ + nnsi = nsinfo__copy(nsi); + if (nnsi) { + nsinfo__put(nsi); + nnsi->need_setns = false; + nsi = nnsi; + } + dso = machine__findnew_vdso(machine, thread); + } else { + dso = machine__findnew_dso_id(machine, filename, id); + } + + if (dso) + dso->nsinfo = nsi; + else + nsinfo__put(nsi); + + thread__put(thread); + return dso; +} + +static int perf_event__repipe_buildid_mmap(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct dso *dso; + + dso = findnew_dso(event->mmap.pid, event->mmap.tid, + event->mmap.filename, NULL, machine); + + if (dso && !dso->hit) { + dso->hit = 1; + dso__inject_build_id(dso, tool, machine, sample->cpumode, 0); + dso__put(dso); + } + + return perf_event__repipe(tool, event, sample, machine); +} + static int perf_event__repipe_mmap2(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -341,6 +424,34 @@ static int perf_event__jit_repipe_mmap2(struct perf_tool *tool, } #endif +static int perf_event__repipe_buildid_mmap2(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct dso_id dso_id = { + .maj = event->mmap2.maj, + .min = event->mmap2.min, + .ino = event->mmap2.ino, + .ino_generation = event->mmap2.ino_generation, + }; + struct dso *dso; + + dso = findnew_dso(event->mmap2.pid, event->mmap2.tid, + event->mmap2.filename, &dso_id, machine); + + if (dso && !dso->hit) { + dso->hit = 1; + dso__inject_build_id(dso, tool, machine, sample->cpumode, + event->mmap2.flags); + dso__put(dso); + } + + perf_event__repipe(tool, event, sample, machine); + + return 0; +} + static int perf_event__repipe_fork(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -405,34 +516,36 @@ static int perf_event__repipe_tracing_data(struct perf_session *session, static int dso__read_build_id(struct dso *dso) { + struct nscookie nsc; + if (dso->has_build_id) return 0; - if (filename__read_build_id(dso->long_name, dso->build_id, - sizeof(dso->build_id)) > 0) { + nsinfo__mountns_enter(dso->nsinfo, &nsc); + if (filename__read_build_id(dso->long_name, &dso->bid) > 0) dso->has_build_id = true; - return 0; - } + nsinfo__mountns_exit(&nsc); - return -1; + return dso->has_build_id ? 0 : -1; } static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool, - struct machine *machine) + struct machine *machine, u8 cpumode, u32 flags) { - u16 misc = PERF_RECORD_MISC_USER; int err; + if (is_anon_memory(dso->long_name) || flags & MAP_HUGETLB) + return 0; + if (is_no_dso_memory(dso->long_name)) + return 0; + if (dso__read_build_id(dso) < 0) { pr_debug("no build_id found for %s\n", dso->long_name); return -1; } - if (dso->kernel) - misc = PERF_RECORD_MISC_KERNEL; - - err = perf_event__synthesize_build_id(tool, dso, misc, perf_event__repipe, - machine); + err = perf_event__synthesize_build_id(tool, dso, cpumode, + perf_event__repipe, machine); if (err) { pr_err("Can't synthesize build_id event for %s\n", dso->long_name); return -1; @@ -441,11 +554,10 @@ static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool, return 0; } -static int perf_event__inject_buildid(struct perf_tool *tool, - union perf_event *event, - struct perf_sample *sample, - struct evsel *evsel __maybe_unused, - struct machine *machine) +int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, + struct evsel *evsel __maybe_unused, + struct machine *machine) { struct addr_location al; struct thread *thread; @@ -460,19 +572,8 @@ static int perf_event__inject_buildid(struct perf_tool *tool, if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) { if (!al.map->dso->hit) { al.map->dso->hit = 1; - if (map__load(al.map) >= 0) { - dso__inject_build_id(al.map->dso, tool, machine); - /* - * If this fails, too bad, let the other side - * account this as unresolved. - */ - } else { -#ifdef HAVE_LIBELF_SUPPORT - pr_warning("no symbols found in %s, maybe " - "install a debug package?\n", - al.map->dso->long_name); -#endif - } + dso__inject_build_id(al.map->dso, tool, machine, + sample->cpumode, al.map->flags); } } @@ -606,7 +707,7 @@ static int __cmd_inject(struct perf_inject *inject) signal(SIGINT, sig_handler); if (inject->build_ids || inject->sched_stat || - inject->itrace_synth_opts.set) { + inject->itrace_synth_opts.set || inject->build_id_all) { inject->tool.mmap = perf_event__repipe_mmap; inject->tool.mmap2 = perf_event__repipe_mmap2; inject->tool.fork = perf_event__repipe_fork; @@ -615,7 +716,10 @@ static int __cmd_inject(struct perf_inject *inject) output_data_offset = session->header.data_offset; - if (inject->build_ids) { + if (inject->build_id_all) { + inject->tool.mmap = perf_event__repipe_buildid_mmap; + inject->tool.mmap2 = perf_event__repipe_buildid_mmap2; + } else if (inject->build_ids) { inject->tool.sample = perf_event__inject_buildid; } else if (inject->sched_stat) { struct evsel *evsel; @@ -675,25 +779,15 @@ static int __cmd_inject(struct perf_inject *inject) dsos__hit_all(session); /* * The AUX areas have been removed and replaced with - * synthesized hardware events, so clear the feature flag and - * remove the evsel. + * synthesized hardware events, so clear the feature flag. */ if (inject->itrace_synth_opts.set) { - struct evsel *evsel; - perf_header__clear_feat(&session->header, HEADER_AUXTRACE); if (inject->itrace_synth_opts.last_branch || inject->itrace_synth_opts.add_last_branch) perf_header__set_feat(&session->header, HEADER_BRANCH_STACK); - evsel = perf_evlist__id2evsel_strict(session->evlist, - inject->aux_id); - if (evsel) { - pr_debug("Deleting %s\n", evsel__name(evsel)); - evlist__remove(session->evlist, evsel); - evsel__delete(evsel); - } } session->header.data_offset = output_data_offset; session->header.data_size = inject->bytes_written; @@ -708,9 +802,12 @@ int cmd_inject(int argc, const char **argv) struct perf_inject inject = { .tool = { .sample = perf_event__repipe_sample, + .read = perf_event__repipe_sample, .mmap = perf_event__repipe, .mmap2 = perf_event__repipe, .comm = perf_event__repipe, + .namespaces = perf_event__repipe, + .cgroup = perf_event__repipe, .fork = perf_event__repipe, .exit = perf_event__repipe, .lost = perf_event__repipe, @@ -718,35 +815,48 @@ int cmd_inject(int argc, const char **argv) .aux = perf_event__repipe, .itrace_start = perf_event__repipe, .context_switch = perf_event__repipe, - .read = perf_event__repipe_sample, .throttle = perf_event__repipe, .unthrottle = perf_event__repipe, + .ksymbol = perf_event__repipe, + .bpf = perf_event__repipe, + .text_poke = perf_event__repipe, .attr = perf_event__repipe_attr, + .event_update = perf_event__repipe_event_update, .tracing_data = perf_event__repipe_op2_synth, - .auxtrace_info = perf_event__repipe_op2_synth, - .auxtrace = perf_event__repipe_auxtrace, - .auxtrace_error = perf_event__repipe_op2_synth, - .time_conv = perf_event__repipe_op2_synth, .finished_round = perf_event__repipe_oe_synth, .build_id = perf_event__repipe_op2_synth, .id_index = perf_event__repipe_op2_synth, + .auxtrace_info = perf_event__repipe_op2_synth, + .auxtrace_error = perf_event__repipe_op2_synth, + .time_conv = perf_event__repipe_op2_synth, + .thread_map = perf_event__repipe_op2_synth, + .cpu_map = perf_event__repipe_op2_synth, + .stat_config = perf_event__repipe_op2_synth, + .stat = perf_event__repipe_op2_synth, + .stat_round = perf_event__repipe_op2_synth, .feature = perf_event__repipe_op2_synth, + .compressed = perf_event__repipe_op4_synth, + .auxtrace = perf_event__repipe_auxtrace, }, .input_name = "-", .samples = LIST_HEAD_INIT(inject.samples), .output = { .path = "-", .mode = PERF_DATA_MODE_WRITE, + .use_stdio = true, }, }; struct perf_data data = { .mode = PERF_DATA_MODE_READ, + .use_stdio = true, }; int ret; struct option options[] = { OPT_BOOLEAN('b', "build-ids", &inject.build_ids, "Inject build-ids into the output stream"), + OPT_BOOLEAN(0, "buildid-all", &inject.build_id_all, + "Inject build-ids of all DSOs into the output stream"), OPT_STRING('i', "input", &inject.input_name, "file", "input file name"), OPT_STRING('o', "output", &inject.output.path, "file", @@ -795,8 +905,6 @@ int cmd_inject(int argc, const char **argv) return -1; } - inject.tool.ordered_events = inject.sched_stat; - data.path = inject.input_name; inject.session = perf_session__new(&data, true, &inject.tool); if (IS_ERR(inject.session)) @@ -805,7 +913,7 @@ int cmd_inject(int argc, const char **argv) if (zstd_init(&(inject.session->zstd_data), 0) < 0) pr_warning("Decompression initialization failed.\n"); - if (inject.build_ids) { + if (inject.build_ids && !inject.build_id_all) { /* * to make sure the mmap records are ordered correctly * and so that the correct especially due to jitted code @@ -815,6 +923,11 @@ int cmd_inject(int argc, const char **argv) inject.tool.ordered_events = true; inject.tool.ordering_requires_timestamps = true; } + + if (inject.sched_stat) { + inject.tool.ordered_events = true; + } + #ifdef HAVE_JITDUMP if (inject.jit_mode) { inject.tool.mmap2 = perf_event__jit_repipe_mmap2; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index a50dae2c4ae9e..0062445e8ead8 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1960,18 +1960,15 @@ int cmd_kmem(int argc, const char **argv) ret = -1; if (kmem_slab) { - if (!perf_evlist__find_tracepoint_by_name(session->evlist, - "kmem:kmalloc")) { + if (!evlist__find_tracepoint_by_name(session->evlist, "kmem:kmalloc")) { pr_err(errmsg, "slab", "slab"); goto out_delete; } } if (kmem_page) { - struct evsel *evsel; + struct evsel *evsel = evlist__find_tracepoint_by_name(session->evlist, "kmem:mm_page_alloc"); - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "kmem:mm_page_alloc"); if (evsel == NULL) { pr_err(errmsg, "page", "page"); goto out_delete; diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 460945ded6dd2..1105c9e40a80f 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -764,7 +764,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, return (err == -EAGAIN) ? 0 : -1; while ((event = perf_mmap__read_event(&md->core)) != NULL) { - err = perf_evlist__parse_sample_timestamp(evlist, event, ×tamp); + err = evlist__parse_sample_timestamp(evlist, event, ×tamp); if (err) { perf_mmap__consume(&md->core); pr_err("Failed to parse sample\n"); @@ -1022,7 +1022,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) struct evlist *evlist = kvm->evlist; char sbuf[STRERR_BUFSIZE]; - perf_evlist__config(evlist, &kvm->opts, NULL); + evlist__config(evlist, &kvm->opts, NULL); /* * Note: exclude_{guest,host} do not apply here. @@ -1349,8 +1349,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid", "record events on existing process id"), OPT_CALLBACK('m', "mmap-pages", &kvm->opts.mmap_pages, "pages", - "number of mmap data pages", - perf_evlist__parse_mmap_pages), + "number of mmap data pages", evlist__parse_mmap_pages), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('a', "all-cpus", &kvm->opts.target.system_wide, @@ -1442,7 +1441,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, goto out; } - if (perf_evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0) + if (evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0) usage_with_options(live_usage, live_options); /* diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 0a7fe4cb5555e..10ab5e40a34f8 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -92,13 +92,6 @@ int cmd_list(int argc, const char **argv) else if ((sep = strchr(argv[i], ':')) != NULL) { int sep_idx; - if (sep == NULL) { - print_events(argv[i], raw_dump, !desc_flag, - long_desc_flag, - details_flag, - deprecated); - continue; - } sep_idx = sep - argv[i]; s = strdup(argv[i]); if (s == NULL) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index f0a1dbacb46c7..a2f1e53f37a7a 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -406,7 +406,7 @@ static int report_lock_acquire_event(struct evsel *evsel, struct lock_seq_stat *seq; const char *name = evsel__strval(evsel, sample, "name"); u64 tmp = evsel__intval(evsel, sample, "lockdep_addr"); - int flag = evsel__intval(evsel, sample, "flag"); + int flag = evsel__intval(evsel, sample, "flags"); memcpy(&addr, &tmp, sizeof(void *)); @@ -621,7 +621,7 @@ static int report_lock_release_event(struct evsel *evsel, case SEQ_STATE_READ_ACQUIRED: seq->read_count--; BUG_ON(seq->read_count < 0); - if (!seq->read_count) { + if (seq->read_count) { ls->nr_release++; goto end; } diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 3523279af6aff..823742036ddb2 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -7,6 +7,7 @@ #include "perf.h" #include <subcmd/parse-options.h> +#include "util/auxtrace.h" #include "util/trace-event.h" #include "util/tool.h" #include "util/session.h" @@ -64,6 +65,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) const char **rec_argv; int ret; bool all_user = false, all_kernel = false; + struct perf_mem_event *e; struct option options[] = { OPT_CALLBACK('e', "event", &mem, "event", "event selector. use 'perf mem record -e list' to list available events", @@ -76,6 +78,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) OPT_END() }; + if (perf_mem_events__init()) { + pr_err("failed: memory events not supported\n"); + return -1; + } + argc = parse_options(argc, argv, options, record_mem_usage, PARSE_OPT_KEEP_UNKNOWN); @@ -86,13 +93,30 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = "record"; - if (mem->operation & MEM_OPERATION_LOAD) - perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE); - if (mem->operation & MEM_OPERATION_STORE) - perf_mem_events[PERF_MEM_EVENTS__STORE].record = true; + /* + * The load and store operations are required, use the event + * PERF_MEM_EVENTS__LOAD_STORE if it is supported. + */ + if (e->tag && + (mem->operation & MEM_OPERATION_LOAD) && + (mem->operation & MEM_OPERATION_STORE)) { + e->record = true; + } else { + if (mem->operation & MEM_OPERATION_LOAD) { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + e->record = true; + } - if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) + if (mem->operation & MEM_OPERATION_STORE) { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE); + e->record = true; + } + } + + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + if (e->record) rec_argv[i++] = "-W"; rec_argv[i++] = "-d"; @@ -101,10 +125,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = "--phys-data"; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - if (!perf_mem_events[j].record) + e = perf_mem_events__ptr(j); + if (!e->record) continue; - if (!perf_mem_events[j].supported) { + if (!e->supported) { pr_err("failed: event '%s' not supported\n", perf_mem_events__name(j)); free(rec_argv); @@ -231,6 +256,12 @@ static int process_sample_event(struct perf_tool *tool, static int report_raw_events(struct perf_mem *mem) { + struct itrace_synth_opts itrace_synth_opts = { + .set = true, + .mem = true, /* Only enable memory event */ + .default_no_sample = true, + }; + struct perf_data data = { .path = input_name, .mode = PERF_DATA_MODE_READ, @@ -243,6 +274,8 @@ static int report_raw_events(struct perf_mem *mem) if (IS_ERR(session)) return PTR_ERR(session); + session->itrace_synth_opts = &itrace_synth_opts; + if (mem->cpu_list) { ret = perf_session__cpu_bitmap(session, mem->cpu_list, mem->cpu_bitmap); @@ -265,11 +298,35 @@ out_delete: perf_session__delete(session); return ret; } +static char *get_sort_order(struct perf_mem *mem) +{ + bool has_extra_options = mem->phys_addr ? true : false; + char sort[128]; + + /* + * there is no weight (cost) associated with stores, so don't print + * the column + */ + if (!(mem->operation & MEM_OPERATION_LOAD)) { + strcpy(sort, "--sort=mem,sym,dso,symbol_daddr," + "dso_daddr,tlb,locked"); + } else if (has_extra_options) { + strcpy(sort, "--sort=local_weight,mem,sym,dso,symbol_daddr," + "dso_daddr,snoop,tlb,locked"); + } else + return NULL; + + if (mem->phys_addr) + strcat(sort, ",phys_daddr"); + + return strdup(sort); +} static int report_events(int argc, const char **argv, struct perf_mem *mem) { const char **rep_argv; int ret, i = 0, j, rep_argc; + char *new_sort_order; if (mem->dump_raw) return report_raw_events(mem); @@ -283,20 +340,9 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) rep_argv[i++] = "--mem-mode"; rep_argv[i++] = "-n"; /* display number of samples */ - /* - * there is no weight (cost) associated with stores, so don't print - * the column - */ - if (!(mem->operation & MEM_OPERATION_LOAD)) { - if (mem->phys_addr) - rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr," - "dso_daddr,tlb,locked,phys_daddr"; - else - rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr," - "dso_daddr,tlb,locked"; - } else if (mem->phys_addr) - rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr," - "dso_daddr,snoop,tlb,locked,phys_daddr"; + new_sort_order = get_sort_order(mem); + if (new_sort_order) + rep_argv[i++] = new_sort_order; for (j = 1; j < argc; j++, i++) rep_argv[i] = argv[j]; @@ -386,8 +432,12 @@ int cmd_mem(int argc, const char **argv) .comm = perf_event__process_comm, .lost = perf_event__process_lost, .fork = perf_event__process_fork, + .attr = perf_event__process_attr, .build_id = perf_event__process_build_id, .namespaces = perf_event__process_namespaces, + .auxtrace_info = perf_event__process_auxtrace_info, + .auxtrace = perf_event__process_auxtrace, + .auxtrace_error = perf_event__process_auxtrace_error, .ordered_events = true, }, .input_name = "perf.data", @@ -422,11 +472,6 @@ int cmd_mem(int argc, const char **argv) NULL }; - if (perf_mem_events__init()) { - pr_err("failed: memory events not supported\n"); - return -1; - } - argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, mem_usage, PARSE_OPT_KEEP_UNKNOWN); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 772f1057647ff..fd39116506123 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -891,13 +891,13 @@ static int record__open(struct record *rec) * event synthesis. */ if (opts->initial_delay || target__has_cpu(&opts->target)) { - pos = perf_evlist__get_tracking_event(evlist); + pos = evlist__get_tracking_event(evlist); if (!evsel__is_dummy_event(pos)) { /* Set up dummy event. */ if (evlist__add_dummy(evlist)) return -ENOMEM; pos = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, pos); + evlist__set_tracking_event(evlist, pos); } /* @@ -910,7 +910,7 @@ static int record__open(struct record *rec) pos->immediate = 1; } - perf_evlist__config(evlist, opts, &callchain_param); + evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, pos) { try_again: @@ -923,7 +923,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && pos->leader != pos && pos->weak_group) { - pos = perf_evlist__reset_weak_group(evlist, pos, true); + pos = evlist__reset_weak_group(evlist, pos, true); goto try_again; } rc = -errno; @@ -935,7 +935,7 @@ try_again: pos->supported = true; } - if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(evlist)) { + if (symbol_conf.kptr_restrict && !evlist__exclude_kernel(evlist)) { pr_warning( "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n" "check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n" @@ -946,7 +946,7 @@ try_again: "even with a suitable vmlinux or kallsyms file.\n\n"); } - if (perf_evlist__apply_filters(evlist, &pos)) { + if (evlist__apply_filters(evlist, &pos)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", pos->filter, evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); @@ -1166,7 +1166,7 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist, rc = record__write(rec, NULL, &finished_round_event, sizeof(finished_round_event)); if (overwrite) - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); out: return rc; } @@ -1333,7 +1333,7 @@ record__switch_output(struct record *rec, bool at_exit) static volatile int workload_exec_errno; /* - * perf_evlist__prepare_workload will send a SIGUSR1 + * evlist__prepare_workload will send a SIGUSR1 * if the fork fails, since we asked by setting its * want_signal to true. */ @@ -1349,8 +1349,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, static void snapshot_sig_handler(int sig); static void alarm_sig_handler(int sig); -static const struct perf_event_mmap_page * -perf_evlist__pick_pc(struct evlist *evlist) +static const struct perf_event_mmap_page *evlist__pick_pc(struct evlist *evlist) { if (evlist) { if (evlist->mmap && evlist->mmap[0].core.base) @@ -1363,9 +1362,7 @@ perf_evlist__pick_pc(struct evlist *evlist) static const struct perf_event_mmap_page *record__pick_pc(struct record *rec) { - const struct perf_event_mmap_page *pc; - - pc = perf_evlist__pick_pc(rec->evlist); + const struct perf_event_mmap_page *pc = evlist__pick_pc(rec->evlist); if (pc) return pc; return NULL; @@ -1444,7 +1441,7 @@ static int record__synthesize(struct record *rec, bool tail) goto out; } - if (!perf_evlist__exclude_kernel(rec->evlist)) { + if (!evlist__exclude_kernel(rec->evlist)) { err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, machine); WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n" @@ -1548,7 +1545,7 @@ static int record__setup_sb_evlist(struct record *rec) } } #endif - if (perf_evlist__start_sb_thread(rec->sb_evlist, &rec->opts.target)) { + if (evlist__start_sb_thread(rec->sb_evlist, &rec->opts.target)) { pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); opts->no_bpf_event = true; } @@ -1593,6 +1590,16 @@ static int record__init_clock(struct record *rec) return 0; } +static void hit_auxtrace_snapshot_trigger(struct record *rec) +{ + if (trigger_is_ready(&auxtrace_snapshot_trigger)) { + trigger_hit(&auxtrace_snapshot_trigger); + auxtrace_record__snapshot_started = 1; + if (auxtrace_record__snapshot_start(rec->itr)) + trigger_error(&auxtrace_snapshot_trigger); + } +} + static int __cmd_record(struct record *rec, int argc, const char **argv) { int err; @@ -1679,9 +1686,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) record__init_features(rec); if (forks) { - err = perf_evlist__prepare_workload(rec->evlist, &opts->target, - argv, data->is_pipe, - workload_exec_failed_signal); + err = evlist__prepare_workload(rec->evlist, &opts->target, argv, data->is_pipe, + workload_exec_failed_signal); if (err < 0) { pr_err("Couldn't run the workload!\n"); status = err; @@ -1825,7 +1831,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) machine); free(event); - perf_evlist__start_workload(rec->evlist); + evlist__start_workload(rec->evlist); } if (evlist__initialize_ctlfd(rec->evlist, opts->ctl_fd, opts->ctl_fd_ack)) @@ -1851,11 +1857,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * BKW_MMAP_EMPTY here: when done == true and * hits != rec->samples in previous round. * - * perf_evlist__toggle_bkw_mmap ensure we never + * evlist__toggle_bkw_mmap ensure we never * convert BKW_MMAP_EMPTY to BKW_MMAP_DATA_PENDING. */ if (trigger_is_hit(&switch_output_trigger) || done || draining) - perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING); + evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING); if (record__mmap_read_all(rec, false) < 0) { trigger_error(&auxtrace_snapshot_trigger); @@ -1894,7 +1900,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * record__mmap_read_all(): we should have collected * data from it. */ - perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_RUNNING); + evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_RUNNING); if (!quiet) fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n", @@ -1937,6 +1943,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) case EVLIST_CTL_CMD_DISABLE: pr_info(EVLIST_DISABLED_MSG); break; + case EVLIST_CTL_CMD_SNAPSHOT: + hit_auxtrace_snapshot_trigger(rec); + evlist__ctlfd_ack(rec->evlist); + break; case EVLIST_CTL_CMD_ACK: case EVLIST_CTL_CMD_UNSUPPORTED: default: @@ -2052,7 +2062,7 @@ out_delete_session: perf_session__delete(session); if (!opts->no_bpf_event) - perf_evlist__stop_sb_thread(rec->sb_evlist); + evlist__stop_sb_thread(rec->sb_evlist); return status; } @@ -2208,7 +2218,7 @@ static int record__parse_mmap_pages(const struct option *opt, *p = '\0'; if (*s) { - ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s); + ret = __evlist__parse_mmap_pages(&mmap_pages, s); if (ret) goto out_free; opts->mmap_pages = mmap_pages; @@ -2219,7 +2229,7 @@ static int record__parse_mmap_pages(const struct option *opt, goto out_free; } - ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1); + ret = __evlist__parse_mmap_pages(&mmap_pages, p + 1); if (ret) goto out_free; @@ -2234,27 +2244,9 @@ static int parse_control_option(const struct option *opt, const char *str, int unset __maybe_unused) { - char *comma = NULL, *endptr = NULL; - struct record_opts *config = (struct record_opts *)opt->value; - - if (strncmp(str, "fd:", 3)) - return -EINVAL; - - config->ctl_fd = strtoul(&str[3], &endptr, 0); - if (endptr == &str[3]) - return -EINVAL; - - comma = strchr(str, ','); - if (comma) { - if (endptr != comma) - return -EINVAL; - - config->ctl_fd_ack = strtoul(comma + 1, &endptr, 0); - if (endptr == comma + 1 || *endptr != '\0') - return -EINVAL; - } + struct record_opts *opts = opt->value; - return 0; + return evlist__parse_control(str, &opts->ctl_fd, &opts->ctl_fd_ack, &opts->ctl_fd_close); } static void switch_output_size_warn(struct record *rec) @@ -2417,7 +2409,7 @@ static bool dry_run; * XXX Will stay a global variable till we fix builtin-script.c to stop messing * with it and switch to use the library functions in perf_evlist that came * from builtin-record.c, i.e. use record_opts, - * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record', + * evlist__prepare_workload, etc instead of fork+exec'in 'perf record', * using pipes, etc. */ static struct option __record_options[] = { @@ -2480,6 +2472,8 @@ static struct option __record_options[] = { OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"), OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr, "Record the sample physical addresses"), + OPT_BOOLEAN(0, "data-page-size", &record.opts.sample_data_page_size, + "Record the sampled data address data page size"), OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"), OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time, &record.opts.sample_time_set, @@ -2596,9 +2590,11 @@ static struct option __record_options[] = { "libpfm4 event selector. use 'perf list' to list available events", parse_libpfm_events_option), #endif - OPT_CALLBACK(0, "control", &record.opts, "fd:ctl-fd[,ack-fd]", - "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events).\n" - "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.", + OPT_CALLBACK(0, "control", &record.opts, "fd:ctl-fd[,ack-fd] or fifo:ctl-fifo[,ack-fifo]", + "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events,\n" + "\t\t\t 'snapshot': AUX area tracing snapshot).\n" + "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n" + "\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.", parse_control_option), OPT_END() }; @@ -2671,12 +2667,14 @@ int cmd_record(int argc, const char **argv) !perf_can_record_switch_events()) { ui__error("kernel does not support recording context switch events\n"); parse_options_usage(record_usage, record_options, "switch-events", 0); - return -EINVAL; + err = -EINVAL; + goto out_opts; } if (switch_output_setup(rec)) { parse_options_usage(record_usage, record_options, "switch-output", 0); - return -EINVAL; + err = -EINVAL; + goto out_opts; } if (rec->switch_output.time) { @@ -2687,8 +2685,10 @@ int cmd_record(int argc, const char **argv) if (rec->switch_output.num_files) { rec->switch_output.filenames = calloc(sizeof(char *), rec->switch_output.num_files); - if (!rec->switch_output.filenames) - return -EINVAL; + if (!rec->switch_output.filenames) { + err = -EINVAL; + goto out_opts; + } } /* @@ -2704,7 +2704,8 @@ int cmd_record(int argc, const char **argv) rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits); if (!rec->affinity_mask.bits) { pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits); - return -ENOMEM; + err = -ENOMEM; + goto out_opts; } pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits); } @@ -2790,7 +2791,7 @@ int cmd_record(int argc, const char **argv) rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX || rec->opts.target.pid; err = -ENOMEM; - if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0) + if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0) usage_with_options(record_usage, record_options); err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts); @@ -2835,6 +2836,8 @@ out: evlist__delete(rec->evlist); symbol__exit(); auxtrace_record__free(rec->itr); +out_opts: + evlist__close_control(rec->opts.ctl_fd, rec->opts.ctl_fd_ack, &rec->opts.ctl_fd_close); return err; } @@ -2842,12 +2845,7 @@ static void snapshot_sig_handler(int sig __maybe_unused) { struct record *rec = &record; - if (trigger_is_ready(&auxtrace_snapshot_trigger)) { - trigger_hit(&auxtrace_snapshot_trigger); - auxtrace_record__snapshot_started = 1; - if (auxtrace_record__snapshot_start(record.itr)) - trigger_error(&auxtrace_snapshot_trigger); - } + hit_auxtrace_snapshot_trigger(rec); if (switch_output_signal(rec)) trigger_hit(&switch_output_trigger); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3c74c9c0f3c38..2a845d6cac09f 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -211,7 +211,7 @@ static void setup_forced_leader(struct report *report, struct evlist *evlist) { if (report->group_set) - perf_evlist__force_leader(evlist); + evlist__force_leader(evlist); } static int process_feature_event(struct perf_session *session, @@ -226,6 +226,8 @@ static int process_feature_event(struct perf_session *session, pr_err("failed: wrong feature ID: %" PRI_lu64 "\n", event->feat.feat_id); return -1; + } else if (rep->header_only) { + session_done = 1; } /* @@ -493,8 +495,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report return ret + fprintf(fp, "\n#\n"); } -static int perf_evlist__tui_block_hists_browse(struct evlist *evlist, - struct report *rep) +static int evlist__tui_block_hists_browse(struct evlist *evlist, struct report *rep) { struct evsel *pos; int i = 0, ret; @@ -511,9 +512,7 @@ static int perf_evlist__tui_block_hists_browse(struct evlist *evlist, return 0; } -static int perf_evlist__tty_browse_hists(struct evlist *evlist, - struct report *rep, - const char *help) +static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, const char *help) { struct evsel *pos; int i = 0; @@ -566,7 +565,7 @@ static void report__warn_kptr_restrict(const struct report *rep) struct map *kernel_map = machine__kernel_map(&rep->session->machines.host); struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL; - if (perf_evlist__exclude_kernel(rep->session->evlist)) + if (evlist__exclude_kernel(rep->session->evlist)) return; if (kernel_map == NULL || @@ -595,7 +594,7 @@ static int report__gtk_browse_hists(struct report *rep, const char *help) int (*hist_browser)(struct evlist *evlist, const char *help, struct hist_browser_timer *timer, float min_pcnt); - hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists"); + hist_browser = dlsym(perf_gtk_handle, "evlist__gtk_browse_hists"); if (hist_browser == NULL) { ui__error("GTK browser not found!\n"); @@ -622,14 +621,12 @@ static int report__browse_hists(struct report *rep) switch (use_browser) { case 1: if (rep->total_cycles_mode) { - ret = perf_evlist__tui_block_hists_browse(evlist, rep); + ret = evlist__tui_block_hists_browse(evlist, rep); break; } - ret = perf_evlist__tui_browse_hists(evlist, help, NULL, - rep->min_percent, - &session->header.env, - true, &rep->annotation_opts); + ret = evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, + &session->header.env, true, &rep->annotation_opts); /* * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. @@ -641,7 +638,7 @@ static int report__browse_hists(struct report *rep) ret = report__gtk_browse_hists(rep, help); break; default: - ret = perf_evlist__tty_browse_hists(evlist, rep, help); + ret = evlist__tty_browse_hists(evlist, rep, help); break; } @@ -933,7 +930,7 @@ static int __cmd_report(struct report *rep) if (dump_trace) { perf_session__fprintf_nr_events(session, stdout); - perf_evlist__fprintf_nr_events(session->evlist, stdout); + evlist__fprintf_nr_events(session->evlist, stdout); return 0; } } @@ -1517,6 +1514,13 @@ repeat: perf_session__fprintf_info(session, stdout, report.show_full_info); if (report.header_only) { + if (data.is_pipe) { + /* + * we need to process first few records + * which contains PERF_RECORD_HEADER_FEATURE. + */ + perf_session__process_events(session); + } ret = 0; goto error; } diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index e6fc297cee91d..69c769b04a61f 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -130,7 +130,8 @@ struct work_atoms { struct thread *thread; struct rb_node node; u64 max_lat; - u64 max_lat_at; + u64 max_lat_start; + u64 max_lat_end; u64 total_lat; u64 nb_atoms; u64 total_runtime; @@ -1096,7 +1097,8 @@ add_sched_in_event(struct work_atoms *atoms, u64 timestamp) atoms->total_lat += delta; if (delta > atoms->max_lat) { atoms->max_lat = delta; - atoms->max_lat_at = timestamp; + atoms->max_lat_start = atom->wake_up_time; + atoms->max_lat_end = timestamp; } atoms->nb_atoms++; } @@ -1322,7 +1324,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_ int i; int ret; u64 avg; - char max_lat_at[32]; + char max_lat_start[32], max_lat_end[32]; if (!work_list->nb_atoms) return; @@ -1344,13 +1346,14 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_ printf(" "); avg = work_list->total_lat / work_list->nb_atoms; - timestamp__scnprintf_usec(work_list->max_lat_at, max_lat_at, sizeof(max_lat_at)); + timestamp__scnprintf_usec(work_list->max_lat_start, max_lat_start, sizeof(max_lat_start)); + timestamp__scnprintf_usec(work_list->max_lat_end, max_lat_end, sizeof(max_lat_end)); - printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13s s\n", + printf("|%11.3f ms |%9" PRIu64 " | avg:%8.3f ms | max:%8.3f ms | max start: %12s s | max end: %12s s\n", (double)work_list->total_runtime / NSEC_PER_MSEC, work_list->nb_atoms, (double)avg / NSEC_PER_MSEC, (double)work_list->max_lat / NSEC_PER_MSEC, - max_lat_at); + max_lat_start, max_lat_end); } static int pid_cmp(struct work_atoms *l, struct work_atoms *r) @@ -3033,8 +3036,7 @@ static int perf_sched__timehist(struct perf_sched *sched) setup_pager(); /* prefer sched_waking if it is captured */ - if (perf_evlist__find_tracepoint_by_name(session->evlist, - "sched:sched_waking")) + if (evlist__find_tracepoint_by_name(session->evlist, "sched:sched_waking")) handlers[1].handler = timehist_sched_wakeup_ignore; /* setup per-evsel handlers */ @@ -3042,8 +3044,7 @@ static int perf_sched__timehist(struct perf_sched *sched) goto out; /* sched_switch event at a minimum needs to exist */ - if (!perf_evlist__find_tracepoint_by_name(session->evlist, - "sched:sched_switch")) { + if (!evlist__find_tracepoint_by_name(session->evlist, "sched:sched_switch")) { pr_err("No sched_switch events found. Have you run 'perf sched record'?\n"); goto out; } @@ -3137,7 +3138,8 @@ static void __merge_work_atoms(struct rb_root_cached *root, struct work_atoms *d list_splice(&data->work_list, &this->work_list); if (this->max_lat < data->max_lat) { this->max_lat = data->max_lat; - this->max_lat_at = data->max_lat_at; + this->max_lat_start = data->max_lat_start; + this->max_lat_end = data->max_lat_end; } zfree(&data); return; @@ -3176,9 +3178,9 @@ static int perf_sched__lat(struct perf_sched *sched) perf_sched__merge_lat(sched); perf_sched__sort_lat(sched); - printf("\n -----------------------------------------------------------------------------------------------------------------\n"); - printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); - printf(" -----------------------------------------------------------------------------------------------------------------\n"); + printf("\n -------------------------------------------------------------------------------------------------------------------------------------------\n"); + printf(" Task | Runtime ms | Switches | Avg delay ms | Max delay ms | Max delay start | Max delay end |\n"); + printf(" -------------------------------------------------------------------------------------------------------------------------------------------\n"); next = rb_first_cached(&sched->sorted_atom_root); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 484ce6067d23f..42dad4a0f8cf4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -30,6 +30,7 @@ #include "util/thread-stack.h" #include "util/time-utils.h" #include "util/path.h" +#include "util/event.h" #include "ui/ui.h" #include "print_binary.h" #include "archinsn.h" @@ -115,6 +116,7 @@ enum perf_output_field { PERF_OUTPUT_SRCCODE = 1ULL << 30, PERF_OUTPUT_IPC = 1ULL << 31, PERF_OUTPUT_TOD = 1ULL << 32, + PERF_OUTPUT_DATA_PAGE_SIZE = 1ULL << 33, }; struct perf_script { @@ -179,10 +181,12 @@ struct output_option { {.str = "srccode", .field = PERF_OUTPUT_SRCCODE}, {.str = "ipc", .field = PERF_OUTPUT_IPC}, {.str = "tod", .field = PERF_OUTPUT_TOD}, + {.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE}, }; enum { OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX, + OUTPUT_TYPE_OTHER, OUTPUT_TYPE_MAX }; @@ -251,7 +255,8 @@ static struct { PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC | - PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR, + PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR | + PERF_OUTPUT_DATA_PAGE_SIZE, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -279,6 +284,18 @@ static struct { .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, + + [OUTPUT_TYPE_OTHER] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, }; struct evsel_script { @@ -339,8 +356,11 @@ static inline int output_type(unsigned int type) case PERF_TYPE_SYNTH: return OUTPUT_TYPE_SYNTH; default: - return type; + if (type < PERF_TYPE_MAX) + return type; } + + return OUTPUT_TYPE_OTHER; } static inline unsigned int attr_type(unsigned int type) @@ -499,6 +519,10 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR)) return -EINVAL; + if (PRINT_FIELD(DATA_PAGE_SIZE) && + evsel__check_stype(evsel, PERF_SAMPLE_DATA_PAGE_SIZE, "DATA_PAGE_SIZE", PERF_OUTPUT_DATA_PAGE_SIZE)) + return -EINVAL; + return 0; } @@ -702,12 +726,14 @@ static int perf_sample__fprintf_start(struct perf_script *script, char tstr[128]; if (PRINT_FIELD(COMM)) { + const char *comm = thread ? thread__comm_str(thread) : ":-1"; + if (latency_format) - printed += fprintf(fp, "%8.8s ", thread__comm_str(thread)); + printed += fprintf(fp, "%8.8s ", comm); else if (PRINT_FIELD(IP) && evsel__has_callchain(evsel) && symbol_conf.use_callchain) - printed += fprintf(fp, "%s ", thread__comm_str(thread)); + printed += fprintf(fp, "%s ", comm); else - printed += fprintf(fp, "%16s ", thread__comm_str(thread)); + printed += fprintf(fp, "%16s ", comm); } if (PRINT_FIELD(PID) && PRINT_FIELD(TID)) @@ -1845,7 +1871,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, u64 val; if (!evsel->stats) - perf_evlist__alloc_stats(script->session->evlist, false); + evlist__alloc_stats(script->session->evlist, false); if (evsel_script(evsel->leader)->gnum++ == 0) perf_stat__reset_shadow_stats(); val = sample->period * evsel->scale; @@ -1918,6 +1944,7 @@ static void process_event(struct perf_script *script, unsigned int type = output_type(attr->type); struct evsel_script *es = evsel->priv; FILE *fp = es->fp; + char str[PAGE_SIZE_NAME_LEN]; if (output[type].fields == 0) return; @@ -2006,6 +2033,9 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(PHYS_ADDR)) fprintf(fp, "%16" PRIx64, sample->phys_addr); + if (PRINT_FIELD(DATA_PAGE_SIZE)) + fprintf(fp, " %s", get_page_size_name(sample->data_page_size, str)); + perf_sample__fprintf_ipc(sample, attr, fp); fprintf(fp, "\n"); @@ -2222,7 +2252,7 @@ static int print_event_with_time(struct perf_tool *tool, { struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = evlist__id2evsel(session->evlist, sample->id); struct thread *thread = NULL; if (evsel && !evsel->core.attr.sample_id_all) { @@ -2238,7 +2268,7 @@ static int print_event_with_time(struct perf_tool *tool, if (tid != -1) thread = machine__findnew_thread(machine, pid, tid); - if (thread && evsel) { + if (evsel) { perf_sample__fprintf_start(script, sample, thread, evsel, event->header.type, stdout); } @@ -3306,7 +3336,7 @@ static int set_maps(struct perf_script *script) perf_evlist__set_maps(&evlist->core, script->cpus, script->threads); - if (perf_evlist__alloc_stats(evlist, true)) + if (evlist__alloc_stats(evlist, true)) return -ENOMEM; script->allocated = true; @@ -3504,7 +3534,8 @@ int cmd_script(int argc, const char **argv) "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,srcline,period,iregs,uregs,brstack," "brstacksym,flags,bpf-output,brstackinsn,brstackoff," - "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod", + "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod," + "data_page_size", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), @@ -3933,7 +3964,7 @@ out_delete: zfree(&script.ptime_range); } - perf_evlist__free_stats(session->evlist); + evlist__free_stats(session->evlist); perf_session__delete(session); if (script_started) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index fddc97cac9841..8cc24967bc273 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -56,7 +56,7 @@ #include "util/cpumap.h" #include "util/thread_map.h" #include "util/counts.h" -#include "util/group.h" +#include "util/topdown.h" #include "util/session.h" #include "util/tool.h" #include "util/string2.h" @@ -128,6 +128,15 @@ static const char * topdown_attrs[] = { NULL, }; +static const char *topdown_metric_attrs[] = { + "slots", + "topdown-retiring", + "topdown-bad-spec", + "topdown-fe-bound", + "topdown-be-bound", + NULL, +}; + static const char *smi_cost_attrs = { "{" "msr/aperf/," @@ -261,7 +270,7 @@ static void perf_stat__reset_stats(void) { int i; - perf_evlist__reset_stats(evsel_list); + evlist__reset_stats(evsel_list); perf_stat__reset_shadow_stats(); for (i = 0; i < stat_config.stats_num; i++) @@ -525,7 +534,7 @@ static void disable_counters(void) static volatile int workload_exec_errno; /* - * perf_evlist__prepare_workload will send a SIGUSR1 + * evlist__prepare_workload will send a SIGUSR1 * if the fork fails, since we asked by setting its * want_signal to true. */ @@ -578,6 +587,7 @@ static void process_evlist(struct evlist *evlist, unsigned int interval) process_interval(); pr_info(EVLIST_DISABLED_MSG); break; + case EVLIST_CTL_CMD_SNAPSHOT: case EVLIST_CTL_CMD_ACK: case EVLIST_CTL_CMD_UNSUPPORTED: default: @@ -714,8 +724,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) bool second_pass = false; if (forks) { - if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe, - workload_exec_failed_signal) < 0) { + if (evlist__prepare_workload(evsel_list, &target, argv, is_pipe, workload_exec_failed_signal) < 0) { perror("failed to prepare workload"); return -1; } @@ -723,7 +732,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) } if (group) - perf_evlist__set_leader(evsel_list); + evlist__set_leader(evsel_list); if (affinity__setup(&affinity) < 0) return -1; @@ -750,7 +759,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && counter->leader != counter && counter->weak_group) { - perf_evlist__reset_weak_group(evsel_list, counter, false); + evlist__reset_weak_group(evsel_list, counter, false); assert(counter->reset_group); second_pass = true; continue; @@ -833,7 +842,7 @@ try_again_reset: return -1; } - if (perf_evlist__apply_filters(evsel_list, &counter)) { + if (evlist__apply_filters(evsel_list, &counter)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", counter->filter, evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); @@ -866,7 +875,7 @@ try_again_reset: clock_gettime(CLOCK_MONOTONIC, &ref_time); if (forks) { - perf_evlist__start_workload(evsel_list); + evlist__start_workload(evsel_list); enable_counters(); if (interval || timeout || evlist__ctlfd_initialized(evsel_list)) @@ -904,10 +913,10 @@ try_again_reset: update_stats(&walltime_nsecs_stats, t1 - t0); if (stat_config.aggr_mode == AGGR_GLOBAL) - perf_evlist__save_aggr_prev_raw_counts(evsel_list); + evlist__save_aggr_prev_raw_counts(evsel_list); - perf_evlist__copy_prev_raw_counts(evsel_list); - perf_evlist__reset_prev_raw_counts(evsel_list); + evlist__copy_prev_raw_counts(evsel_list); + evlist__reset_prev_raw_counts(evsel_list); runtime_stat_reset(&stat_config); perf_stat__reset_shadow_per_stat(&rt_stat); } else @@ -962,9 +971,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv) /* Do not print anything if we record to the pipe. */ if (STAT_RECORD && perf_stat.data.is_pipe) return; + if (stat_config.quiet) + return; - perf_evlist__print_counters(evsel_list, &stat_config, &target, - ts, argc, argv); + evlist__print_counters(evsel_list, &stat_config, &target, ts, argc, argv); } static volatile int signr = -1; @@ -1045,27 +1055,20 @@ static int parse_control_option(const struct option *opt, const char *str, int unset __maybe_unused) { - char *comma = NULL, *endptr = NULL; - struct perf_stat_config *config = (struct perf_stat_config *)opt->value; - - if (strncmp(str, "fd:", 3)) - return -EINVAL; - - config->ctl_fd = strtoul(&str[3], &endptr, 0); - if (endptr == &str[3]) - return -EINVAL; + struct perf_stat_config *config = opt->value; - comma = strchr(str, ','); - if (comma) { - if (endptr != comma) - return -EINVAL; + return evlist__parse_control(str, &config->ctl_fd, &config->ctl_fd_ack, &config->ctl_fd_close); +} - config->ctl_fd_ack = strtoul(comma + 1, &endptr, 0); - if (endptr == comma + 1 || *endptr != '\0') - return -EINVAL; +static int parse_stat_cgroups(const struct option *opt, + const char *str, int unset) +{ + if (stat_config.cgroup_list) { + pr_err("--cgroup and --for-each-cgroup cannot be used together\n"); + return -1; } - return 0; + return parse_cgroups(opt, str, unset); } static struct option stat_options[] = { @@ -1111,7 +1114,9 @@ static struct option stat_options[] = { OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator", "print counts with custom separator"), OPT_CALLBACK('G', "cgroup", &evsel_list, "name", - "monitor event in cgroup name only", parse_cgroups), + "monitor event in cgroup name only", parse_stat_cgroups), + OPT_STRING(0, "for-each-cgroup", &stat_config.cgroup_list, "name", + "expand events for each cgroup"), OPT_STRING('o', "output", &output_name, "file", "output file name"), OPT_BOOLEAN(0, "append", &append_file, "append to the output file"), OPT_INTEGER(0, "log-fd", &output_fd, @@ -1166,77 +1171,82 @@ static struct option stat_options[] = { "threads of same physical core"), OPT_BOOLEAN(0, "summary", &stat_config.summary, "print summary for interval mode"), + OPT_BOOLEAN(0, "quiet", &stat_config.quiet, + "don't print output (useful with record)"), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", parse_libpfm_events_option), #endif - OPT_CALLBACK(0, "control", &stat_config, "fd:ctl-fd[,ack-fd]", + OPT_CALLBACK(0, "control", &stat_config, "fd:ctl-fd[,ack-fd] or fifo:ctl-fifo[,ack-fifo]", "Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events).\n" - "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.", + "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n" + "\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.", parse_control_option), OPT_END() }; -static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_socket(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int cpu) { return cpu_map__get_socket(map, cpu, NULL); } -static int perf_stat__get_die(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_die(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int cpu) { return cpu_map__get_die(map, cpu, NULL); } -static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int cpu) { return cpu_map__get_core(map, cpu, NULL); } -static int perf_stat__get_node(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_node(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int cpu) { return cpu_map__get_node(map, cpu, NULL); } -static int perf_stat__get_aggr(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config, aggr_get_id_t get_id, struct perf_cpu_map *map, int idx) { int cpu; + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); if (idx >= map->nr) - return -1; + return id; cpu = map->map[idx]; - if (config->cpus_aggr_map->map[cpu] == -1) + if (cpu_map__aggr_cpu_id_is_empty(config->cpus_aggr_map->map[cpu])) config->cpus_aggr_map->map[cpu] = get_id(config, map, idx); - return config->cpus_aggr_map->map[cpu]; + id = config->cpus_aggr_map->map[cpu]; + return id; } -static int perf_stat__get_socket_cached(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_socket_cached(struct perf_stat_config *config, struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx); } -static int perf_stat__get_die_cached(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *config, struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_die, map, idx); } -static int perf_stat__get_core_cached(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_core_cached(struct perf_stat_config *config, struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_core, map, idx); } -static int perf_stat__get_node_cached(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_node_cached(struct perf_stat_config *config, struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_node, map, idx); @@ -1310,14 +1320,29 @@ static int perf_stat_init_aggr_mode(void) * the aggregation translate cpumap. */ nr = perf_cpu_map__max(evsel_list->core.cpus); - stat_config.cpus_aggr_map = perf_cpu_map__empty_new(nr + 1); + stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1); return stat_config.cpus_aggr_map ? 0 : -ENOMEM; } +static void cpu_aggr_map__delete(struct cpu_aggr_map *map) +{ + if (map) { + WARN_ONCE(refcount_read(&map->refcnt) != 0, + "cpu_aggr_map refcnt unbalanced\n"); + free(map); + } +} + +static void cpu_aggr_map__put(struct cpu_aggr_map *map) +{ + if (map && refcount_dec_and_test(&map->refcnt)) + cpu_aggr_map__delete(map); +} + static void perf_stat__exit_aggr_mode(void) { - perf_cpu_map__put(stat_config.aggr_map); - perf_cpu_map__put(stat_config.cpus_aggr_map); + cpu_aggr_map__put(stat_config.aggr_map); + cpu_aggr_map__put(stat_config.cpus_aggr_map); stat_config.aggr_map = NULL; stat_config.cpus_aggr_map = NULL; } @@ -1337,117 +1362,108 @@ static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *m return cpu; } -static int perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data) { struct perf_env *env = data; int cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + + if (cpu != -1) + id.socket = env->cpu[cpu].socket_id; - return cpu == -1 ? -1 : env->cpu[cpu].socket_id; + return id; } -static int perf_env__get_die(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data) { struct perf_env *env = data; - int die_id = -1, cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + int cpu = perf_env__get_cpu(env, map, idx); if (cpu != -1) { /* - * Encode socket in bit range 15:8 - * die_id is relative to socket, - * we need a global id. So we combine - * socket + die id + * die_id is relative to socket, so start + * with the socket ID and then add die to + * make a unique ID. */ - if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n")) - return -1; - - if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n")) - return -1; - - die_id = (env->cpu[cpu].socket_id << 8) | (env->cpu[cpu].die_id & 0xff); + id.socket = env->cpu[cpu].socket_id; + id.die = env->cpu[cpu].die_id; } - return die_id; + return id; } -static int perf_env__get_core(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data) { struct perf_env *env = data; - int core = -1, cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + int cpu = perf_env__get_cpu(env, map, idx); if (cpu != -1) { /* - * Encode socket in bit range 31:24 - * encode die id in bit range 23:16 * core_id is relative to socket and die, - * we need a global id. So we combine - * socket + die id + core id + * we need a global id. So we set + * socket, die id and core id */ - if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n")) - return -1; - - if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n")) - return -1; - - if (WARN_ONCE(env->cpu[cpu].core_id >> 16, "The core id number is too big.\n")) - return -1; - - core = (env->cpu[cpu].socket_id << 24) | - (env->cpu[cpu].die_id << 16) | - (env->cpu[cpu].core_id & 0xffff); + id.socket = env->cpu[cpu].socket_id; + id.die = env->cpu[cpu].die_id; + id.core = env->cpu[cpu].core_id; } - return core; + return id; } -static int perf_env__get_node(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data) { int cpu = perf_env__get_cpu(data, map, idx); + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); - return perf_env__numa_node(data, cpu); + id.node = perf_env__numa_node(data, cpu); + return id; } static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct perf_cpu_map **sockp) + struct cpu_aggr_map **sockp) { return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env); } static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct perf_cpu_map **diep) + struct cpu_aggr_map **diep) { return cpu_map__build_map(cpus, diep, perf_env__get_die, env); } static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct perf_cpu_map **corep) + struct cpu_aggr_map **corep) { return cpu_map__build_map(cpus, corep, perf_env__get_core, env); } static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct perf_cpu_map **nodep) + struct cpu_aggr_map **nodep) { return cpu_map__build_map(cpus, nodep, perf_env__get_node, env); } -static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int idx) { return perf_env__get_socket(map, idx, &perf_stat.session->header.env); } -static int perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int idx) { return perf_env__get_die(map, idx, &perf_stat.session->header.env); } -static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int idx) { return perf_env__get_core(map, idx, &perf_stat.session->header.env); } -static int perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int idx) { return perf_env__get_node(map, idx, &perf_stat.session->header.env); @@ -1497,55 +1513,6 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st) return 0; } -static int topdown_filter_events(const char **attr, char **str, bool use_group) -{ - int off = 0; - int i; - int len = 0; - char *s; - - for (i = 0; attr[i]; i++) { - if (pmu_have_event("cpu", attr[i])) { - len += strlen(attr[i]) + 1; - attr[i - off] = attr[i]; - } else - off++; - } - attr[i - off] = NULL; - - *str = malloc(len + 1 + 2); - if (!*str) - return -1; - s = *str; - if (i - off == 0) { - *s = 0; - return 0; - } - if (use_group) - *s++ = '{'; - for (i = 0; attr[i]; i++) { - strcpy(s, attr[i]); - s += strlen(s); - *s++ = ','; - } - if (use_group) { - s[-1] = '}'; - *s = 0; - } else - s[-1] = 0; - return 0; -} - -__weak bool arch_topdown_check_group(bool *warn) -{ - *warn = false; - return false; -} - -__weak void arch_topdown_group_warn(void) -{ -} - /* * Add default attributes, if there were no attributes specified or * if -d/--detailed, -d -d or -d -d -d is used: @@ -1742,6 +1709,24 @@ static int add_default_attributes(void) char *str = NULL; bool warn = false; + if (!force_metric_only) + stat_config.metric_only = true; + + if (topdown_filter_events(topdown_metric_attrs, &str, 1) < 0) { + pr_err("Out of memory\n"); + return -1; + } + if (topdown_metric_attrs[0] && str) { + if (!stat_config.interval && !stat_config.metric_only) { + fprintf(stat_config.output, + "Topdown accuracy may decrease when measuring long periods.\n" + "Please print the result regularly, e.g. -I1000\n"); + } + goto setup_metrics; + } + + zfree(&str); + if (stat_config.aggr_mode != AGGR_GLOBAL && stat_config.aggr_mode != AGGR_CORE) { pr_err("top down event configuration requires --per-core mode\n"); @@ -1753,8 +1738,6 @@ static int add_default_attributes(void) return -1; } - if (!force_metric_only) - stat_config.metric_only = true; if (topdown_filter_events(topdown_attrs, &str, arch_topdown_check_group(&warn)) < 0) { pr_err("Out of memory\n"); @@ -1763,6 +1746,7 @@ static int add_default_attributes(void) if (topdown_attrs[0] && str) { if (warn) arch_topdown_group_warn(); +setup_metrics: err = parse_events(evsel_list, str, &errinfo); if (err) { fprintf(stderr, @@ -1930,7 +1914,7 @@ static int set_maps(struct perf_stat *st) perf_evlist__set_maps(&evsel_list->core, st->cpus, st->threads); - if (perf_evlist__alloc_stats(evsel_list, true)) + if (evlist__alloc_stats(evsel_list, true)) return -ENOMEM; st->maps_allocated = true; @@ -2063,8 +2047,10 @@ static void setup_system_wide(int forks) struct evsel *counter; evlist__for_each_entry(evsel_list, counter) { - if (!counter->core.system_wide) + if (!counter->core.system_wide && + strcmp(counter->name, "duration_time")) { return; + } } if (evsel_list->core.nr_entries) @@ -2156,7 +2142,7 @@ int cmd_stat(int argc, const char **argv) goto out; } - if (!output) { + if (!output && !stat_config.quiet) { struct timespec tm; mode = append_file ? "a" : "w"; @@ -2250,12 +2236,28 @@ int cmd_stat(int argc, const char **argv) if (add_default_attributes()) goto out; + if (stat_config.cgroup_list) { + if (nr_cgroups > 0) { + pr_err("--cgroup and --for-each-cgroup cannot be used together\n"); + parse_options_usage(stat_usage, stat_options, "G", 1); + parse_options_usage(NULL, stat_options, "for-each-cgroup", 0); + goto out; + } + + if (evlist__expand_cgroup(evsel_list, stat_config.cgroup_list, + &stat_config.metric_events, true) < 0) { + parse_options_usage(stat_usage, stat_options, + "for-each-cgroup", 0); + goto out; + } + } + target__validate(&target); if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide)) target.per_thread = true; - if (perf_evlist__create_maps(evsel_list, &target) < 0) { + if (evlist__create_maps(evsel_list, &target) < 0) { if (target__has_task(&target)) { pr_err("Problems finding threads of monitor\n"); parse_options_usage(stat_usage, stat_options, "p", 1); @@ -2314,7 +2316,7 @@ int cmd_stat(int argc, const char **argv) goto out; } - if (perf_evlist__alloc_stats(evsel_list, interval)) + if (evlist__alloc_stats(evsel_list, interval)) goto out; if (perf_stat_init_aggr_mode()) @@ -2354,7 +2356,7 @@ int cmd_stat(int argc, const char **argv) run_idx + 1); if (run_idx != 0) - perf_evlist__reset_prev_raw_counts(evsel_list); + evlist__reset_prev_raw_counts(evsel_list); status = run_perf_stat(argc, argv, run_idx); if (forever && status != -1 && !interval) { @@ -2405,7 +2407,7 @@ int cmd_stat(int argc, const char **argv) } perf_stat__exit_aggr_mode(); - perf_evlist__free_stats(evsel_list); + evlist__free_stats(evsel_list); out: zfree(&stat_config.walltime_run); @@ -2416,6 +2418,7 @@ out: metricgroup__rblist_exit(&stat_config.metric_events); runtime_stat_delete(&stat_config); + evlist__close_control(stat_config.ctl_fd, stat_config.ctl_fd_ack, &stat_config.ctl_fd_close); return status; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7c64134472c77..3673c04d16b6d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -641,12 +641,9 @@ repeat: hists->uid_filter_str = top->record_opts.target.uid_str; } - ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt, - top->min_percent, - &top->session->header.env, - !top->record_opts.overwrite, - &top->annotation_opts); - + ret = evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, + &top->session->header.env, !top->record_opts.overwrite, + &top->annotation_opts); if (ret == K_RELOAD) { top->zero = true; goto repeat; @@ -782,7 +779,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if (!machine->kptr_restrict_warned && symbol_conf.kptr_restrict && al.cpumode == PERF_RECORD_MISC_KERNEL) { - if (!perf_evlist__exclude_kernel(top->session->evlist)) { + if (!evlist__exclude_kernel(top->session->evlist)) { ui__warning( "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n" "Check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n" @@ -890,7 +887,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) while ((event = perf_mmap__read_event(&md->core)) != NULL) { int ret; - ret = perf_evlist__parse_sample_timestamp(evlist, event, &last_timestamp); + ret = evlist__parse_sample_timestamp(evlist, event, &last_timestamp); if (ret && ret != -1) break; @@ -918,14 +915,14 @@ static void perf_top__mmap_read(struct perf_top *top) int i; if (overwrite) - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING); for (i = 0; i < top->evlist->core.nr_mmaps; i++) perf_top__mmap_read_idx(top, i); if (overwrite) { - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); } } @@ -1025,7 +1022,7 @@ static int perf_top__start_counters(struct perf_top *top) goto out_err; } - perf_evlist__config(evlist, opts, &callchain_param); + evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, counter) { try_again: @@ -1153,13 +1150,13 @@ static int deliver_event(struct ordered_events *qe, return 0; } - ret = perf_evlist__parse_sample(evlist, event, &sample); + ret = evlist__parse_sample(evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); goto next_event; } - evsel = perf_evlist__id2evsel(session->evlist, sample.id); + evsel = evlist__id2evsel(session->evlist, sample.id); assert(evsel != NULL); if (event->header.type == PERF_RECORD_SAMPLE) { @@ -1469,8 +1466,7 @@ int cmd_top(int argc, const char **argv) OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols, "hide kernel symbols"), OPT_CALLBACK('m', "mmap-pages", &opts->mmap_pages, "pages", - "number of mmap data pages", - perf_evlist__parse_mmap_pages), + "number of mmap data pages", evlist__parse_mmap_pages), OPT_INTEGER('r', "realtime", &top.realtime_prio, "collect data with this RT SCHED_FIFO priority"), OPT_INTEGER('d', "delay", &top.delay_secs, @@ -1697,7 +1693,7 @@ int cmd_top(int argc, const char **argv) if (target__none(target)) target->system_wide = true; - if (perf_evlist__create_maps(top.evlist, target) < 0) { + if (evlist__create_maps(top.evlist, target) < 0) { ui__error("Couldn't create thread/CPU maps: %s\n", errno == ENOENT ? "No such process" : str_error_r(errno, errbuf, sizeof(errbuf))); goto out_delete_evlist; @@ -1762,7 +1758,7 @@ int cmd_top(int argc, const char **argv) } #endif - if (perf_evlist__start_sb_thread(top.sb_evlist, target)) { + if (evlist__start_sb_thread(top.sb_evlist, target)) { pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); opts->no_bpf_event = true; } @@ -1770,7 +1766,7 @@ int cmd_top(int argc, const char **argv) status = __cmd_top(&top); if (!opts->no_bpf_event) - perf_evlist__stop_sb_thread(top.sb_evlist); + evlist__stop_sb_thread(top.sb_evlist); out_delete_evlist: evlist__delete(top.evlist); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index bea461b6f937b..85b6a46e85b68 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1762,7 +1762,11 @@ static int trace__read_syscall_info(struct trace *trace, int id) if (table == NULL) return -ENOMEM; - memset(table + trace->sctbl->syscalls.max_id, 0, (id - trace->sctbl->syscalls.max_id) * sizeof(*sc)); + // 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; @@ -3101,7 +3105,7 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st return; } - evsel = perf_evlist__id2evsel(trace->evlist, sample->id); + evsel = evlist__id2evsel(trace->evlist, sample->id); if (evsel == NULL) { fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample->id); return; @@ -3662,7 +3666,7 @@ static int trace__set_filter_loop_pids(struct trace *trace) thread = parent; } - err = perf_evlist__append_tp_filter_pids(trace->evlist, nr, pids); + err = evlist__append_tp_filter_pids(trace->evlist, nr, pids); if (!err && trace->filter_pids.map) err = bpf_map__set_filter_pids(trace->filter_pids.map, nr, pids); @@ -3676,11 +3680,11 @@ static int trace__set_filter_pids(struct trace *trace) * Better not use !target__has_task() here because we need to cover the * case where no threads were specified in the command line, but a * workload was, and in that case we will fill in the thread_map when - * we fork the workload in perf_evlist__prepare_workload. + * we fork the workload in evlist__prepare_workload. */ if (trace->filter_pids.nr > 0) { - err = perf_evlist__append_tp_filter_pids(trace->evlist, trace->filter_pids.nr, - trace->filter_pids.entries); + err = evlist__append_tp_filter_pids(trace->evlist, trace->filter_pids.nr, + trace->filter_pids.entries); if (!err && trace->filter_pids.map) { err = bpf_map__set_filter_pids(trace->filter_pids.map, trace->filter_pids.nr, trace->filter_pids.entries); @@ -3696,9 +3700,8 @@ static int __trace__deliver_event(struct trace *trace, union perf_event *event) { struct evlist *evlist = trace->evlist; struct perf_sample sample; - int err; + int err = evlist__parse_sample(evlist, event, &sample); - err = perf_evlist__parse_sample(evlist, event, &sample); if (err) fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err); else @@ -3731,7 +3734,7 @@ static int trace__deliver_event(struct trace *trace, union perf_event *event) if (!trace->sort_events) return __trace__deliver_event(trace, event); - err = perf_evlist__parse_sample_timestamp(trace->evlist, event, &trace->oe.last); + err = evlist__parse_sample_timestamp(trace->evlist, event, &trace->oe.last); if (err && err != -1) return err; @@ -3947,7 +3950,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (trace->cgroup) evlist__set_default_cgroup(trace->evlist, trace->cgroup); - err = perf_evlist__create_maps(evlist, &trace->opts.target); + err = evlist__create_maps(evlist, &trace->opts.target); if (err < 0) { fprintf(trace->output, "Problems parsing the target to trace, check your options!\n"); goto out_delete_evlist; @@ -3959,14 +3962,13 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_delete_evlist; } - perf_evlist__config(evlist, &trace->opts, &callchain_param); + evlist__config(evlist, &trace->opts, &callchain_param); signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); if (forks) { - err = perf_evlist__prepare_workload(evlist, &trace->opts.target, - argv, false, NULL); + err = evlist__prepare_workload(evlist, &trace->opts.target, argv, false, NULL); if (err < 0) { fprintf(trace->output, "Couldn't run the workload!\n"); goto out_delete_evlist; @@ -4024,7 +4026,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) err = trace__expand_filters(trace, &evsel); if (err) goto out_delete_evlist; - err = perf_evlist__apply_filters(evlist, &evsel); + err = evlist__apply_filters(evlist, &evsel); if (err < 0) goto out_error_apply_filters; @@ -4039,7 +4041,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) evlist__enable(evlist); if (forks) - perf_evlist__start_workload(evlist); + evlist__start_workload(evlist); if (trace->opts.initial_delay) { usleep(trace->opts.initial_delay * 1000); @@ -4225,12 +4227,10 @@ static int trace__replay(struct trace *trace) if (err) goto out; - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "raw_syscalls:sys_enter"); + evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_enter"); /* older kernels have syscalls tp versus raw_syscalls */ if (evsel == NULL) - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "syscalls:sys_enter"); + evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_enter"); if (evsel && (evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 || @@ -4239,11 +4239,9 @@ static int trace__replay(struct trace *trace) goto out; } - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "raw_syscalls:sys_exit"); + evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_exit"); if (evsel == NULL) - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "syscalls:sys_exit"); + evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit"); if (evsel && (evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 || perf_evsel__init_sc_tp_uint_field(evsel, ret))) { @@ -4635,9 +4633,9 @@ do_concat: err = 0; if (lists[0]) { - struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event", - "event selector. use 'perf list' to list available events", - parse_events_option); + struct option o = { + .value = &trace->evlist, + }; err = parse_events_option(&o, lists[0], 0); } out: @@ -4651,9 +4649,12 @@ static int trace__parse_cgroups(const struct option *opt, const char *str, int u { struct trace *trace = opt->value; - if (!list_empty(&trace->evlist->core.entries)) - return parse_cgroups(opt, str, unset); - + if (!list_empty(&trace->evlist->core.entries)) { + struct option o = { + .value = &trace->evlist, + }; + return parse_cgroups(&o, str, unset); + } trace->cgroup = evlist__findnew_cgroup(trace->evlist, str); return 0; @@ -4762,8 +4763,7 @@ int cmd_trace(int argc, const char **argv) OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit, "child tasks do not inherit counters"), OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages", - "number of mmap data pages", - perf_evlist__parse_mmap_pages), + "number of mmap data pages", evlist__parse_mmap_pages), OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user", "user to profile"), OPT_CALLBACK(0, "duration", &trace, "float", @@ -4900,7 +4900,7 @@ int cmd_trace(int argc, const char **argv) if (evsel) { trace.syscalls.events.augmented = evsel; - evsel = perf_evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter"); + evsel = evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter"); if (evsel == NULL) { pr_err("ERROR: raw_syscalls:sys_enter not found in the augmented BPF object\n"); goto out; diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 05cf2af9e2c27..9cd074a3d825d 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -60,7 +60,6 @@ static void library_status(void) STATUS(HAVE_DWARF_SUPPORT, dwarf); STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations); STATUS(HAVE_GLIBC_SUPPORT, glibc); - STATUS(HAVE_GTK2_SUPPORT, gtk2); #ifndef HAVE_SYSCALL_TABLE_SUPPORT STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit); #endif @@ -81,6 +80,7 @@ static void library_status(void) STATUS(HAVE_LIBBPF_SUPPORT, bpf); STATUS(HAVE_AIO_SUPPORT, aio); STATUS(HAVE_ZSTD_SUPPORT, zstd); + STATUS(HAVE_LIBPFM, libpfm4); } int cmd_version(int argc, const char **argv) diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 0b4d6431b0729..dded93a2bc89a 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -75,6 +75,15 @@ include/uapi/asm-generic/mman-common.h include/uapi/asm-generic/unistd.h ' +# These copies are under tools/perf/trace/beauty/ as they are not used to in +# building object files only by scripts in tools/perf/trace/beauty/ to generate +# tables that then gets included in .c files for things like id->string syscall +# tables (and the reverse lookup as well: string -> id) + +BEAUTY_FILES=' +include/linux/socket.h +' + check_2 () { file1=$1 file2=$2 @@ -100,6 +109,14 @@ check () { check_2 tools/$file $file $* } +beauty_check () { + file=$1 + + shift + + check_2 tools/perf/trace/beauty/$file $file $* +} + # Check if we have the kernel headers (tools/perf/../../include), else # we're probably on a detached tarball, so no point in trying to check # differences. @@ -127,9 +144,12 @@ check arch/x86/lib/insn.c '-I "^#include [\"<]\(../include/\)*asm/in # diff non-symmetric files check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl +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 -# These will require a beauty_check when we get some more like that -check_2 tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h +for i in $BEAUTY_FILES; do + beauty_check $i -B +done # check duplicated library files check_2 tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c index 65c4ff6892d96..e6b6181c6dc63 100644 --- a/tools/perf/examples/bpf/5sec.c +++ b/tools/perf/examples/bpf/5sec.c @@ -39,7 +39,7 @@ Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com> */ -#include <bpf/bpf.h> +#include <bpf.h> #define NSEC_PER_SEC 1000000000L diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index 15e458e150bd8..7a2264e1e4e1e 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -9,31 +9,13 @@ struct perf_event_attr; -extern bool test_attr__enabled; -void test_attr__ready(void); -void test_attr__init(void); -void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, - int fd, int group_fd, unsigned long flags); - -#ifndef HAVE_ATTR_TEST -#define HAVE_ATTR_TEST 1 -#endif - static inline int sys_perf_event_open(struct perf_event_attr *attr, pid_t pid, int cpu, int group_fd, unsigned long flags) { - int fd; - - fd = syscall(__NR_perf_event_open, attr, pid, cpu, - group_fd, flags); - -#if HAVE_ATTR_TEST - if (unlikely(test_attr__enabled)) - test_attr__open(attr, pid, cpu, fd, group_fd, flags); -#endif - return fd; + return syscall(__NR_perf_event_open, attr, pid, cpu, + group_fd, flags); } #endif /* _PERF_SYS_H */ diff --git a/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/ddrc.json b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/ddrc.json new file mode 100644 index 0000000000000..3b1cd708f568c --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/ddrc.json @@ -0,0 +1,39 @@ +[ + { + "BriefDescription": "ddr cycles event", + "EventCode": "0x00", + "EventName": "imx8mm_ddr.cycles", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "ddr read-cycles event", + "EventCode": "0x2a", + "EventName": "imx8mm_ddr.read_cycles", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "ddr write-cycles event", + "EventCode": "0x2b", + "EventName": "imx8mm_ddr.write_cycles", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "ddr read event", + "EventCode": "0x35", + "EventName": "imx8mm_ddr.read", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "ddr write event", + "EventCode": "0x38", + "EventName": "imx8mm_ddr.write", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + } +] + + diff --git a/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/metrics.json b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/metrics.json new file mode 100644 index 0000000000000..8e553b67cae63 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/metrics.json @@ -0,0 +1,18 @@ +[ + { + "BriefDescription": "bytes all masters read from ddr based on read-cycles event", + "MetricName": "imx8mm_ddr_read.all", + "MetricExpr": "imx8mm_ddr.read_cycles * 4 * 4", + "ScaleUnit": "9.765625e-4KB", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "bytes all masters write to ddr based on write-cycles event", + "MetricName": "imx8mm_ddr_write.all", + "MetricExpr": "imx8mm_ddr.write_cycles * 4 * 4", + "ScaleUnit": "9.765625e-4KB", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power8/cache.json b/tools/perf/pmu-events/arch/powerpc/power8/cache.json index 6b792b2c87e23..05a17084d939e 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/cache.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/cache.json @@ -32,8 +32,8 @@ { "EventCode": "0x1c04e", "EventName": "PM_DATA_FROM_L2MISS_MOD", - "BriefDescription": "The processor's data cache was reloaded from a localtion other than the local core's L2 due to a demand load", - "PublicDescription": "The processor's data cache was reloaded from a localtion other than the local core's L2 due to either only demand loads or demand loads plus prefetches if MMCR1[16] is 1" + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to a demand load", + "PublicDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to either only demand loads or demand loads plus prefetches if MMCR1[16] is 1" }, { "EventCode": "0x3c040", @@ -74,8 +74,8 @@ { "EventCode": "0x4c04e", "EventName": "PM_DATA_FROM_L3MISS_MOD", - "BriefDescription": "The processor's data cache was reloaded from a localtion other than the local core's L3 due to a demand load", - "PublicDescription": "The processor's data cache was reloaded from a localtion other than the local core's L3 due to either only demand loads or demand loads plus prefetches if MMCR1[16] is 1" + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a demand load", + "PublicDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to either only demand loads or demand loads plus prefetches if MMCR1[16] is 1" }, { "EventCode": "0x3c042", @@ -134,7 +134,7 @@ { "EventCode": "0x4e04e", "EventName": "PM_DPTEG_FROM_L3MISS", - "BriefDescription": "A Page Table Entry was loaded into the TLB from a localtion other than the local core's L3 due to a data side request", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a data side request", "PublicDescription": "" }, { diff --git a/tools/perf/pmu-events/arch/powerpc/power8/frontend.json b/tools/perf/pmu-events/arch/powerpc/power8/frontend.json index 1ddc30655d439..1c902a8263b6e 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/frontend.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/frontend.json @@ -116,8 +116,8 @@ { "EventCode": "0x1404e", "EventName": "PM_INST_FROM_L2MISS", - "BriefDescription": "The processor's Instruction cache was reloaded from a localtion other than the local core's L2 due to an instruction fetch (not prefetch)", - "PublicDescription": "The processor's Instruction cache was reloaded from a localtion other than the local core's L2 due to either an instruction fetch or instruction fetch plus prefetch if MMCR1[17] is 1" + "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L2 due to an instruction fetch (not prefetch)", + "PublicDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L2 due to either an instruction fetch or instruction fetch plus prefetch if MMCR1[17] is 1" }, { "EventCode": "0x34040", @@ -158,8 +158,8 @@ { "EventCode": "0x4404e", "EventName": "PM_INST_FROM_L3MISS_MOD", - "BriefDescription": "The processor's Instruction cache was reloaded from a localtion other than the local core's L3 due to a instruction fetch", - "PublicDescription": "The processor's Instruction cache was reloaded from a localtion other than the local core's L3 due to either an instruction fetch or instruction fetch plus prefetch if MMCR1[17] is 1" + "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L3 due to a instruction fetch", + "PublicDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L3 due to either an instruction fetch or instruction fetch plus prefetch if MMCR1[17] is 1" }, { "EventCode": "0x34042", @@ -320,7 +320,7 @@ { "EventCode": "0x1504e", "EventName": "PM_IPTEG_FROM_L2MISS", - "BriefDescription": "A Page Table Entry was loaded into the TLB from a localtion other than the local core's L2 due to a instruction side request", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a instruction side request", "PublicDescription": "" }, { @@ -344,7 +344,7 @@ { "EventCode": "0x4504e", "EventName": "PM_IPTEG_FROM_L3MISS", - "BriefDescription": "A Page Table Entry was loaded into the TLB from a localtion other than the local core's L3 due to a instruction side request", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a instruction side request", "PublicDescription": "" }, { diff --git a/tools/perf/pmu-events/arch/powerpc/power8/marked.json b/tools/perf/pmu-events/arch/powerpc/power8/marked.json index 94dc58b83b7e5..6de61a797bbde 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/marked.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/marked.json @@ -92,7 +92,7 @@ { "EventCode": "0x4c12e", "EventName": "PM_MRK_DATA_FROM_L2MISS_CYC", - "BriefDescription": "Duration in cycles to reload from a localtion other than the local core's L2 due to a marked load", + "BriefDescription": "Duration in cycles to reload from a location other than the local core's L2 due to a marked load", "PublicDescription": "" }, { @@ -158,13 +158,13 @@ { "EventCode": "0x201e4", "EventName": "PM_MRK_DATA_FROM_L3MISS", - "BriefDescription": "The processor's data cache was reloaded from a localtion other than the local core's L3 due to a marked load", + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a marked load", "PublicDescription": "" }, { "EventCode": "0x2d12e", "EventName": "PM_MRK_DATA_FROM_L3MISS_CYC", - "BriefDescription": "Duration in cycles to reload from a localtion other than the local core's L3 due to a marked load", + "BriefDescription": "Duration in cycles to reload from a location other than the local core's L3 due to a marked load", "PublicDescription": "" }, { @@ -392,7 +392,7 @@ { "EventCode": "0x1f14e", "EventName": "PM_MRK_DPTEG_FROM_L2MISS", - "BriefDescription": "A Page Table Entry was loaded into the TLB from a localtion other than the local core's L2 due to a marked data side request", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a marked data side request", "PublicDescription": "" }, { @@ -416,7 +416,7 @@ { "EventCode": "0x4f14e", "EventName": "PM_MRK_DPTEG_FROM_L3MISS", - "BriefDescription": "A Page Table Entry was loaded into the TLB from a localtion other than the local core's L3 due to a marked data side request", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a marked data side request", "PublicDescription": "" }, { diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json index f4e760cab1117..84a0cedf1fd9b 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json @@ -410,8 +410,8 @@ { "EventCode": "0x61c04e", "EventName": "PM_DATA_ALL_FROM_L2MISS_MOD", - "BriefDescription": "The processor's data cache was reloaded from a localtion other than the local core's L2 due to either demand loads or data prefetch", - "PublicDescription": "The processor's data cache was reloaded from a localtion other than the local core's L2 due to either only demand loads or demand loads plus prefetches if MMCR1[16] is 1" + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to either demand loads or data prefetch", + "PublicDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to either only demand loads or demand loads plus prefetches if MMCR1[16] is 1" }, { "EventCode": "0x63c040", @@ -470,8 +470,8 @@ { "EventCode": "0x64c04e", "EventName": "PM_DATA_ALL_FROM_L3MISS_MOD", - "BriefDescription": "The processor's data cache was reloaded from a localtion other than the local core's L3 due to either demand loads or data prefetch", - "PublicDescription": "The processor's data cache was reloaded from a localtion other than the local core's L3 due to either only demand loads or demand loads plus prefetches if MMCR1[16] is 1" + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to either demand loads or data prefetch", + "PublicDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to either only demand loads or demand loads plus prefetches if MMCR1[16] is 1" }, { "EventCode": "0x63c042", @@ -1280,8 +1280,8 @@ { "EventCode": "0x51404e", "EventName": "PM_INST_ALL_FROM_L2MISS", - "BriefDescription": "The processor's Instruction cache was reloaded from a localtion other than the local core's L2 due to instruction fetches and prefetches", - "PublicDescription": "The processor's Instruction cache was reloaded from a localtion other than the local core's L2 due to either an instruction fetch or instruction fetch plus prefetch if MMCR1[17] is 1" + "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L2 due to instruction fetches and prefetches", + "PublicDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L2 due to either an instruction fetch or instruction fetch plus prefetch if MMCR1[17] is 1" }, { "EventCode": "0x534040", @@ -1340,8 +1340,8 @@ { "EventCode": "0x54404e", "EventName": "PM_INST_ALL_FROM_L3MISS_MOD", - "BriefDescription": "The processor's Instruction cache was reloaded from a localtion other than the local core's L3 due to a instruction fetch", - "PublicDescription": "The processor's Instruction cache was reloaded from a localtion other than the local core's L3 due to either an instruction fetch or instruction fetch plus prefetch if MMCR1[17] is 1" + "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L3 due to a instruction fetch", + "PublicDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L3 due to either an instruction fetch or instruction fetch plus prefetch if MMCR1[17] is 1" }, { "EventCode": "0x534042", diff --git a/tools/perf/pmu-events/arch/powerpc/power8/translation.json b/tools/perf/pmu-events/arch/powerpc/power8/translation.json index 623e7475b0104..a1657f5fdc6b5 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/translation.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/translation.json @@ -44,7 +44,7 @@ { "EventCode": "0x1e04e", "EventName": "PM_DPTEG_FROM_L2MISS", - "BriefDescription": "A Page Table Entry was loaded into the TLB from a localtion other than the local core's L2 due to a data side request", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a data side request", "PublicDescription": "" }, { diff --git a/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json index 8383a37647ad0..7a5d1bf543f82 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json @@ -1,37 +1,46 @@ [ { - "MetricExpr": "(hv_24x7@PM_MCS01_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_RD_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT23\\,chip\\=?@)", - "MetricName": "Memory_RD_BW_Chip", - "MetricGroup": "Memory_BW", - "ScaleUnit": "1.6e-2MB" + "MetricExpr": "(hv_24x7@PM_MCS01_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_RD_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT23\\,chip\\=?@)", + "MetricName": "Memory_RD_BW_Chip", + "MetricGroup": "Memory_BW", + "ScaleUnit": "1.6e-2MB", + "AggregationMode": "PerChip" }, { "MetricExpr": "(hv_24x7@PM_MCS01_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_WR_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT23\\,chip\\=?@ )", - "MetricName": "Memory_WR_BW_Chip", - "MetricGroup": "Memory_BW", - "ScaleUnit": "1.6e-2MB" + "MetricName": "Memory_WR_BW_Chip", + "MetricGroup": "Memory_BW", + "ScaleUnit": "1.6e-2MB", + "AggregationMode": "PerChip" }, { "MetricExpr": "(hv_24x7@PM_PB_CYC\\,chip\\=?@ )", - "MetricName": "PowerBUS_Frequency", - "ScaleUnit": "2.5e-7GHz" + "MetricName": "PowerBUS_Frequency", + "ScaleUnit": "2.5e-7GHz", + "AggregationMode": "PerChip" + }, + { + "MetricExpr": "(hv_24x7@CPM_CS_32MHZ_CYC\\,domain\\=3\\,core\\=?@ )", + "MetricName": "CPM_CS_32MHZ_CYC", + "ScaleUnit": "1MHz", + "AggregationMode": "PerCore" }, { "MetricExpr" : "nest_mcs01_imc@PM_MCS01_128B_RD_DISP_PORT01@ + nest_mcs01_imc@PM_MCS01_128B_RD_DISP_PORT23@", "MetricName" : "mcs01-read", - "MetricGroup" : "memory_bw", + "MetricGroup" : "memory-bandwidth", "ScaleUnit": "6.1e-5MB" }, { "MetricExpr" : "nest_mcs23_imc@PM_MCS23_128B_RD_DISP_PORT01@ + nest_mcs23_imc@PM_MCS23_128B_RD_DISP_PORT23@", "MetricName" : "mcs23-read", - "MetricGroup" : "memory_bw", + "MetricGroup" : "memory-bandwidth", "ScaleUnit": "6.1e-5MB" }, { "MetricExpr" : "nest_mcs01_imc@PM_MCS01_128B_WR_DISP_PORT01@ + nest_mcs01_imc@PM_MCS01_128B_WR_DISP_PORT23@", "MetricName" : "mcs01-write", - "MetricGroup" : "memory_bw", + "MetricGroup" : "memory-bandwidth", "ScaleUnit": "6.1e-5MB" }, { @@ -48,7 +57,7 @@ { "MetricExpr" : "(nest_mcs01_imc@PM_MCS01_128B_RD_DISP_PORT01@ + nest_mcs01_imc@PM_MCS01_128B_RD_DISP_PORT23@ + nest_mcs23_imc@PM_MCS23_128B_RD_DISP_PORT01@ + nest_mcs23_imc@PM_MCS23_128B_RD_DISP_PORT23@ + nest_mcs01_imc@PM_MCS01_128B_WR_DISP_PORT01@ + nest_mcs01_imc@PM_MCS01_128B_WR_DISP_PORT23@ + nest_mcs23_imc@PM_MCS23_128B_WR_DISP_PORT01@ + nest_mcs23_imc@PM_MCS23_128B_WR_DISP_PORT23@)", "MetricName" : "Memory-bandwidth-MCS", - "MetricGroup" : "memory_bw", + "MetricGroup" : "memory-bandwidth", "ScaleUnit": "6.1e-5MB" } ] diff --git a/tools/perf/pmu-events/arch/test/arch-std-events.json b/tools/perf/pmu-events/arch/test/arch-std-events.json new file mode 100644 index 0000000000000..43f6f729d6aef --- /dev/null +++ b/tools/perf/pmu-events/arch/test/arch-std-events.json @@ -0,0 +1,8 @@ +[ + { + "PublicDescription": "Attributable Level 3 cache access, read", + "EventCode": "0x40", + "EventName": "L3_CACHE_RD", + "BriefDescription": "L3 cache access, read" + } +] diff --git a/tools/perf/pmu-events/arch/test/test_cpu/cache.json b/tools/perf/pmu-events/arch/test/test_cpu/cache.json new file mode 100644 index 0000000000000..036d0efdb2bb0 --- /dev/null +++ b/tools/perf/pmu-events/arch/test/test_cpu/cache.json @@ -0,0 +1,5 @@ +[ + { + "ArchStdEvent": "L3_CACHE_RD" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/branch.json b/tools/perf/pmu-events/arch/x86/amdzen1/branch.json index a9943eeb8d6b2..4ceb67a0db215 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen1/branch.json +++ b/tools/perf/pmu-events/arch/x86/amdzen1/branch.json @@ -19,5 +19,10 @@ "EventName": "bp_de_redirect", "EventCode": "0x91", "BriefDescription": "Decoder Overrides Existing Branch Prediction (speculative)." + }, + { + "EventName": "bp_l1_tlb_fetch_hit", + "EventCode": "0x94", + "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB." } ] diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/cache.json b/tools/perf/pmu-events/arch/x86/amdzen1/cache.json index 404d4c569c01e..4ea7ec4f496e8 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen1/cache.json +++ b/tools/perf/pmu-events/arch/x86/amdzen1/cache.json @@ -118,6 +118,11 @@ "UMask": "0x1" }, { + "EventName": "l2_request_g1.all_no_prefetch", + "EventCode": "0x60", + "UMask": "0xf9" + }, + { "EventName": "l2_request_g2.group1", "EventCode": "0x61", "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).", @@ -244,12 +249,48 @@ "UMask": "0x1" }, { + "EventName": "l2_cache_req_stat.ic_access_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache requests in L2.", + "UMask": "0x7" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_miss_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2 and Data cache request miss in L2 (all types).", + "UMask": "0x9" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_hit_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request hit in L2 and Data cache request hit in L2 (all types).", + "UMask": "0xf6" + }, + { "EventName": "l2_fill_pending.l2_fill_busy", "EventCode": "0x6d", "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.", "UMask": "0x1" }, { + "EventName": "l2_pf_hit_l2", + "EventCode": "0x70", + "BriefDescription": "L2 prefetch hit in L2.", + "UMask": "0xff" + }, + { + "EventName": "l2_pf_miss_l2_hit_l3", + "EventCode": "0x71", + "BriefDescription": "L2 prefetcher hits in L3. Counts all L2 prefetches accepted by the L2 pipeline which miss the L2 cache and hit the L3.", + "UMask": "0xff" + }, + { + "EventName": "l2_pf_miss_l2_l3", + "EventCode": "0x72", + "BriefDescription": "L2 prefetcher misses in L3. All L2 prefetches accepted by the L2 pipeline which miss the L2 and the L3 caches.", + "UMask": "0xff" + }, + { "EventName": "l3_request_g1.caching_l3_cache_accesses", "EventCode": "0x01", "BriefDescription": "Caching: L3 cache accesses", diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json b/tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json new file mode 100644 index 0000000000000..40271df40015b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json @@ -0,0 +1,98 @@ +[ + { + "EventName": "remote_outbound_data_controller_0", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 0", + "EventCode": "0x7c7", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_1", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 1", + "EventCode": "0x807", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_2", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 2", + "EventCode": "0x847", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_3", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 3", + "EventCode": "0x887", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_0", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x07", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_1", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x47", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_2", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x87", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_3", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0xc7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_4", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x107", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_5", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x147", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_6", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x187", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_7", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x1c7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json new file mode 100644 index 0000000000000..2cfe2d2f3bfdd --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json @@ -0,0 +1,178 @@ +[ + { + "MetricName": "branch_misprediction_ratio", + "BriefDescription": "Execution-Time Branch Misprediction Ratio (Non-Speculative)", + "MetricExpr": "d_ratio(ex_ret_brn_misp, ex_ret_brn)", + "MetricGroup": "branch_prediction", + "ScaleUnit": "100%" + }, + { + "EventName": "all_dc_accesses", + "EventCode": "0x29", + "BriefDescription": "All L1 Data Cache Accesses", + "UMask": "0x7" + }, + { + "MetricName": "all_l2_cache_accesses", + "BriefDescription": "All L2 Cache Accesses", + "MetricExpr": "l2_request_g1.all_no_prefetch + l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_accesses_from_ic_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Instruction Cache Misses (including prefetch)", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_accesses_from_dc_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Data Cache Misses (including prefetch)", + "UMask": "0xc8" + }, + { + "MetricName": "l2_cache_accesses_from_l2_hwpf", + "BriefDescription": "L2 Cache Accesses from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_misses", + "BriefDescription": "All L2 Cache Misses", + "MetricExpr": "l2_cache_req_stat.ic_dc_miss_in_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_misses_from_ic_miss", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Instruction Cache Misses", + "UMask": "0x01" + }, + { + "EventName": "l2_cache_misses_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Data Cache Misses", + "UMask": "0x08" + }, + { + "MetricName": "l2_cache_misses_from_l2_hwpf", + "BriefDescription": "L2 Cache Misses from L2 HWPF", + "MetricExpr": "l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_hits", + "BriefDescription": "All L2 Cache Hits", + "MetricExpr": "l2_cache_req_stat.ic_dc_hit_in_l2 + l2_pf_hit_l2", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_hits_from_ic_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Instruction Cache Misses", + "UMask": "0x06" + }, + { + "EventName": "l2_cache_hits_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Data Cache Misses", + "UMask": "0x70" + }, + { + "MetricName": "l2_cache_hits_from_l2_hwpf", + "BriefDescription": "L2 Cache Hits from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l3_accesses", + "EventCode": "0x04", + "BriefDescription": "L3 Accesses", + "UMask": "0xff", + "Unit": "L3PMC" + }, + { + "EventName": "l3_misses", + "EventCode": "0x04", + "BriefDescription": "L3 Misses (includes Chg2X)", + "UMask": "0x01", + "Unit": "L3PMC" + }, + { + "MetricName": "l3_read_miss_latency", + "BriefDescription": "Average L3 Read Miss Latency (in core clocks)", + "MetricExpr": "(xi_sys_fill_latency * 16) / xi_ccx_sdp_req1.all_l3_miss_req_typs", + "MetricGroup": "l3_cache", + "ScaleUnit": "1core clocks" + }, + { + "MetricName": "ic_fetch_miss_ratio", + "BriefDescription": "L1 Instruction Cache (32B) Fetch Miss Ratio", + "MetricExpr": "d_ratio(l2_cache_req_stat.ic_access_in_l2, bp_l1_tlb_fetch_hit + bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_miss)", + "MetricGroup": "l2_cache", + "ScaleUnit": "100%" + }, + { + "MetricName": "l1_itlb_misses", + "BriefDescription": "L1 ITLB Misses", + "MetricExpr": "bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_miss", + "MetricGroup": "tlb" + }, + { + "EventName": "l2_itlb_misses", + "EventCode": "0x85", + "BriefDescription": "L2 ITLB Misses & Instruction page walks", + "UMask": "0x07" + }, + { + "EventName": "l1_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Misses", + "UMask": "0xff" + }, + { + "EventName": "l2_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L2 DTLB Misses & Data page walks", + "UMask": "0xf0" + }, + { + "EventName": "all_tlbs_flushed", + "EventCode": "0x78", + "BriefDescription": "All TLBs Flushed", + "UMask": "0xdf" + }, + { + "EventName": "uops_dispatched", + "EventCode": "0xaa", + "BriefDescription": "Micro-ops Dispatched", + "UMask": "0x03" + }, + { + "EventName": "sse_avx_stalls", + "EventCode": "0x0e", + "BriefDescription": "Mixed SSE/AVX Stalls", + "UMask": "0x0e" + }, + { + "EventName": "uops_retired", + "EventCode": "0xc1", + "BriefDescription": "Micro-ops Retired" + }, + { + "MetricName": "all_remote_links_outbound", + "BriefDescription": "Approximate: Outbound data bytes for all Remote Links for a node (die)", + "MetricExpr": "remote_outbound_data_controller_0 + remote_outbound_data_controller_1 + remote_outbound_data_controller_2 + remote_outbound_data_controller_3", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "3e-5MiB" + }, + { + "MetricName": "nps1_die_to_dram", + "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die) (may need --metric-no-group)", + "MetricExpr": "dram_channel_data_controller_0 + dram_channel_data_controller_1 + dram_channel_data_controller_2 + dram_channel_data_controller_3 + dram_channel_data_controller_4 + dram_channel_data_controller_5 + dram_channel_data_controller_6 + dram_channel_data_controller_7", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "6.1e-5MiB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/cache.json b/tools/perf/pmu-events/arch/x86/amdzen2/cache.json index 1c60bfa0f00b9..f61b982f83ca3 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen2/cache.json +++ b/tools/perf/pmu-events/arch/x86/amdzen2/cache.json @@ -48,6 +48,11 @@ "UMask": "0x1" }, { + "EventName": "l2_request_g1.all_no_prefetch", + "EventCode": "0x60", + "UMask": "0xf9" + }, + { "EventName": "l2_request_g2.group1", "EventCode": "0x61", "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).", @@ -174,6 +179,24 @@ "UMask": "0x1" }, { + "EventName": "l2_cache_req_stat.ic_access_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache requests in L2.", + "UMask": "0x7" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_miss_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2 and Data cache request miss in L2 (all types).", + "UMask": "0x9" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_hit_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request hit in L2 and Data cache request hit in L2 (all types).", + "UMask": "0xf6" + }, + { "EventName": "l2_fill_pending.l2_fill_busy", "EventCode": "0x6d", "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.", diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json b/tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json new file mode 100644 index 0000000000000..40271df40015b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json @@ -0,0 +1,98 @@ +[ + { + "EventName": "remote_outbound_data_controller_0", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 0", + "EventCode": "0x7c7", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_1", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 1", + "EventCode": "0x807", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_2", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 2", + "EventCode": "0x847", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_3", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 3", + "EventCode": "0x887", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_0", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x07", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_1", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x47", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_2", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x87", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_3", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0xc7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_4", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x107", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_5", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x147", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_6", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x187", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_7", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x1c7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json new file mode 100644 index 0000000000000..2ef91e25e6613 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json @@ -0,0 +1,178 @@ +[ + { + "MetricName": "branch_misprediction_ratio", + "BriefDescription": "Execution-Time Branch Misprediction Ratio (Non-Speculative)", + "MetricExpr": "d_ratio(ex_ret_brn_misp, ex_ret_brn)", + "MetricGroup": "branch_prediction", + "ScaleUnit": "100%" + }, + { + "EventName": "all_dc_accesses", + "EventCode": "0x29", + "BriefDescription": "All L1 Data Cache Accesses", + "UMask": "0x7" + }, + { + "MetricName": "all_l2_cache_accesses", + "BriefDescription": "All L2 Cache Accesses", + "MetricExpr": "l2_request_g1.all_no_prefetch + l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_accesses_from_ic_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Instruction Cache Misses (including prefetch)", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_accesses_from_dc_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Data Cache Misses (including prefetch)", + "UMask": "0xc8" + }, + { + "MetricName": "l2_cache_accesses_from_l2_hwpf", + "BriefDescription": "L2 Cache Accesses from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_misses", + "BriefDescription": "All L2 Cache Misses", + "MetricExpr": "l2_cache_req_stat.ic_dc_miss_in_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_misses_from_ic_miss", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Instruction Cache Misses", + "UMask": "0x01" + }, + { + "EventName": "l2_cache_misses_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Data Cache Misses", + "UMask": "0x08" + }, + { + "MetricName": "l2_cache_misses_from_l2_hwpf", + "BriefDescription": "L2 Cache Misses from L2 HWPF", + "MetricExpr": "l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_hits", + "BriefDescription": "All L2 Cache Hits", + "MetricExpr": "l2_cache_req_stat.ic_dc_hit_in_l2 + l2_pf_hit_l2", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_hits_from_ic_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Instruction Cache Misses", + "UMask": "0x06" + }, + { + "EventName": "l2_cache_hits_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Data Cache Misses", + "UMask": "0x70" + }, + { + "MetricName": "l2_cache_hits_from_l2_hwpf", + "BriefDescription": "L2 Cache Hits from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l3_accesses", + "EventCode": "0x04", + "BriefDescription": "L3 Accesses", + "UMask": "0xff", + "Unit": "L3PMC" + }, + { + "EventName": "l3_misses", + "EventCode": "0x04", + "BriefDescription": "L3 Misses (includes Chg2X)", + "UMask": "0x01", + "Unit": "L3PMC" + }, + { + "MetricName": "l3_read_miss_latency", + "BriefDescription": "Average L3 Read Miss Latency (in core clocks)", + "MetricExpr": "(xi_sys_fill_latency * 16) / xi_ccx_sdp_req1.all_l3_miss_req_typs", + "MetricGroup": "l3_cache", + "ScaleUnit": "1core clocks" + }, + { + "MetricName": "ic_fetch_miss_ratio", + "BriefDescription": "L1 Instruction Cache (32B) Fetch Miss Ratio", + "MetricExpr": "d_ratio(l2_cache_req_stat.ic_access_in_l2, bp_l1_tlb_fetch_hit + bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_tlb_miss)", + "MetricGroup": "l2_cache", + "ScaleUnit": "100%" + }, + { + "MetricName": "l1_itlb_misses", + "BriefDescription": "L1 ITLB Misses", + "MetricExpr": "bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_tlb_miss", + "MetricGroup": "tlb" + }, + { + "EventName": "l2_itlb_misses", + "EventCode": "0x85", + "BriefDescription": "L2 ITLB Misses & Instruction page walks", + "UMask": "0x07" + }, + { + "EventName": "l1_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Misses", + "UMask": "0xff" + }, + { + "EventName": "l2_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L2 DTLB Misses & Data page walks", + "UMask": "0xf0" + }, + { + "EventName": "all_tlbs_flushed", + "EventCode": "0x78", + "BriefDescription": "All TLBs Flushed", + "UMask": "0xdf" + }, + { + "EventName": "uops_dispatched", + "EventCode": "0xaa", + "BriefDescription": "Micro-ops Dispatched", + "UMask": "0x03" + }, + { + "EventName": "sse_avx_stalls", + "EventCode": "0x0e", + "BriefDescription": "Mixed SSE/AVX Stalls", + "UMask": "0x0e" + }, + { + "EventName": "uops_retired", + "EventCode": "0xc1", + "BriefDescription": "Micro-ops Retired" + }, + { + "MetricName": "all_remote_links_outbound", + "BriefDescription": "Approximate: Outbound data bytes for all Remote Links for a node (die)", + "MetricExpr": "remote_outbound_data_controller_0 + remote_outbound_data_controller_1 + remote_outbound_data_controller_2 + remote_outbound_data_controller_3", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "3e-5MiB" + }, + { + "MetricName": "nps1_die_to_dram", + "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die) (may need --metric-no-group)", + "MetricExpr": "dram_channel_data_controller_0 + dram_channel_data_controller_1 + dram_channel_data_controller_2 + dram_channel_data_controller_3 + dram_channel_data_controller_4 + dram_channel_data_controller_5 + dram_channel_data_controller_6 + dram_channel_data_controller_7", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "6.1e-5MiB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json index 3fba310a50122..3c0f5837480fe 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json @@ -8064,6 +8064,20 @@ "UMask": "0x1" }, { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "This event is deprecated. Refer to new event OCR.ALL_PF_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", @@ -9256,20 +9270,6 @@ "UMask": "0x1" }, { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x1000020004", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "This event is deprecated. Refer to new event OCR.ALL_PF_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index d25eebce34c99..00f4fcffa8158 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -4,14 +4,14 @@ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", "MetricGroup": "TopdownL1", "MetricName": "Frontend_Bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound." + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound." }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", "MetricGroup": "TopdownL1_SMT", "MetricName": "Frontend_Bound_SMT", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU." }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", @@ -22,13 +22,14 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", "MetricGroup": "TopdownL1_SMT", "MetricName": "Bad_Speculation_SMT", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU." }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_NMI_WATCHDOG", "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", "MetricGroup": "TopdownL1", "MetricName": "Backend_Bound", @@ -36,7 +37,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )", "MetricGroup": "TopdownL1_SMT", "MetricName": "Backend_Bound_SMT", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU." @@ -50,7 +51,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", "MetricGroup": "TopdownL1_SMT", "MetricName": "Retiring_SMT", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU." @@ -58,7 +59,7 @@ { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopDownL1", + "MetricGroup": "Summary", "MetricName": "IPC" }, { @@ -74,24 +75,6 @@ "MetricName": "IpTB" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;PGO", - "MetricName": "BpTB" - }, - { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", - "MetricGroup": "PGO;IcMiss", - "MetricName": "IFetch_Line_Utilization" - }, - { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fetch_BW", - "MetricName": "DSB_Coverage" - }, - { "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", "MetricGroup": "Pipeline;Summary", @@ -104,86 +87,110 @@ "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", "MetricExpr": "4 * cycles", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", - "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "MetricGroup": "TopDownL1_SMT", "MetricName": "SLOTS_SMT" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurance rate)", + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "Instruction_Type", - "MetricName": "IpL" + "MetricName": "IpLoad" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurance rate)", + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "Instruction_Type", - "MetricName": "IpS" + "MetricName": "IpStore" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Instruction_Type", - "MetricName": "IpB" + "MetricName": "IpBranch" }, { - "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches", "MetricName": "IpCall" }, { + "BriefDescription": "Branch instructions per taken branch. ", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTkBranch" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )", + "MetricGroup": "FLOPS;FP_Arith;Instruction_Type", + "MetricName": "IpFLOP" + }, + { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary", + "MetricGroup": "Summary;TopDownL1", "MetricName": "Instructions" }, { + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "LSD", + "MetricName": "LSD_Coverage" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fetch_BW", + "MetricName": "DSB_Coverage" + }, + { "BriefDescription": "Instructions Per Cycle (per physical core)", "MetricExpr": "INST_RETIRED.ANY / cycles", - "MetricGroup": "SMT", + "MetricGroup": "SMT;TopDownL1", "MetricName": "CoreIPC" }, { "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", - "MetricGroup": "SMT", + "MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "SMT;TopDownL1", "MetricName": "CoreIPC_SMT" }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles", + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / cycles", "MetricGroup": "FLOPS", "MetricName": "FLOPc" }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "MetricGroup": "FLOPS_SMT", "MetricName": "FLOPc_SMT" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Pipeline", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 )", + "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", - "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "BrMispredicts", "MetricName": "Branch_Misprediction_Cost" }, { "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", - "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "BrMispredicts_SMT", "MetricName": "Branch_Misprediction_Cost_SMT" }, @@ -213,14 +220,14 @@ }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_NMI_WATCHDOG", "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", "MetricGroup": "TLB", - "MetricName": "Page_Walks_Utilization", - "MetricConstraint": "NO_NMI_WATCHDOG" + "MetricName": "Page_Walks_Utilization" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )", "MetricGroup": "TLB_SMT", "MetricName": "Page_Walks_Utilization_SMT" }, @@ -245,7 +252,7 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", - "MetricGroup": "Memory_BW", + "MetricGroup": "Memory_BW;Offcore", "MetricName": "L3_Cache_Access_BW" }, { @@ -263,7 +270,7 @@ { "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "Cache_Misses", + "MetricGroup": "Cache_Misses;Offcore", "MetricName": "L2MPKI_All" }, { @@ -298,7 +305,7 @@ }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time", + "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, @@ -310,62 +317,74 @@ }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 )", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Summary", + "MetricGroup": "OS", "MetricName": "Kernel_Utilization" }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", - "MetricGroup": "Memory_BW", + "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time", + "MetricGroup": "Memory_BW;SoC", "MetricName": "DRAM_BW_Use" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1000000000 * ( cha@event\\=0x36\\,umask\\=0x21@ / cha@event\\=0x35\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )", - "MetricGroup": "Memory_Lat", - "MetricName": "DRAM_Read_Latency" + "MetricExpr": "1000000000 * ( cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433@ / cha@event\\=0x35\\,umask\\=0x21\\,config\\=0x40433@ ) / ( cha_0@event\\=0x0@ / duration_time )", + "MetricGroup": "Memory_Lat;SoC", + "MetricName": "MEM_Read_Latency" }, { "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "cha@event\\=0x36\\,umask\\=0x21@ / cha@event\\=0x36\\,umask\\=0x21\\,thresh\\=1@", - "MetricGroup": "Memory_BW", - "MetricName": "DRAM_Parallel_Reads" + "MetricExpr": "cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433@ / cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433\\,thresh\\=1@", + "MetricGroup": "Memory_BW;SoC", + "MetricName": "MEM_Parallel_Reads" }, { "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ )", - "MetricGroup": "Memory_Lat", + "MetricGroup": "Memory_Lat;SoC;Server", "MetricName": "MEM_PMM_Read_Latency" }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time )", - "MetricGroup": "Memory_BW", + "MetricGroup": "Memory_BW;SoC;Server", "MetricName": "PMM_Read_BW" }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time )", - "MetricGroup": "Memory_BW", + "MetricGroup": "Memory_BW;SoC;Server", "MetricName": "PMM_Write_BW" }, { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "( UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3 ) * 4 / 1000000000 / duration_time", + "MetricGroup": "IO_BW;SoC;Server", + "MetricName": "IO_Write_BW" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", + "MetricExpr": "( UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 ) * 4 / 1000000000 / duration_time", + "MetricGroup": "IO_BW;SoC;Server", + "MetricName": "IO_Read_BW" + }, + { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "cha_0@event\\=0x0@", - "MetricGroup": "", + "MetricGroup": "SoC", "MetricName": "Socket_CLKS" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions. )", + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", "MetricExpr": "INST_RETIRED.ANY / ( BR_INST_RETIRED.FAR_BRANCH / 2 )", - "MetricGroup": "", + "MetricGroup": "Branches;OS", "MetricName": "IpFarBranch" }, { diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json b/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json index 3553472ad2665..0716b2e3ff75c 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json @@ -247,6 +247,30 @@ "UMask": "0x10" }, { + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.COUNT", + "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", + "Counter": "0,1,2,3,4,5,6,7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x400106", + "PEBS": "2", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", @@ -360,6 +384,16 @@ "UMask": "0x24" }, { + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xE6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/memory.json b/tools/perf/pmu-events/arch/x86/cascadelakex/memory.json index cc66a51c6a7b9..0c07cb4fbf586 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/memory.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/memory.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "ALL_READS & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_READS.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -13,7 +13,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -26,7 +26,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -81,7 +81,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -177,7 +177,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -218,7 +218,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -245,7 +245,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -286,7 +286,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -313,7 +313,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -350,7 +350,7 @@ "UMask": "0x8" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -405,7 +405,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP OCR.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -432,7 +432,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -473,7 +473,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -513,7 +513,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS.ANY_SNOOP OCR.ALL_PF_RFO.L3_MISS.ANY_SNOOP OCR.ALL_PF_RFO.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -540,7 +540,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS.HIT_OTHER_CORE_FWD OCR.PF_L2_RFO.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -678,7 +678,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -705,7 +705,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -779,7 +779,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -792,7 +792,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -847,7 +847,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -874,7 +874,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -950,7 +950,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -977,7 +977,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1045,7 +1045,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD OCR.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1058,7 +1058,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1071,7 +1071,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1084,7 +1084,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.PF_L2_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1097,7 +1097,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1258,7 +1258,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1285,7 +1285,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1298,7 +1298,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1339,7 +1339,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1380,7 +1380,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD OCR.PF_L2_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1393,7 +1393,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1406,7 +1406,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1419,7 +1419,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & REMOTE_HITM", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM OCR.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1432,7 +1432,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1445,7 +1445,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1513,7 +1513,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS.NO_SNOOP_NEEDED OCR.PF_L1D_AND_SW.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1540,7 +1540,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1619,7 +1619,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1632,7 +1632,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1645,7 +1645,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1672,7 +1672,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS.HITM_OTHER_CORE OCR.PF_L2_DATA_RD.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1699,7 +1699,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_MISS.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1712,7 +1712,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1725,7 +1725,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS.NO_SNOOP_NEEDED OCR.DEMAND_RFO.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1738,7 +1738,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1765,7 +1765,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS & SNOOP_MISS", + "BriefDescription": "OCR.ALL_READS.L3_MISS.SNOOP_MISS OCR.ALL_READS.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1806,7 +1806,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1833,7 +1833,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1874,7 +1874,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1887,7 +1887,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1942,7 +1942,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1969,7 +1969,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1982,7 +1982,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1995,7 +1995,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2008,7 +2008,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2021,7 +2021,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2048,7 +2048,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS & REMOTE_HITM", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2089,7 +2089,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.L3_MISS_LOCAL_DRAM.ANY_SNOOP OCR.ALL_READS.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2144,7 +2144,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2185,7 +2185,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_READS.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE OCR.ALL_READS.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2212,7 +2212,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2225,7 +2225,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2241,7 +2241,8 @@ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xCD", + "Data_LA": "1", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", @@ -2290,7 +2291,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2345,7 +2346,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2386,7 +2387,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2399,7 +2400,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2426,7 +2427,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2439,7 +2440,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS.HIT_OTHER_CORE_FWD OCR.DEMAND_RFO.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2452,7 +2453,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS.ANY_SNOOP OCR.ALL_DATA_RD.L3_MISS.ANY_SNOOP OCR.ALL_DATA_RD.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2493,7 +2494,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2520,7 +2521,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2547,7 +2548,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2560,7 +2561,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2586,7 +2587,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2599,7 +2600,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS OCR.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2612,7 +2613,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2653,7 +2654,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2694,7 +2695,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2707,7 +2708,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP OCR.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2730,7 +2731,7 @@ "UMask": "0x40" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2743,7 +2744,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2756,7 +2757,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2769,7 +2770,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2782,7 +2783,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2809,7 +2810,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2822,7 +2823,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_READS.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2835,7 +2836,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2848,7 +2849,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2875,7 +2876,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "OCR.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD OCR.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2902,7 +2903,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_READS.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2915,7 +2916,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2928,7 +2929,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS.NO_SNOOP_NEEDED OCR.PF_L2_DATA_RD.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2941,7 +2942,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2954,7 +2955,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2981,7 +2982,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3050,7 +3051,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3104,7 +3105,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS.HITM_OTHER_CORE OCR.PF_L3_RFO.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3117,7 +3118,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3195,7 +3196,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3222,7 +3223,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3235,7 +3236,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3290,7 +3291,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3373,7 +3374,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3413,7 +3414,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3426,7 +3427,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3481,7 +3482,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.DEMAND_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3522,7 +3523,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3535,7 +3536,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3548,7 +3549,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3561,7 +3562,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3588,7 +3589,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3601,7 +3602,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3614,7 +3615,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3778,7 +3779,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3791,7 +3792,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3804,7 +3805,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3859,7 +3860,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3886,7 +3887,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3899,7 +3900,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3925,7 +3926,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS.NO_SNOOP_NEEDED OCR.PF_L2_RFO.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3938,7 +3939,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3979,7 +3980,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS.NO_SNOOP_NEEDED OCR.PF_L3_RFO.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4044,7 +4045,7 @@ "UMask": "0x20" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS.SNOOP_MISS OCR.ALL_PF_RFO.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4071,7 +4072,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS.HITM_OTHER_CORE OCR.PF_L3_DATA_RD.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4111,7 +4112,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4138,7 +4139,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4151,7 +4152,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP OCR.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4164,7 +4165,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.L3_MISS.ANY_SNOOP OCR.ALL_READS.L3_MISS.ANY_SNOOP OCR.ALL_READS.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4205,7 +4206,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4243,7 +4244,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4284,7 +4285,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4297,7 +4298,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4310,7 +4311,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4323,7 +4324,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4336,7 +4337,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4363,7 +4364,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP OCR.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4390,7 +4391,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4503,7 +4504,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4529,7 +4530,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4556,7 +4557,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4569,7 +4570,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD OCR.DEMAND_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4582,7 +4583,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4623,7 +4624,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS.HITM_OTHER_CORE OCR.PF_L2_RFO.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4636,7 +4637,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4649,7 +4650,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_READS.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_READS.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_READS.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4662,7 +4663,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4685,7 +4686,7 @@ "UMask": "0x80" }, { - "BriefDescription": "ALL_READS & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4698,7 +4699,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS.SNOOP_NONE OCR.ALL_PF_RFO.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4711,7 +4712,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.DEMAND_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4724,7 +4725,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_MISS", + "BriefDescription": "OCR.ALL_RFO.L3_MISS.SNOOP_MISS OCR.ALL_RFO.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4765,7 +4766,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4802,7 +4803,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4828,7 +4829,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS.HITM_OTHER_CORE OCR.DEMAND_DATA_RD.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4841,7 +4842,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS & REMOTE_HITM", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4909,7 +4910,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4950,7 +4951,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4977,7 +4978,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "OCR.ALL_READS.L3_MISS.REMOTE_HIT_FORWARD OCR.ALL_READS.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4990,21 +4991,7 @@ "UMask": "0x1" }, { - "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "Deprecated": "1", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0110000001", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "ALL_RFO & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_RFO.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5017,7 +5004,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS.HIT_OTHER_CORE_FWD OCR.PF_L3_RFO.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5030,7 +5017,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5043,7 +5030,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5070,7 +5057,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS & REMOTE_HITM", + "BriefDescription": "OCR.ALL_READS.L3_MISS.REMOTE_HITM OCR.ALL_READS.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5097,7 +5084,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS.ANY_SNOOP OCR.PF_L3_RFO.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5152,7 +5139,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5188,7 +5175,7 @@ "UMask": "0x10" }, { - "BriefDescription": "ALL_RFO & L3_MISS & REMOTE_HITM", + "BriefDescription": "OCR.ALL_RFO.L3_MISS.REMOTE_HITM OCR.ALL_RFO.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5201,7 +5188,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5214,7 +5201,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS & REMOTE_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5227,7 +5214,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5240,7 +5227,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5253,7 +5240,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5266,7 +5253,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5335,7 +5322,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5390,7 +5377,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5403,7 +5390,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5419,7 +5406,8 @@ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xCD", + "Data_LA": "1", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", @@ -5444,7 +5432,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5457,7 +5445,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5470,7 +5458,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5510,7 +5498,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5523,7 +5511,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5536,7 +5524,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5549,7 +5537,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5585,7 +5573,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.L3_MISS.SNOOP_NONE OCR.ALL_RFO.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5598,7 +5586,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5667,7 +5655,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5708,7 +5696,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.OTHER.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5747,7 +5735,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5760,7 +5748,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.L3_MISS.SNOOP_NONE OCR.ALL_READS.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5829,7 +5817,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5870,7 +5858,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5925,7 +5913,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5938,7 +5926,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5951,7 +5939,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5964,7 +5952,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5977,7 +5965,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_MISS", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS.SNOOP_MISS OCR.ALL_DATA_RD.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6004,7 +5992,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6017,7 +6005,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6030,7 +6018,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6099,7 +6087,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6181,7 +6169,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_MISS.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6222,7 +6210,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6235,7 +6223,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS.ANY_SNOOP OCR.PF_L2_RFO.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6262,7 +6250,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6359,7 +6347,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6400,7 +6388,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6413,7 +6401,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6426,7 +6414,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6439,7 +6427,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6452,7 +6440,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS.HITM_OTHER_CORE OCR.OTHER.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6496,7 +6484,8 @@ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xCD", + "Data_LA": "1", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", @@ -6592,7 +6581,8 @@ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xCD", + "Data_LA": "1", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", @@ -6640,7 +6630,7 @@ "UMask": "0x20" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6694,7 +6684,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6707,7 +6697,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6763,7 +6753,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6776,7 +6766,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6789,7 +6779,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6816,7 +6806,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6843,7 +6833,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6873,7 +6863,8 @@ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xCD", + "Data_LA": "1", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", @@ -6893,7 +6884,7 @@ "UMask": "0x20" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6962,7 +6953,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6975,7 +6966,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7016,7 +7007,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS.NO_SNOOP_NEEDED OCR.DEMAND_CODE_RD.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7029,7 +7020,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS.HITM_OTHER_CORE OCR.PF_L1D_AND_SW.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7070,7 +7061,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS & REMOTE_HITM", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7083,7 +7074,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS.NO_SNOOP_NEEDED OCR.DEMAND_DATA_RD.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7096,7 +7087,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7123,7 +7114,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7136,7 +7127,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.L3_MISS.ANY_SNOOP OCR.ALL_RFO.L3_MISS.ANY_SNOOP OCR.ALL_RFO.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7149,7 +7140,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7204,7 +7195,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS.HIT_OTHER_CORE_FWD OCR.DEMAND_CODE_RD.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7217,7 +7208,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS & REMOTE_HITM", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7243,7 +7234,8 @@ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xCD", + "Data_LA": "1", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", @@ -7254,7 +7246,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_RFO.L3_MISS.HITM_OTHER_CORE OCR.ALL_RFO.L3_MISS.HITM_OTHER_CORE OCR.ALL_RFO.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7295,7 +7287,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS.SNOOP_NONE OCR.ALL_PF_DATA_RD.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7336,7 +7328,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS.NO_SNOOP_NEEDED OCR.OTHER.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7405,7 +7397,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7418,7 +7410,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS.ANY_SNOOP OCR.OTHER.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7431,7 +7423,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7444,7 +7436,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7457,7 +7449,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7470,7 +7462,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD OCR.PF_L3_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7483,7 +7475,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7524,7 +7516,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD OCR.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7551,7 +7543,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7564,7 +7556,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7577,7 +7569,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.PF_L3_RFO.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7604,7 +7596,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7617,7 +7609,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS.HITM_OTHER_CORE OCR.DEMAND_RFO.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7658,7 +7650,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7681,7 +7673,7 @@ "UMask": "0x2" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS & REMOTE_HITM", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7708,7 +7700,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7735,7 +7727,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.PF_L3_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7762,7 +7754,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7789,7 +7781,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7802,7 +7794,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS.SNOOP_NONE OCR.ALL_DATA_RD.L3_MISS.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7815,7 +7807,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_MISS.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7828,7 +7820,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP OCR.ALL_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7841,7 +7833,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7854,7 +7846,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7895,7 +7887,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_MISS.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7922,7 +7914,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7949,7 +7941,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7976,19 +7968,6 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0810000001", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "This event is deprecated. Refer to new event OCR.PF_L2_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", @@ -8003,7 +7982,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8026,7 +8005,7 @@ "UMask": "0x2" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_LOCAL_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8039,7 +8018,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8070,7 +8049,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS.ANY_SNOOP OCR.DEMAND_RFO.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8083,7 +8062,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8236,7 +8215,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_READS.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED OCR.ALL_READS.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8249,7 +8228,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.DEMAND_CODE_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8262,7 +8241,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_REMOTE_DRAM & SNOOP_MISS_OR_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8289,7 +8268,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8344,7 +8323,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS & REMOTE_HITM", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS.REMOTE_HITM OCR.ALL_DATA_RD.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8357,7 +8336,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8426,7 +8405,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS & REMOTE_HITM", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8439,7 +8418,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8452,7 +8431,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8520,7 +8499,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS & REMOTE_HITM", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8630,7 +8609,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS.NO_SNOOP_NEEDED OCR.PF_L3_DATA_RD.L3_MISS.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8713,7 +8692,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8726,7 +8705,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8766,7 +8745,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS & REMOTE_HIT_FORWARD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD OCR.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8803,7 +8782,7 @@ "UMask": "0x10" }, { - "BriefDescription": "ALL_READS & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED OCR.ALL_READS.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8816,7 +8795,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8857,7 +8836,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8968,7 +8947,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.PF_L1D_AND_SW.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8981,7 +8960,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS.HITM_OTHER_CORE OCR.DEMAND_CODE_RD.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8994,7 +8973,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9021,7 +9000,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9047,7 +9026,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9060,7 +9039,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_READS.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9073,7 +9052,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_LOCAL_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_LOCAL_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9169,6 +9148,19 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0810000001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", @@ -9261,7 +9253,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9316,7 +9308,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9329,7 +9321,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP OCR.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9356,7 +9348,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP OCR.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9383,7 +9375,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9424,7 +9416,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9465,7 +9457,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & NO_SNOOP_NEEDED", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9506,7 +9498,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_MISS & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD OCR.PF_L2_DATA_RD.L3_MISS.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9533,7 +9525,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_LOCAL_DRAM & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9546,7 +9538,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS_REMOTE_HOP1_DRAM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS_REMOTE_HOP1_DRAM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9601,7 +9593,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9614,7 +9606,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS.HIT_OTHER_CORE_FWD OCR.PF_L1D_AND_SW.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9641,7 +9633,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_MISS & REMOTE_HITM", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9678,7 +9670,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9705,7 +9697,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_MISS_REMOTE_HOP1_DRAM & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9718,7 +9710,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9745,7 +9737,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_READS.L3_MISS.HITM_OTHER_CORE OCR.ALL_READS.L3_MISS.HITM_OTHER_CORE OCR.ALL_READS.L3_MISS.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9772,7 +9764,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_MISS_REMOTE_HOP1_DRAM & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_MISS_REMOTE_HOP1_DRAM.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9785,7 +9777,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_MISS.HIT_OTHER_CORE_FWD OCR.OTHER.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9812,7 +9804,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_MISS & REMOTE_HITM", + "BriefDescription": "OCR.ALL_PF_RFO.L3_MISS.REMOTE_HITM OCR.ALL_PF_RFO.L3_MISS.REMOTE_HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9839,7 +9831,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS_LOCAL_DRAM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9855,7 +9847,8 @@ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xCD", + "Data_LA": "1", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", @@ -9883,7 +9876,8 @@ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xCD", + "Data_LA": "1", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", @@ -9894,7 +9888,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_MISS & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_READS.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_MISS.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_MISS.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -9905,5 +9899,19 @@ "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Deprecated": "1", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_HOP1_DRAM.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0110000001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json index 05d13d53c3744..f77d78e90954b 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -13,7 +13,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_S.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -26,7 +26,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_READS.L3_HIT_F.NO_SNOOP_NEEDED OCR.ALL_READS.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -39,7 +39,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -52,7 +52,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "OCR.ALL_RFO.SUPPLIER_NONE.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -65,7 +65,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT_M.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -78,7 +78,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -104,7 +104,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -117,7 +117,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_S.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -130,7 +130,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "Counts any other requests OCR.OTHER.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -143,7 +143,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -156,7 +156,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -169,7 +169,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_S.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -182,7 +182,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -195,7 +195,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT.ANY_SNOOP OCR.ALL_PF_RFO.L3_HIT.ANY_SNOOP OCR.ALL_PF_RFO.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -208,7 +208,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_S.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -221,7 +221,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_S.ANY_SNOOP OCR.ALL_PF_RFO.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -234,7 +234,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -247,7 +247,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT & SNOOP_MISS", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -260,7 +260,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -273,7 +273,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -299,7 +299,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -312,7 +312,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -325,7 +325,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_READS.L3_HIT_M.NO_SNOOP_NEEDED OCR.ALL_READS.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -338,7 +338,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -351,7 +351,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_FWD OCR.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -364,7 +364,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_E.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -377,7 +377,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -390,7 +390,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED OCR.ALL_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -403,7 +403,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_F.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -416,7 +416,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -429,7 +429,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -442,7 +442,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.PMM_HIT_LOCAL_PMM.ANY_SNOOP OCR.ALL_READS.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -478,7 +478,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE OCR.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -491,7 +491,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_E.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -517,7 +517,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -530,7 +530,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -543,7 +543,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.OTHER.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -556,7 +556,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP OCR.ALL_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -582,7 +582,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -595,7 +595,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_F & SNOOP_MISS", + "BriefDescription": "OCR.ALL_READS.L3_HIT_F.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -621,7 +621,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -634,7 +634,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -660,7 +660,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_E.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -673,7 +673,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_S.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -699,7 +699,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -712,7 +712,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT & SNOOP_MISS", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -738,7 +738,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -751,7 +751,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_MISS", + "BriefDescription": "OCR.ALL_RFO.L3_HIT.SNOOP_MISS OCR.ALL_RFO.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -764,7 +764,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -777,7 +777,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -790,7 +790,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_F.HITM_OTHER_CORE OCR.ALL_RFO.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -803,7 +803,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -816,7 +816,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "OCR.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -829,7 +829,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -842,7 +842,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -855,7 +855,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -868,7 +868,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_M & SNOOP_MISS", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_M.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -881,7 +881,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT.HITM_OTHER_CORE OCR.ALL_RFO.L3_HIT.HITM_OTHER_CORE OCR.ALL_RFO.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -894,7 +894,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -946,7 +946,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -985,7 +985,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -998,7 +998,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1011,7 +1011,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT_E.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1024,7 +1024,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_F.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1050,7 +1050,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1063,7 +1063,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1076,7 +1076,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1089,7 +1089,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE OCR.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1102,7 +1102,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1115,7 +1115,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1128,7 +1128,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1141,7 +1141,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_E.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1167,7 +1167,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1180,7 +1180,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.ANY_SNOOP OCR.DEMAND_RFO.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1193,7 +1193,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1206,7 +1206,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1219,7 +1219,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1232,7 +1232,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1245,7 +1245,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1258,7 +1258,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1297,7 +1297,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1310,7 +1310,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & ANY_RESPONSE have any response type.", + "BriefDescription": "OCR.ALL_PF_DATA_RD.ANY_RESPONSE have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1323,7 +1323,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1336,7 +1336,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT.SNOOP_MISS OCR.ALL_PF_RFO.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1349,7 +1349,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1362,7 +1362,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1388,7 +1388,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_S & SNOOP_MISS", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_S.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1401,7 +1401,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_M.ANY_SNOOP OCR.ALL_RFO.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1414,7 +1414,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1427,7 +1427,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1440,7 +1440,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.L3_HIT_E.ANY_SNOOP OCR.ALL_READS.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1453,7 +1453,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1466,7 +1466,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1479,7 +1479,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_F.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1492,7 +1492,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_READS.SUPPLIER_NONE.HIT_OTHER_CORE_FWD OCR.ALL_READS.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1505,7 +1505,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_READS.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1518,7 +1518,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_E & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_E.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1531,7 +1531,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1544,7 +1544,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_E.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1557,7 +1557,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_E.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1570,7 +1570,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_F.ANY_SNOOP OCR.ALL_DATA_RD.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1583,7 +1583,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1596,7 +1596,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1609,7 +1609,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1622,7 +1622,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1635,7 +1635,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_M.HITM_OTHER_CORE OCR.ALL_RFO.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1661,7 +1661,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & ANY_RESPONSE have any response type.", + "BriefDescription": "OCR.ALL_RFO.ANY_RESPONSE have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1726,7 +1726,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1739,7 +1739,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1752,7 +1752,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT.ANY_SNOOP OCR.PF_L2_RFO.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1765,7 +1765,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1778,7 +1778,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1791,7 +1791,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1804,7 +1804,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1817,7 +1817,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT & SNOOP_MISS", + "BriefDescription": "OCR.ALL_READS.L3_HIT.SNOOP_MISS OCR.ALL_READS.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1830,7 +1830,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1843,7 +1843,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1856,7 +1856,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1908,7 +1908,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1921,7 +1921,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1934,7 +1934,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_F.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1947,7 +1947,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_M.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1960,7 +1960,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.SUPPLIER_NONE.ANY_SNOOP OCR.ALL_READS.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1973,7 +1973,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1986,7 +1986,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -1999,7 +1999,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_S.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2012,7 +2012,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2025,7 +2025,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_M.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2038,7 +2038,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.SUPPLIER_NONE.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2051,7 +2051,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2077,7 +2077,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE OCR.ALL_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2090,7 +2090,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2103,7 +2103,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_E & SNOOP_MISS", + "BriefDescription": "OCR.ALL_READS.L3_HIT_E.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2116,7 +2116,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2129,7 +2129,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_M & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_M.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2142,7 +2142,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP OCR.ALL_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2155,7 +2155,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_M.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2168,7 +2168,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2194,7 +2194,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2207,7 +2207,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2220,7 +2220,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2233,7 +2233,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2246,7 +2246,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2259,7 +2259,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2272,7 +2272,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2285,7 +2285,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2337,7 +2337,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_F & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_F.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2350,7 +2350,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_M.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2363,7 +2363,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2376,7 +2376,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_FWD OCR.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2389,7 +2389,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2402,7 +2402,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2428,7 +2428,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_F.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2441,7 +2441,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_E.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2454,7 +2454,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2490,7 +2490,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE OCR.ALL_PF_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2503,7 +2503,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2516,7 +2516,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2529,7 +2529,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.SUPPLIER_NONE.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2542,7 +2542,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2555,7 +2555,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2568,7 +2568,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_S.ANY_SNOOP OCR.ALL_DATA_RD.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2581,7 +2581,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT_F.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2594,7 +2594,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_F & SNOOP_MISS", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_F.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2607,7 +2607,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2620,7 +2620,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & ANY_RESPONSE have any response type.", + "BriefDescription": "OCR.ALL_PF_RFO.ANY_RESPONSE have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2633,7 +2633,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2646,7 +2646,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2659,7 +2659,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2672,7 +2672,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2685,7 +2685,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_M & SNOOP_MISS", + "BriefDescription": "OCR.ALL_READS.L3_HIT_M.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2698,7 +2698,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2711,7 +2711,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2724,7 +2724,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT & SNOOP_MISS", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2747,7 +2747,7 @@ "UMask": "0x40" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2773,7 +2773,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2799,7 +2799,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2812,7 +2812,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_M & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_M.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2825,7 +2825,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2838,7 +2838,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2851,7 +2851,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED OCR.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2877,7 +2877,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2890,7 +2890,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD OCR.ALL_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2916,7 +2916,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2929,7 +2929,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2942,7 +2942,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2955,7 +2955,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2968,7 +2968,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -2994,7 +2994,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3020,7 +3020,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT & SNOOP_MISS", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3046,7 +3046,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3059,7 +3059,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3072,7 +3072,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3085,7 +3085,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3098,7 +3098,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_M.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3111,7 +3111,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_E & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_E.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3124,7 +3124,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3137,7 +3137,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & ANY_RESPONSE have any response type.", + "BriefDescription": "OCR.ALL_DATA_RD.ANY_RESPONSE have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3150,7 +3150,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3163,7 +3163,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_S & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_S.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3189,7 +3189,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3202,7 +3202,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE OCR.ALL_PF_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3215,7 +3215,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3241,7 +3241,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_F & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_F.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3254,7 +3254,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3267,7 +3267,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_E.ANY_SNOOP OCR.ALL_PF_RFO.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3280,7 +3280,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.HIT_OTHER_CORE_FWD OCR.OTHER.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3306,7 +3306,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3319,7 +3319,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3332,7 +3332,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_E.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3345,7 +3345,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3358,7 +3358,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3371,7 +3371,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3384,7 +3384,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3397,7 +3397,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3423,7 +3423,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3436,7 +3436,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3449,7 +3449,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3462,7 +3462,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE OCR.ALL_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3475,7 +3475,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3488,7 +3488,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3501,7 +3501,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3514,7 +3514,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3527,7 +3527,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3540,7 +3540,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3553,7 +3553,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3566,7 +3566,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3579,7 +3579,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3592,7 +3592,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3605,7 +3605,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3618,7 +3618,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_E.ANY_SNOOP OCR.ALL_DATA_RD.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3631,7 +3631,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3644,7 +3644,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_READS.L3_HIT_F.HITM_OTHER_CORE OCR.ALL_READS.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3657,7 +3657,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3670,7 +3670,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3696,7 +3696,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_FWD OCR.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3709,7 +3709,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3735,7 +3735,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3748,7 +3748,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_M.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3771,7 +3771,7 @@ "UMask": "0x2" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3797,7 +3797,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3810,7 +3810,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3823,7 +3823,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_M.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3836,7 +3836,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3849,7 +3849,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_F & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_F.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3875,7 +3875,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_F.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3888,7 +3888,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3914,7 +3914,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3927,7 +3927,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT & SNOOP_MISS", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3940,7 +3940,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3953,7 +3953,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3966,7 +3966,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_READS.L3_HIT.HITM_OTHER_CORE OCR.ALL_READS.L3_HIT.HITM_OTHER_CORE OCR.ALL_READS.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3979,7 +3979,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -3992,7 +3992,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4005,7 +4005,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4018,7 +4018,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_F.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4031,7 +4031,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "Counts any other requests OCR.OTHER.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4044,7 +4044,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4057,7 +4057,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "Counts any other requests OCR.OTHER.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4070,7 +4070,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT_S.HIT_OTHER_CORE_FWD OCR.ALL_READS.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4092,7 +4092,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4118,7 +4118,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4131,7 +4131,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4144,7 +4144,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4157,7 +4157,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4170,7 +4170,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_F & SNOOP_MISS", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_F.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4196,7 +4196,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4209,7 +4209,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4235,7 +4235,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.ANY_SNOOP OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4248,7 +4248,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4261,7 +4261,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_RFO.SUPPLIER_NONE.HITM_OTHER_CORE OCR.ALL_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4274,7 +4274,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4287,7 +4287,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_F.ANY_SNOOP OCR.ALL_RFO.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4300,7 +4300,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_S.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4313,7 +4313,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_S.ANY_SNOOP OCR.ALL_RFO.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4326,7 +4326,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts any other requests OCR.OTHER.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4339,7 +4339,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4352,7 +4352,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED OCR.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4365,7 +4365,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT_S.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4378,7 +4378,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4391,7 +4391,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_S.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4404,7 +4404,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4417,7 +4417,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_E.HITM_OTHER_CORE OCR.ALL_DATA_RD.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4430,7 +4430,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_READS.L3_HIT_E.NO_SNOOP_NEEDED OCR.ALL_READS.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4443,7 +4443,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4469,7 +4469,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4495,7 +4495,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4521,7 +4521,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_S.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4534,7 +4534,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4560,7 +4560,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD OCR.ALL_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4573,7 +4573,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4586,7 +4586,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.L3_HIT.ANY_SNOOP OCR.ALL_READS.L3_HIT.ANY_SNOOP OCR.ALL_READS.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4599,7 +4599,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.PMM_HIT_LOCAL_PMM.SNOOP_NONE OCR.ALL_READS.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4612,7 +4612,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4625,7 +4625,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4638,7 +4638,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4651,7 +4651,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4677,7 +4677,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT & SNOOP_HIT_WITH_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4690,7 +4690,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4716,7 +4716,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.L3_HIT.SNOOP_NONE OCR.ALL_READS.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4729,7 +4729,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4742,7 +4742,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4755,7 +4755,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4768,7 +4768,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4781,7 +4781,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4794,7 +4794,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_READS.L3_HIT_S.NO_SNOOP_NEEDED OCR.ALL_READS.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4807,7 +4807,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_S.HITM_OTHER_CORE OCR.ALL_RFO.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4820,7 +4820,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4833,7 +4833,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.L3_HIT_M.ANY_SNOOP OCR.ALL_READS.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4846,7 +4846,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_READS.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_READS.L3_HIT.NO_SNOOP_NEEDED OCR.ALL_READS.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4859,7 +4859,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & ANY_RESPONSE have any response type.", + "BriefDescription": "OCR.ALL_READS.ANY_RESPONSE have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4872,7 +4872,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4885,7 +4885,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_M.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4898,7 +4898,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4911,7 +4911,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4924,7 +4924,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT.ANY_SNOOP OCR.ALL_DATA_RD.L3_HIT.ANY_SNOOP OCR.ALL_DATA_RD.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4937,7 +4937,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4950,7 +4950,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4963,7 +4963,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -4976,7 +4976,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5015,7 +5015,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP OCR.ALL_PF_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5041,7 +5041,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT.SNOOP_MISS OCR.ALL_PF_DATA_RD.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5054,7 +5054,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5067,7 +5067,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5080,7 +5080,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_E & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_E.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5093,7 +5093,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5106,7 +5106,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_READS.L3_HIT_S.HITM_OTHER_CORE OCR.ALL_READS.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5119,7 +5119,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.L3_HIT_F.ANY_SNOOP OCR.ALL_READS.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5132,7 +5132,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT_M.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5145,7 +5145,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_S & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.L3_HIT_S.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5158,7 +5158,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT & SNOOP_MISS", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5171,7 +5171,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_E & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_E.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5184,7 +5184,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5197,7 +5197,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5210,7 +5210,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT_E.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5236,7 +5236,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_S & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_S.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5249,7 +5249,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5262,7 +5262,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP OCR.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5275,7 +5275,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT.SNOOP_NONE OCR.ALL_RFO.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5288,7 +5288,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_M & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_M.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5301,7 +5301,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5314,7 +5314,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5327,7 +5327,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_M.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5340,7 +5340,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_E & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.L3_HIT_E.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5353,7 +5353,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5366,7 +5366,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & SUPPLIER_NONE & SNOOP_MISS", + "BriefDescription": "OCR.ALL_READS.SUPPLIER_NONE.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5379,7 +5379,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5401,7 +5401,7 @@ "UMask": "0x2" }, { - "BriefDescription": "ALL_RFO & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_HIT.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5414,7 +5414,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5427,7 +5427,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5440,7 +5440,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_M & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.L3_HIT_M.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5476,7 +5476,7 @@ "UMask": "0x20" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE OCR.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5489,7 +5489,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED OCR.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5502,7 +5502,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5515,7 +5515,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_F.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5528,7 +5528,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5541,7 +5541,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5554,7 +5554,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5567,7 +5567,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5580,7 +5580,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_F & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_F.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5593,7 +5593,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5606,7 +5606,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5619,7 +5619,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5645,7 +5645,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_READS.SUPPLIER_NONE.NO_SNOOP_NEEDED OCR.ALL_READS.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5658,7 +5658,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_F & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_F.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5671,7 +5671,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5684,7 +5684,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_F & SNOOP_NONE", + "BriefDescription": "OCR.ALL_READS.L3_HIT_F.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5697,7 +5697,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP OCR.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5710,7 +5710,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE OCR.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5723,7 +5723,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5736,7 +5736,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5749,7 +5749,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_M.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5762,7 +5762,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5775,7 +5775,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_FWD OCR.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5788,7 +5788,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5801,7 +5801,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5814,7 +5814,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP OCR.ALL_PF_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5827,7 +5827,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5840,7 +5840,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_NONE", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT.SNOOP_NONE OCR.ALL_DATA_RD.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5853,7 +5853,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5866,7 +5866,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_S & SNOOP_MISS", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_S.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5879,7 +5879,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_E.ANY_SNOOP OCR.ALL_PF_DATA_RD.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5905,7 +5905,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5918,7 +5918,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT.ANY_SNOOP OCR.PF_L3_RFO.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5931,7 +5931,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_M & SNOOP_MISS", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_M.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5957,7 +5957,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED OCR.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5970,7 +5970,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5983,7 +5983,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_F.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -5996,7 +5996,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_E & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_E.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6009,7 +6009,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6022,7 +6022,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_M & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_M.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6035,7 +6035,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6048,7 +6048,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6074,7 +6074,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6100,7 +6100,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_F.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6113,7 +6113,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_E.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6139,7 +6139,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6152,7 +6152,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6165,7 +6165,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6191,7 +6191,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6204,7 +6204,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_M.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6217,7 +6217,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6230,7 +6230,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_F.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6243,7 +6243,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6256,7 +6256,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6269,7 +6269,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.ANY_SNOOP OCR.OTHER.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6282,7 +6282,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6295,7 +6295,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_S & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_S.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6308,7 +6308,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE OCR.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6321,7 +6321,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_READS.L3_HIT_E.HITM_OTHER_CORE OCR.ALL_READS.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6347,7 +6347,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & PMM_HIT_LOCAL_PMM & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6360,7 +6360,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6373,7 +6373,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6386,7 +6386,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6412,7 +6412,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP OCR.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6438,7 +6438,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT & SNOOP_MISS", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6451,7 +6451,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6464,7 +6464,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_RFO.SUPPLIER_NONE.HITM_OTHER_CORE OCR.ALL_PF_RFO.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6477,7 +6477,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6490,7 +6490,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6529,7 +6529,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "OCR.ALL_READS.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED OCR.ALL_READS.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6542,7 +6542,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6555,7 +6555,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6568,7 +6568,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED OCR.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6620,7 +6620,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6633,7 +6633,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_READS.L3_HIT_M.HITM_OTHER_CORE OCR.ALL_READS.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6659,7 +6659,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_READS.SUPPLIER_NONE.HITM_OTHER_CORE OCR.ALL_READS.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6672,7 +6672,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_M.ANY_SNOOP OCR.ALL_DATA_RD.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6685,7 +6685,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_E.NO_SNOOP_NEEDED OCR.ALL_RFO.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6698,7 +6698,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6711,7 +6711,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6763,7 +6763,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.NO_SNOOP_NEEDED OCR.OTHER.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6776,7 +6776,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_F.HITM_OTHER_CORE OCR.ALL_PF_RFO.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6789,7 +6789,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6815,7 +6815,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.L3_HIT.ANY_SNOOP OCR.ALL_RFO.L3_HIT.ANY_SNOOP OCR.ALL_RFO.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6828,7 +6828,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6841,7 +6841,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6867,7 +6867,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6880,7 +6880,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "OCR.ALL_DATA_RD.SUPPLIER_NONE.ANY_SNOOP OCR.ALL_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6893,7 +6893,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_M & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_M.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6906,7 +6906,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6919,7 +6919,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED OCR.ALL_PF_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6958,7 +6958,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.SUPPLIER_NONE.ANY_SNOOP OCR.ALL_RFO.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6971,7 +6971,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6984,7 +6984,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -6997,7 +6997,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_M.HITM_OTHER_CORE OCR.ALL_PF_DATA_RD.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7019,7 +7019,7 @@ "UMask": "0x8" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_S & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_S.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7032,7 +7032,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7045,7 +7045,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7058,7 +7058,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_M.ANY_SNOOP OCR.ALL_PF_RFO.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7071,7 +7071,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_M & SNOOP_MISS", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_M.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7084,7 +7084,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7097,7 +7097,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7110,7 +7110,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP OCR.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7123,7 +7123,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7136,7 +7136,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_E & SNOOP_MISS", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_E.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7149,7 +7149,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7162,7 +7162,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD OCR.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7175,7 +7175,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7188,7 +7188,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED OCR.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7201,7 +7201,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7214,7 +7214,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7227,7 +7227,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED OCR.ALL_PF_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7240,7 +7240,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_S.HIT_OTHER_CORE_FWD OCR.ALL_RFO.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7253,7 +7253,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7276,7 +7276,7 @@ "UMask": "0x18" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7289,7 +7289,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7315,7 +7315,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7328,7 +7328,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NONE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7341,7 +7341,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7354,7 +7354,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7367,7 +7367,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_S & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_S.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7380,7 +7380,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7393,7 +7393,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_E & ANY_SNOOP", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_E.ANY_SNOOP OCR.ALL_RFO.L3_HIT_E.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7406,7 +7406,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_S & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_S.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_RFO.L3_HIT_S.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7419,7 +7419,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED OCR.ALL_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7432,7 +7432,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_E & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_E.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7445,7 +7445,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7458,7 +7458,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT.SNOOP_NONE OCR.ALL_PF_RFO.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7520,7 +7520,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7533,7 +7533,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7546,7 +7546,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7572,7 +7572,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT & SNOOP_NONE", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7585,7 +7585,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_NO_FWD OCR.ALL_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7598,7 +7598,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD OCR.ALL_PF_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7611,7 +7611,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_S.NO_SNOOP_NEEDED OCR.ALL_PF_DATA_RD.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7637,7 +7637,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7650,7 +7650,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7676,7 +7676,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & SUPPLIER_NONE & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7689,7 +7689,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7702,7 +7702,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7728,7 +7728,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_E & SNOOP_MISS", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_E.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7741,7 +7741,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_NO_FWD OCR.ALL_PF_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7754,7 +7754,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7767,7 +7767,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7780,7 +7780,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_MISS", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT.SNOOP_MISS OCR.ALL_DATA_RD.L3_HIT.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7793,7 +7793,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7806,7 +7806,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT & ANY_SNOOP", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP OCR.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7832,7 +7832,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT.SNOOP_NONE OCR.ALL_PF_DATA_RD.L3_HIT.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7845,7 +7845,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.SUPPLIER_NONE.ANY_SNOOP OCR.ALL_PF_RFO.SUPPLIER_NONE.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7858,7 +7858,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED OCR.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7884,7 +7884,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7897,7 +7897,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7910,7 +7910,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_S & HITM_OTHER_CORE", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_S.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7949,7 +7949,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7962,7 +7962,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -7975,7 +7975,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_M & HITM_OTHER_CORE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_M.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8001,7 +8001,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8014,7 +8014,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "OCR.ALL_READS.L3_HIT_F.HIT_OTHER_CORE_NO_FWD OCR.ALL_READS.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8027,7 +8027,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_E & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_E.HITM_OTHER_CORE OCR.ALL_RFO.L3_HIT_E.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8053,7 +8053,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) DEMAND_RFO & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8092,7 +8092,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & NO_SNOOP_NEEDED", + "BriefDescription": "OCR.ALL_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED OCR.ALL_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8105,7 +8105,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8118,7 +8118,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_F & ANY_SNOOP", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_F.ANY_SNOOP OCR.ALL_PF_RFO.L3_HIT_F.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8131,7 +8131,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED OCR.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8144,7 +8144,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_M & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_M.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8157,7 +8157,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8170,7 +8170,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8183,7 +8183,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT & HITM_OTHER_CORE", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.HITM_OTHER_CORE OCR.OTHER.L3_HIT.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8196,7 +8196,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8222,7 +8222,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_E & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_E.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8235,7 +8235,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_F & HITM_OTHER_CORE", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_F.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8257,7 +8257,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8270,7 +8270,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads DEMAND_CODE_RD & L3_HIT_M & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT_M.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8283,7 +8283,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & L3_HIT_S & SNOOP_NONE", + "BriefDescription": "OCR.ALL_PF_RFO.L3_HIT_S.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8309,7 +8309,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8322,7 +8322,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_FWD OCR.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8348,7 +8348,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_E & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_E.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8361,7 +8361,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8374,7 +8374,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs PF_L2_RFO & L3_HIT_S & NO_SNOOP_NEEDED", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs OCR.PF_L2_RFO.L3_HIT_S.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8387,7 +8387,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & L3_HIT_F & SNOOP_NONE", + "BriefDescription": "OCR.ALL_RFO.L3_HIT_F.SNOOP_NONE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8400,7 +8400,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD OCR.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8413,7 +8413,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads DEMAND_DATA_RD & L3_HIT_M & NO_SNOOP_NEEDED", + "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT_M.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8426,7 +8426,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_S & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_S.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8439,7 +8439,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & HITM_OTHER_CORE", + "BriefDescription": "OCR.ALL_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE OCR.ALL_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8452,7 +8452,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_PF_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_FWD OCR.ALL_PF_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8465,7 +8465,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requests OTHER & L3_HIT_F & NO_SNOOP_NEEDED", + "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT_F.NO_SNOOP_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8478,7 +8478,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_S & ANY_SNOOP", + "BriefDescription": "OCR.ALL_READS.L3_HIT_S.ANY_SNOOP OCR.ALL_READS.L3_HIT_S.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8504,7 +8504,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8517,7 +8517,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD OCR.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8543,7 +8543,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8556,7 +8556,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "OCR.ALL_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED OCR.ALL_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8569,7 +8569,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs PF_L3_RFO & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs OCR.PF_L3_RFO.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8582,7 +8582,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads PF_L3_DATA_RD & L3_HIT_M & ANY_SNOOP", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads OCR.PF_L3_DATA_RD.L3_HIT_M.ANY_SNOOP", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8595,7 +8595,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_PF_RFO & PMM_HIT_LOCAL_PMM & SNOOP_NOT_NEEDED", + "BriefDescription": "OCR.ALL_PF_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED OCR.ALL_PF_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8608,7 +8608,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & HIT_OTHER_CORE_FWD", + "BriefDescription": "OCR.ALL_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD OCR.ALL_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8621,7 +8621,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests PF_L1D_AND_SW & L3_HIT_E & HIT_OTHER_CORE_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests OCR.PF_L1D_AND_SW.L3_HIT_E.HIT_OTHER_CORE_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8634,7 +8634,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads PF_L2_DATA_RD & L3_HIT_F & HIT_OTHER_CORE_NO_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads OCR.PF_L2_DATA_RD.L3_HIT_F.HIT_OTHER_CORE_NO_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", @@ -8647,7 +8647,7 @@ "UMask": "0x1" }, { - "BriefDescription": "ALL_READS & L3_HIT_S & SNOOP_MISS", + "BriefDescription": "OCR.ALL_READS.L3_HIT_S.SNOOP_MISS", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json b/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json index 5ec668f46ac1b..023f31c72a421 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json @@ -827,16 +827,6 @@ "UMask": "0x2" }, { - "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xE6", - "EventName": "BACLEARS.ANY", - "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json index 3fb5cdce842fd..4ba9e6d9f25e5 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json @@ -90,32 +90,32 @@ "Unit": "iMC" }, { - "BriefDescription": "Intel Optane DC persistent memory bandwidth read (MB/sec). Derived from unc_m_pmm_rpq_inserts", + "BriefDescription": "Intel Optane DC persistent memory bandwidth read (MB). Derived from unc_m_pmm_rpq_inserts", "Counter": "0,1,2,3", "EventCode": "0xE3", "EventName": "UNC_M_PMM_BANDWIDTH.READ", "PerPkg": "1", - "ScaleUnit": "6.103515625E-5MB/sec", + "ScaleUnit": "6.103515625E-5MB", "Unit": "iMC" }, { - "BriefDescription": "Intel Optane DC persistent memory bandwidth write (MB/sec). Derived from unc_m_pmm_wpq_inserts", + "BriefDescription": "Intel Optane DC persistent memory bandwidth write (MB). Derived from unc_m_pmm_wpq_inserts", "Counter": "0,1,2,3", "EventCode": "0xE7", "EventName": "UNC_M_PMM_BANDWIDTH.WRITE", "PerPkg": "1", - "ScaleUnit": "6.103515625E-5MB/sec", + "ScaleUnit": "6.103515625E-5MB", "Unit": "iMC" }, { - "BriefDescription": "Intel Optane DC persistent memory bandwidth total (MB/sec). Derived from unc_m_pmm_rpq_inserts", + "BriefDescription": "Intel Optane DC persistent memory bandwidth total (MB). Derived from unc_m_pmm_rpq_inserts", "Counter": "0,1,2,3", "EventCode": "0xE3", "EventName": "UNC_M_PMM_BANDWIDTH.TOTAL", "MetricExpr": "UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS", "MetricName": "UNC_M_PMM_BANDWIDTH.TOTAL", "PerPkg": "1", - "ScaleUnit": "6.103515625E-5MB/sec", + "ScaleUnit": "6.103515625E-5MB", "Unit": "iMC" }, { diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json index df355ba7acc88..0cd083839e753 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json @@ -538,6 +538,27 @@ "Unit": "CHA" }, { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { "BriefDescription": "Clockticks of the IIO Traffic Controller", "Counter": "0,1,2,3", "EventCode": "0x1", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 25b06cf987474..2f2a209e87e12 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -38,3 +38,4 @@ GenuineIntel-6-7E,v1,icelake,core GenuineIntel-6-86,v1,tremontx,core AuthenticAMD-23-([12][0-9A-F]|[0-9A-F]),v2,amdzen1,core AuthenticAMD-23-[[:xdigit:]]+,v1,amdzen2,core +AuthenticAMD-25-[[:xdigit:]]+,v1,amdzen2,core diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json index 720458139049c..27ea2b00ad007 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json @@ -1,2928 +1,2926 @@ [ { - "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x21", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read miss L2, no rejects", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x22", - "EventName": "L2_RQSTS.RFO_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400400002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts L2 cache misses when fetching instructions.", - "EventCode": "0x24", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "L2_RQSTS.CODE_RD_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache misses when fetching instructions", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400108000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Demand requests that miss L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x27", - "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Demand requests that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100040002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x38", - "EventName": "L2_RQSTS.PF_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0080001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "All requests that miss L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", "Counter": "0,1,2,3", - "UMask": "0x3f", - "EventName": "L2_RQSTS.MISS", - "SampleAfterValue": "200003", - "BriefDescription": "All requests that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", - "EventCode": "0x24", + "BriefDescription": "Counts all demand code readshave any response type.", "Counter": "0,1,2,3", - "UMask": "0xc1", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read requests that hit L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010004", + "Offcore": "1", + "PublicDescription": "Counts all demand code readshave any response type.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0xc2", - "EventName": "L2_RQSTS.RFO_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that hit L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100020002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", - "EventCode": "0x24", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", "Counter": "0,1,2,3", - "UMask": "0xc4", - "EventName": "L2_RQSTS.CODE_RD_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache hits when fetching instructions, code reads.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xd8", - "EventName": "L2_RQSTS.PF_HIT", + "EventName": "L2_RQSTS.PF_MISS", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x38" }, { - "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0xe1", - "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read requests", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC01C0004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", - "EventCode": "0x24", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0xe2", - "EventName": "L2_RQSTS.ALL_RFO", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests to L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100040001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the total number of L2 code requests.", - "EventCode": "0x24", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0xe4", - "EventName": "L2_RQSTS.ALL_CODE_RD", - "SampleAfterValue": "200003", - "BriefDescription": "L2 code requests", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040100001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Demand requests to L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Demand requests that miss L2 cache", "Counter": "0,1,2,3", - "UMask": "0xe7", - "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "SampleAfterValue": "200003", - "BriefDescription": "Demand requests to L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xf8", - "EventName": "L2_RQSTS.ALL_PF", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "PublicDescription": "Demand requests that miss L2 cache.", "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x27" }, { - "PublicDescription": "All L2 requests.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0xff", - "EventName": "L2_RQSTS.REFERENCES", - "SampleAfterValue": "200003", - "BriefDescription": "All L2 requests", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400100002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", - "EventCode": "0x2E", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x41", - "Errata": "SKL057", - "EventName": "LONGEST_LAT_CACHE.MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", "SampleAfterValue": "100003", - "BriefDescription": "Core-originated cacheable demand requests missed L3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", - "EventCode": "0x2E", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x4f", - "Errata": "SKL057", - "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040080004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", - "BriefDescription": "Core-originated cacheable demand requests that refer to L3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", - "EventCode": "0x48", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L1D_PEND_MISS.PENDING", - "SampleAfterValue": "2000003", - "BriefDescription": "L1D miss outstandings duration in cycles", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", - "EventCode": "0x48", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with L1D load Misses outstanding.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x48", + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "SampleAfterValue": "50021", + "UMask": "0x4" }, { - "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", - "EventCode": "0x48", + "BriefDescription": "L2 writebacks that access L2 cache", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "L1D_PEND_MISS.FB_FULL", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x40" }, { - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", - "EventCode": "0x51", + "BriefDescription": "L2 cache lines filling L2", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L1D.REPLACEMENT", - "SampleAfterValue": "2000003", - "BriefDescription": "L1D data line replacements", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "UMask": "0x1f" }, { - "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", - "EventCode": "0x60", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", - "EventCode": "0x60", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00401C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", - "CounterMask": "6", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400040004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Demand Data Read requests sent to uncore", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000400001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080080002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080100001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", - "EventCode": "0xB0", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001C0004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", - "BriefDescription": "Demand Data Read requests sent to uncore", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", - "EventCode": "0xB0", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00801C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", - "BriefDescription": "Cacheable and noncachaeble code read requests", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", - "EventCode": "0xB0", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080100004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", - "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", - "EventCode": "0xB0", + "BriefDescription": "Retired load instructions missed L3 cache as data sources", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", - "SampleAfterValue": "100003", - "BriefDescription": "Demand and prefetch data reads", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "SampleAfterValue": "100007", + "UMask": "0x20" }, { - "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", - "EventCode": "0xB0", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040020001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", - "BriefDescription": "Any memory transaction that reached the SQ.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", - "EventCode": "0xB2", + "BriefDescription": "All retired store instructions.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", "SampleAfterValue": "2000003", - "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x82" }, { - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "EventCode": "0xB7, 0xBB", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080020004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", - "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions that miss the STLB.", - "EventCode": "0xD0", + "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", "Counter": "0,1,2,3", - "UMask": "0x11", - "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions that miss the STLB. (Precise Event)", - "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.SILENT", + "SampleAfterValue": "200003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired store instructions that miss the STLB.", - "EventCode": "0xD0", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x12", - "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "SampleAfterValue": "100003", - "BriefDescription": "Retired store instructions that miss the STLB. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "L1_Hit_Indication": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040048000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD0", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x21", - "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load instructions with locked access. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000088000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD0", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions that split across a cacheline boundary. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD0", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x42", - "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "SampleAfterValue": "100003", - "BriefDescription": "Retired store instructions that split across a cacheline boundary. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "L1_Hit_Indication": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x02001C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD0", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x81", - "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "SampleAfterValue": "2000003", - "BriefDescription": "All retired load instructions. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080020001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "All retired store instructions.", - "EventCode": "0xD0", + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "UMask": "0x82", - "EventName": "MEM_INST_RETIRED.ALL_STORES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "2000003", - "BriefDescription": "All retired store instructions. (Precise Event)", - "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "L1_Hit_Indication": "1" + "UMask": "0x8" }, { - "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", - "EventCode": "0xD1", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "SampleAfterValue": "2000003", - "BriefDescription": "Retired load instructions with L1 cache hits as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x02001C0004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", - "EventCode": "0xD1", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions with L2 cache hits as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400040002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions with L3 cache hits as data sources.", - "EventCode": "0xD1", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "SampleAfterValue": "50021", - "BriefDescription": "Retired load instructions with L3 cache hits as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", - "EventCode": "0xD1", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions missed L1 cache as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions missed L2 cache as data sources.", - "EventCode": "0xD1", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "SampleAfterValue": "50021", - "BriefDescription": "Retired load instructions missed L2 cache as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04001C0001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions missed L3 cache as data sources.", - "EventCode": "0xD1", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load instructions missed L3 cache as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100400001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", - "EventCode": "0xD1", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04001C8000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD2", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000080001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", - "EventCode": "0xD2", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200020001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", - "EventCode": "0xD2", + "BriefDescription": "Core-originated cacheable demand requests missed L3", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3", - "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL057", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x41" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", - "EventCode": "0xD2", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_PF", + "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "SampleAfterValue": "200003", + "UMask": "0xf8" + }, + { + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0080004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD4", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100400002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts L2 writebacks that access L2 cache.", - "EventCode": "0xF0", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "L2_TRANS.L2_WB", - "SampleAfterValue": "200003", - "BriefDescription": "L2 writebacks that access L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040040002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", - "EventCode": "0xF1", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1f", - "EventName": "L2_LINES_IN.ALL", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000400002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", - "BriefDescription": "L2 cache lines filling L2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xF2", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L2_LINES_OUT.SILENT", - "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xF2", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "L2_LINES_OUT.NON_SILENT", - "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", - "EventCode": "0xF2", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "L2_LINES_OUT.USELESS_PREF", - "SampleAfterValue": "200003", - "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200080004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xF2", + "BriefDescription": "RFO requests that miss L2 cache", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "L2_LINES_OUT.USELESS_HWPF", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x22" }, { - "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", - "EventCode": "0xF4", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "SQ_MISC.SPLIT_LOCK", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400040001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", - "BriefDescription": "Number of cache line split locks sent to uncore.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0408000", + "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.NON_SILENT", + "SampleAfterValue": "200003", + "UMask": "0x2" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000408000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040028000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400408000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200408000", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100408000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080408000", + "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "SampleAfterValue": "200003", + "UMask": "0x4" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040408000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC01C8000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001C8000", + "BriefDescription": "Counts all demand data writes (RFOs)have any response type.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)have any response type.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001C8000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04001C0002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001C8000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00401C0004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001C8000", + "BriefDescription": "All requests that miss L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "All requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x3f" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801C8000", + "BriefDescription": "L2 code requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00401C8000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0108000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000108000", + "BriefDescription": "RFO requests that hit L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc2" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400108000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200108000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100108000", + "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x2" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080108000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040108000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0088000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000088000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0028000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400088000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200088000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100088000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000080004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080088000", + "BriefDescription": "Retired load instructions missed L1 cache as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040088000", + "BriefDescription": "L2 cache misses when fetching instructions", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0048000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01001C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000048000", + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400048000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200048000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC01C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100048000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400028000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080048000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040048000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0028000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000028000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400028000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200028000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x02001C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100028000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080028000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040028000", + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts any other requests have any response type.", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000018000", + "BriefDescription": "Demand requests to L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests have any response type.", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PublicDescription": "Demand requests to L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xe7" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400400004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC01C0004", + "AnyThread": "1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001C0004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC01C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001C0004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x02001C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001C0004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001C0004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801C0004", + "BriefDescription": "Core-originated cacheable demand requests that refer to L3", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL057", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x4f" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00401C0004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0100004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000100004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400100004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200100004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100100004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080100004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040100004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0080004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000080004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400080004", + "BriefDescription": "Retired load instructions that miss the STLB.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PEBS": "1", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x11" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200080004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100080004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080080004", + "BriefDescription": "Counts demand data readshave any response type.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data readshave any response type.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040080004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0040004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080080004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000040004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400040004", + "BriefDescription": "L1D data line replacements", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200040004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100040004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080040004", + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x4" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040040004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0020004", + "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "SampleAfterValue": "100007", + "UMask": "0x40" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020004", + "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.USELESS_PREF", + "SampleAfterValue": "200003", + "UMask": "0x4" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020004", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.PF_HIT", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xd8" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020004", + "BriefDescription": "Demand Data Read miss L2, no rejects", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0x21" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040020004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0400002", + "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000400002", + "BriefDescription": "All retired load instructions.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x81" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400400002", + "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200400002", + "BriefDescription": "Demand Data Read requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0xe1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100400002", + "BriefDescription": "All L2 requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "All L2 requests.", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080400002", + "BriefDescription": "Cycles with L1D load Misses outstanding.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040400002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC01C0002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001C0002", + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001C0002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001C0002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00401C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001C0002", + "BriefDescription": "Number of cache line split locks sent to uncore.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF4", + "EventName": "SQ_MISC.SPLIT_LOCK", + "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC01C0002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801C0002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00401C0002", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0100002", + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000100002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400100002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200100002", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100100002", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080100002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040100002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0080002", + "BriefDescription": "L1D miss outstandings duration in cycles", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000080002", + "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", + "SampleAfterValue": "200003", + "UMask": "0xc1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400080002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04001C0004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200080002", + "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", + "SampleAfterValue": "20011", + "UMask": "0x4" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100080002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0100001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01001C0002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080080002", + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x42" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040080002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0040002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000040002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00801C0004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400040002", + "BriefDescription": "Any memory transaction that reached the SQ.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x80" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200040002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100040002", + "BriefDescription": "Counts any other requestshave any response type.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000018000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requestshave any response type.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080040002", + "BriefDescription": "Cacheable and noncachaeble code read requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040040002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0020002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020002", + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020002", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0xc4" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040020002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs) have any response type.", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0400001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000400001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400400001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200400001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100400001", + "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080400001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040400001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC01C0001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001C0001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001C0001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400080004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001C0001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100080004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001C0001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801C0001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00801C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00401C0001", + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0100001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000100001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400100001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0100004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200100001", + "BriefDescription": "Retired load instructions with locked access.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x21" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100100001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00801C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080100001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040100001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01001C0004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0080001", + "BriefDescription": "Demand and prefetch data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000080001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400080001", + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200080001", + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x41" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100080001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080080001", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040080001", + "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB2", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0040001", + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000040001", + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400040001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200040001", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100040001", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080040001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040040001", + "BriefDescription": "Retired store instructions that miss the STLB.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", "SampleAfterValue": "100003", + "UMask": "0x12" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0020001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01001C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020001", + "BriefDescription": "RFO requests to L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "SampleAfterValue": "200003", + "UMask": "0xe2" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020001", + "BriefDescription": "Retired load instructions missed L2 cache as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PEBS": "1", + "PublicDescription": "Retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "50021", + "UMask": "0x10" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400020002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020001", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040020001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads have any response type.", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00401C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json index 213dd6230cf2b..834e1cd841fc9 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json @@ -1,67 +1,67 @@ [ { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0xC7", + "BriefDescription": "Cycles with any input/output SSE or FP assist", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.ANY", + "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", + "SampleAfterValue": "100003", + "UMask": "0x1e" }, { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", - "EventCode": "0xCA", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x1e", - "EventName": "FP_ASSIST.ANY", - "SampleAfterValue": "100003", - "BriefDescription": "Cycles with any input/output SSE or FP assist", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "UMask": "0x8" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json index 7fa95a35e3cac..e84504d6adea2 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json @@ -1,482 +1,516 @@ [ { - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", - "EventCode": "0x79", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "IDQ.MITE_UOPS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE_16B.IFDATA_STALL", + "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "IDQ.MITE_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "IDQ.DSB_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x408006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "UMask": "0x8", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "IDQ.MS_DSB_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", "Counter": "0,1,2,3", - "UMask": "0x18", - "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xE6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.", "Counter": "0,1,2,3", - "UMask": "0x18", - "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "IDQ.MS_MITE_UOPS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", "SampleAfterValue": "2000003", - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", - "EventCode": "0x79", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles MITE is delivering 4 Uops", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x401006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", - "EventCode": "0x79", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles MITE is delivering any Uop", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", - "EventCode": "0x79", + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", - "EventCode": "0x79", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "UMask": "0x30", - "EdgeDetect": "1", - "EventName": "IDQ.MS_SWITCHES", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", "EventCode": "0x79", - "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_UOPS", + "EventName": "IDQ.MS_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x30" }, { - "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", - "EventCode": "0x80", + "BriefDescription": "Cycles MITE is delivering any Uop", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "ICACHE_16B.IFDATA_STALL", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x24" }, { - "EventCode": "0x83", + "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", "EventName": "ICACHE_64B.IFTAG_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x83", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "ICACHE_64B.IFTAG_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "2000003", + "UMask": "0x30" }, { - "EventCode": "0x83", + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "ICACHE_64B.IFTAG_STALL", - "SampleAfterValue": "200003", - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", - "EventCode": "0x9C", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", - "EventCode": "0x9C", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x404006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", - "EventCode": "0x9C", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", - "EventCode": "0x9C", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", - "EventCode": "0x9C", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_STALL", + "SampleAfterValue": "200003", + "UMask": "0x4" }, { - "EventCode": "0x9C", - "Invert": "1", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", "SampleAfterValue": "2000003", - "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", - "EventCode": "0xAB", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x18" }, { - "PEBS": "1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", - "EventCode": "0xC6", - "MSRValue": "0x11", + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.DSB_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x12", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.L1I_MISS", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x13", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.L2_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", + "MSRValue": "0x420006", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", - "EventCode": "0xC6", - "MSRValue": "0x14", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", + "MSRValue": "0x400806", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", - "EventCode": "0xC6", - "MSRValue": "0x15", + "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.STLB_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", + "MSRValue": "0x400106", + "PEBS": "2", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x400206", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", + "MSRValue": "0x400206", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x200206", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", + "MSRValue": "0x400406", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x400406", + "BriefDescription": "Cycles MITE is delivering 4 Uops", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x24" }, { - "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", - "EventCode": "0xC6", - "MSRValue": "0x400806", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_CYCLES", + "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", - "EventCode": "0xC6", - "MSRValue": "0x401006", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "SampleAfterValue": "2000003", + "UMask": "0x30" }, { - "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", - "EventCode": "0xC6", - "MSRValue": "0x402006", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", + "MSRValue": "0x410006", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x404006", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", "MSRIndex": "0x3F7", + "MSRValue": "0x200206", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x408006", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", "MSRIndex": "0x3F7", + "MSRValue": "0x300206", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x410006", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x420006", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x18" }, { - "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", - "EventCode": "0xC6", - "MSRValue": "0x100206", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.COUNT", + "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", + "MSRValue": "0x402006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x300206", + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_MISS", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", + "MSRValue": "0x12", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/memory.json b/tools/perf/pmu-events/arch/x86/skylake/memory.json index f197b4c7695be..7bd3ae3383437 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/memory.json +++ b/tools/perf/pmu-events/arch/x86/skylake/memory.json @@ -1,1604 +1,1611 @@ [ { - "PublicDescription": "Number of times a TSX line had a cache conflict.", - "EventCode": "0x54", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "TX_MEM.ABORT_CONFLICT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000080004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x54", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "TX_MEM.ABORT_CAPACITY", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0104000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", - "EventCode": "0x54", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000100002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", - "EventCode": "0x54", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0084008000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", - "EventCode": "0x54", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x007C400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", - "EventCode": "0x54", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x043C408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times we could not allocate Lock Buffer.", - "EventCode": "0x54", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0204000004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x5d", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "TX_EXEC.MISC1", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000088000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", - "EventCode": "0x5d", + "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "TX_EXEC.MISC2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", - "EventCode": "0x5d", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "TX_EXEC.MISC3", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00BC408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "RTM region detected inside HLE.", - "EventCode": "0x5d", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "TX_EXEC.MISC4", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103C408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", - "EventCode": "0x5d", + "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "TX_EXEC.MISC5", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_TIMER", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x60", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x023C400001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0204000002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", - "CounterMask": "6", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xA3", + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0xA3", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x6", - "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", - "SampleAfterValue": "2000003", - "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", - "CounterMask": "6", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000080002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Demand Data Read requests who miss L3 cache.", - "EventCode": "0xB0", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1004008000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", "SampleAfterValue": "100003", - "BriefDescription": "Demand Data Read requests who miss L3 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", - "EventCode": "0xC3", + "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "SKL089", - "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "SampleAfterValue": "100003", - "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", - "EventCode": "0xC8", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "HLE_RETIRED.START", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution started.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times HLE commit succeeded.", - "EventCode": "0xC8", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "HLE_RETIRED.COMMIT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution successfully committed", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFC408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Number of times HLE abort was triggered. (PEBS)", - "EventCode": "0xC8", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "HLE_RETIRED.ABORTED", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC8", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "HLE_RETIRED.ABORTED_MEM", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x043C400002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC8", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "HLE_RETIRED.ABORTED_TIMER", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000020004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", - "EventCode": "0xC8", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0044000002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", - "EventCode": "0xC8", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0204008000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC8", + "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", + "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", - "EventCode": "0xC9", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "RTM_RETIRED.START", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution started.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103C400001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times RTM commit succeeded.", - "EventCode": "0xC9", + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "RTM_RETIRED.COMMIT", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Number of times a TSX line had a cache conflict.", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution successfully committed", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Number of times RTM abort was triggered. (PEBS)", - "EventCode": "0xC9", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "RTM_RETIRED.ABORTED", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1004000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", - "EventCode": "0xC9", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "RTM_RETIRED.ABORTED_MEM", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000080001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC9", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "RTM_RETIRED.ABORTED_TIMER", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", - "EventCode": "0xC9", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0204000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", - "EventCode": "0xC9", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000020002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", - "EventCode": "0xC9", + "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", + "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x4", + "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", - "MSRIndex": "0x3F6", - "SampleAfterValue": "100003", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC5", + "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x8", + "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", - "MSRIndex": "0x3F6", - "SampleAfterValue": "50021", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC4", + "PublicDescription": "RTM region detected inside HLE.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x10", + "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", - "MSRIndex": "0x3F6", - "SampleAfterValue": "20011", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC3", + "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x20", + "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", - "MSRIndex": "0x3F6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC2", + "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x40", + "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", - "MSRIndex": "0x3F6", - "SampleAfterValue": "2003", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC1", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x80", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", - "MSRIndex": "0x3F6", - "SampleAfterValue": "1009", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0404000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x100", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", - "MSRIndex": "0x3F6", - "SampleAfterValue": "503", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0084000004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x200", + "BriefDescription": "Number of times an RTM execution successfully committed", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", - "MSRIndex": "0x3F6", - "SampleAfterValue": "101", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Number of times RTM commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FFC408000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x203C408000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103C408000", + "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043C408000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023C408000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013C408000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0104000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00BC408000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x203C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x007C408000", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x007C408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC4008000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004008000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0104000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004008000", + "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404008000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2004000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204008000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1004000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104008000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0044008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084008000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0044008000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0044000001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000408000", + "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20001C8000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0084000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000108000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x043C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000088000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00BC400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000048000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000028000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FFC400004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x203C400004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103C400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043C400004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001C0004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023C400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013C400004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x013C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00BC400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0404008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x007C400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0104008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC4000004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x013C408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000004", + "BriefDescription": "Number of times an HLE execution successfully committed", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.COMMIT", + "PublicDescription": "Number of times HLE commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x203C408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x023C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0044000004", + "BriefDescription": "Demand Data Read requests who miss L3 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Demand Data Read requests who miss L3 cache.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x10" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000400004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00BC400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20001C0004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2004000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000100004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x023C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000080004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFC400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000040004", + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020004", + "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEM", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FFC400002", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x203C400002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x013C400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103C400002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x203C400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043C400002", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x007C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023C400002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC4008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013C400002", + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times RTM abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00BC400002", + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times HLE abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x203C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x007C400002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0404000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC4000002", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2004008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000002", + "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", + "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000002", + "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC4000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000002", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000002", + "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0044000002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0084000001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000400002", + "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20001C0002", + "BriefDescription": "Number of times an RTM execution started.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000100002", + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL089", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000080002", + "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", + "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000040002", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1004000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FFC400001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC4000002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x007C400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x203C400001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103C400001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00BC400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043C400001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x043C400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023C400001", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013C400001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFC400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00BC400001", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "SampleAfterValue": "2000003", + "UMask": "0x80" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x007C400001", + "BriefDescription": "Number of times an HLE execution started.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.START", + "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC4000001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFC400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2004000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC4000001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000001", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000001", + "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", + "PublicDescription": "Number of times we could not allocate Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0044000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x013C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0044000001", + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x6" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000400001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x023C408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20001C0001", + "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "SampleAfterValue": "2000003", + "UMask": "0x80" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000100001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001C8000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000080001", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000040001", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0404000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/other.json b/tools/perf/pmu-events/arch/x86/skylake/other.json index 84a316d380acb..1a3683f1de918 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/other.json +++ b/tools/perf/pmu-events/arch/x86/skylake/other.json @@ -1,48 +1,56 @@ [ { - "EventCode": "0x32", + "BriefDescription": "Number of PREFETCHW instructions executed.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "SW_PREFETCH_ACCESS.NTA", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", "SampleAfterValue": "2000003", - "BriefDescription": "Number of PREFETCHNTA instructions executed.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0x32", + "BriefDescription": "Number of PREFETCHT0 instructions executed.", "Counter": "0,1,2,3", - "UMask": "0x2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.T0", "SampleAfterValue": "2000003", - "BriefDescription": "Number of PREFETCHT0 instructions executed.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0x32", + "BriefDescription": "Number of hardware interrupts received by the processor.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCB", + "EventName": "HW_INTERRUPTS.RECEIVED", + "PublicDescription": "Counts the number of hardware interruptions received by the processor.", + "SampleAfterValue": "203", + "UMask": "0x1" }, { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", "SampleAfterValue": "2000003", - "BriefDescription": "Number of PREFETCHW instructions executed.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts the number of hardware interruptions received by the processor.", - "EventCode": "0xCB", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "HW_INTERRUPTS.RECEIVED", - "SampleAfterValue": "203", - "BriefDescription": "Number of hardware interrupts received by the processor.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x09", + "EventName": "MEMORY_DISAMBIGUATION.HISTORY_RESET", + "SampleAfterValue": "2000003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json index 4a891fbbc4bb2..f46e93a57fb49 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json @@ -1,967 +1,969 @@ [ { - "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "Counter": "Fixed counter 0", - "UMask": "0x1", - "EventName": "INST_RETIRED.ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Instructions retired from execution.", - "CounterHTOff": "Fixed counter 0" - }, - { - "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", - "Counter": "Fixed counter 1", - "UMask": "0x2", - "EventName": "CPU_CLK_UNHALTED.THREAD", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when the thread is not in halt state", - "CounterHTOff": "Fixed counter 1" + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.ANY_P", + "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", + "SampleAfterValue": "2000003" }, { - "Counter": "Fixed counter 1", - "UMask": "0x2", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "CounterHTOff": "Fixed counter 1" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", - "Counter": "Fixed counter 2", - "UMask": "0x3", - "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the core is not in halt state.", - "CounterHTOff": "Fixed counter 2" + "UMask": "0x10" }, { - "PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.", - "EventCode": "0x03", + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "LD_BLOCKS.STORE_FORWARD", - "SampleAfterValue": "100003", - "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x14", + "EventName": "ARITH.DIVIDER_ACTIVE", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", - "EventCode": "0x03", + "BriefDescription": "False dependencies in MOB due to partial compare on address.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "LD_BLOCKS.NO_SR", - "SampleAfterValue": "100003", - "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x07", - "Counter": "0,1,2,3", - "UMask": "0x1", "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", "SampleAfterValue": "100003", - "BriefDescription": "False dependencies in MOB due to partial compare on address.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", - "EventCode": "0x0D", + "BriefDescription": "Far branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "INT_MISC.RECOVERY_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PEBS": "1", + "PublicDescription": "This event counts far branch instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x40" }, { - "EventCode": "0x0D", + "BriefDescription": "Counts the number of x87 uops dispatched.", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x0D", + "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4C", + "EventName": "LOAD_HIT_PRE.SW_PF", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", - "EventCode": "0x0E", + "BriefDescription": "Mispredicted direct and indirect near call instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_ISSUED.ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.", + "SampleAfterValue": "400009", + "UMask": "0x2" }, { - "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", - "EventCode": "0x0E", - "Invert": "1", + "BriefDescription": "Total execution stalls.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_ISSUED.STALL_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.", - "EventCode": "0x0E", + "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", - "SampleAfterValue": "2000003", - "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x0E", - "Counter": "0,1,2,3", - "UMask": "0x20", "EventName": "UOPS_ISSUED.SLOW_LEA", "SampleAfterValue": "2000003", - "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0x14", + "BriefDescription": "Cycles with less than 10 actually retired uops.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ARITH.DIVIDER_ACTIVE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "10", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "Invert": "1", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", - "EventCode": "0x3C", + "BriefDescription": "Thread cycles when thread is not in halt state", "Counter": "0,1,2,3", - "UMask": "0x0", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "SampleAfterValue": "2000003", - "BriefDescription": "Thread cycles when thread is not in halt state", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003" }, { - "EventCode": "0x3C", + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", "Counter": "0,1,2,3", - "UMask": "0x0", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", - "EventCode": "0x3C", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", - "UMask": "0x0", - "EdgeDetect": "1", - "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", - "SampleAfterValue": "100007", - "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x1", "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0x3C", + "BriefDescription": "Number of machine clears (nukes) of any type.", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.COUNT", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0x3C", + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Number of uops to be executed per-thread each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0x3C", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x3C", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", - "EventCode": "0x4C", + "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LOAD_HIT_PRE.SW_PF", - "SampleAfterValue": "100003", - "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", - "EventCode": "0x59", + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "8", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", - "EventCode": "0x5E", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "RS_EVENTS.EMPTY_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", - "EventCode": "0x5E", - "Invert": "1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "RS_EVENTS.EMPTY_END", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", "SampleAfterValue": "2000003", - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", - "EventCode": "0x87", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ILD_STALL.LCP", - "SampleAfterValue": "2000003", - "BriefDescription": "Stalls caused by changing prefix length of the instruction.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 0", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 0", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 1", "Counter": "0,1,2,3", - "UMask": "0x2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 2", "Counter": "0,1,2,3", - "UMask": "0x4", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 3", "Counter": "0,1,2,3", - "UMask": "0x8", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 4", "Counter": "0,1,2,3", - "UMask": "0x10", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 5", "Counter": "0,1,2,3", - "UMask": "0x20", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 5", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 6", "Counter": "0,1,2,3", - "UMask": "0x40", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_6", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 6", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 7", "Counter": "0,1,2,3", - "UMask": "0x80", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_7", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 7", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x80" }, { - "PublicDescription": "Counts resource-related stall cycles.", - "EventCode": "0xa2", + "AnyThread": "1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "RESOURCE_STALLS.ANY", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Resource-related stall cycles", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", - "EventCode": "0xA2", - "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "RESOURCE_STALLS.SB", + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "Counter": "1", + "CounterHTOff": "1", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.PREC_DIST", + "PEBS": "2", + "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_4_UOPS", + "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", - "BriefDescription": "Total execution stalls.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xA3", + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", "Counter": "0,1,2,3", - "UMask": "0x5", - "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "SampleAfterValue": "2000003", - "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", - "CounterMask": "5", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x2" }, { - "EventCode": "0xA3", + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", - "CounterMask": "8", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", "Counter": "0,1,2,3", - "UMask": "0xc", - "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x59", + "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", "SampleAfterValue": "2000003", - "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", - "CounterMask": "12", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles while memory subsystem has an outstanding load.", - "CounterMask": "16", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Not taken branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x14", - "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", - "CounterMask": "20", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" }, { - "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", - "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 2", + "CounterHTOff": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x3" }, { - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", + "BriefDescription": "All mispredicted macro branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009" }, { - "EventCode": "0xA6", + "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.ANY", + "SampleAfterValue": "100003", + "UMask": "0x3f" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).", - "EventCode": "0xA8", + "BriefDescription": "Number of Uops delivered by the LSD.", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA8", "EventName": "LSD.UOPS", + "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).", "SampleAfterValue": "2000003", - "BriefDescription": "Number of Uops delivered by the LSD.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", - "EventCode": "0xA8", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_ACTIVE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" }, { - "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", - "EventCode": "0xA8", + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_4_UOPS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x87", + "EventName": "ILD_STALL.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Number of uops to be executed per-thread each cycle.", - "EventCode": "0xB1", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.THREAD", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_END", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", - "EventCode": "0xB1", - "Invert": "1", + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "16", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", - "EventCode": "0xB1", + "BriefDescription": "Taken branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 1 uop was executed per-thread", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "This event counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20" }, { - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", - "EventCode": "0xB1", + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 2 uops were executed per-thread", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x8" }, { - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", - "EventCode": "0xB1", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 3 uops were executed per-thread", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", - "EventCode": "0xB1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "BriefDescription": "Core cycles when the thread is not in halt state", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 4 uops were executed per-thread", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Number of uops executed from any thread.", - "EventCode": "0xB1", + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of uops executed on the core.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0xB1", + "BriefDescription": "Direct and indirect near call instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "This event counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2" }, { - "EventCode": "0xB1", + "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.PAUSE_INST", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0xB1", + "BriefDescription": "Resource-related stall cycles", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.ANY", + "PublicDescription": "Counts resource-related stall cycles.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xB1", + "BriefDescription": "Self-modifying code (SMC) detected.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "EventCode": "0xB1", - "Invert": "1", + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "5", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x5" }, { - "PublicDescription": "Counts the number of x87 uops executed.", - "EventCode": "0xB1", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "UOPS_EXECUTED.X87", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of x87 uops dispatched.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", - "EventCode": "0xC0", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "Counter": "0,1,2,3", - "UMask": "0x0", - "Errata": "SKL091, SKL044", - "EventName": "INST_RETIRED.ANY_P", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "20", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Number of instructions retired. General Counter - architectural event", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x14" }, { - "PEBS": "2", - "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.", - "EventCode": "0xC0", - "Counter": "1", - "UMask": "0x1", - "Errata": "SKL091, SKL044", - "EventName": "INST_RETIRED.PREC_DIST", + "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", - "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", - "CounterHTOff": "1" + "UMask": "0x1" }, { - "PEBS": "2", - "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", - "EventCode": "0xC0", - "Invert": "1", + "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", "Counter": "0,2,3", - "UMask": "0x1", + "CounterHTOff": "0,2,3", + "CounterMask": "10", "Errata": "SKL091, SKL044", + "EventCode": "0xC0", "EventName": "INST_RETIRED.TOTAL_CYCLES_PS", + "Invert": "1", + "PEBS": "2", + "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", "SampleAfterValue": "2000003", - "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", - "CounterMask": "10", - "CounterHTOff": "0,2,3" + "UMask": "0x1" }, { - "EventCode": "0xC1", + "BriefDescription": "Retirement slots used.", "Counter": "0,1,2,3", - "UMask": "0x3f", - "EventName": "OTHER_ASSISTS.ANY", - "SampleAfterValue": "100003", - "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts the retirement slots used.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0xC2", - "Counter": "0,1,2,3", - "UMask": "0x2", "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "Counts the retirement slots used.", "SampleAfterValue": "2000003", - "BriefDescription": "Retirement slots used.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "This event counts cycles without actually retired uops.", - "EventCode": "0xC2", - "Invert": "1", + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_RETIRED.STALL_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", - "EventCode": "0xC2", - "Invert": "1", + "BriefDescription": "Number of macro-fused uops retired. (non precise)", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MACRO_FUSED", + "PublicDescription": "Counts the number of macro-fused uops retired. (non precise)", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 10 actually retired uops.", - "CounterMask": "10", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Number of machine clears (nukes) of any type.", - "EventCode": "0xC3", + "BriefDescription": "Increments whenever there is an update to the LBR array.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "MACHINE_CLEARS.COUNT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of machine clears (nukes) of any type.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", - "EventCode": "0xC3", + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MACHINE_CLEARS.SMC", - "SampleAfterValue": "100003", - "BriefDescription": "Self-modifying code (SMC) detected.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all (macro) branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Instructions retired from execution.", + "Counter": "Fixed counter 0", + "CounterHTOff": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x0", - "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "SampleAfterValue": "400009", - "BriefDescription": "All (macro) branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.CONDITIONAL", - "SampleAfterValue": "400009", - "BriefDescription": "Conditional branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.NEAR_CALL", - "SampleAfterValue": "100007", - "BriefDescription": "Direct and indirect near call instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", + "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", + "SampleAfterValue": "100007" }, { - "PEBS": "2", - "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "All (macro) branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x4", + "CounterHTOff": "0,1,2,3", "Errata": "SKL091", + "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", "SampleAfterValue": "400009", - "BriefDescription": "All (macro) branch instructions retired.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x4" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Mispredicted macro branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x8", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Return instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", "Errata": "SKL091", + "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "PublicDescription": "This event counts return instructions retired.", "SampleAfterValue": "100007", - "BriefDescription": "Return instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "UMask": "0x10", - "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.NOT_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Counts all not taken macro branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Not taken branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x20", + "CounterHTOff": "0,1,2,3,4,5,6,7", "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", "SampleAfterValue": "400009", - "BriefDescription": "Taken branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Conditional branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x40", + "CounterHTOff": "0,1,2,3,4,5,6,7", "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of far branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", - "EventCode": "0xC5", - "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "This event counts conditional branch instructions retired.", "SampleAfterValue": "400009", - "BriefDescription": "All mispredicted macro branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.", - "EventCode": "0xC5", + "BriefDescription": "Mispredicted conditional branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "This event counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted conditional branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "This event counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.", - "EventCode": "0xC5", + "BriefDescription": "Number of uops executed on the core.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "BR_MISP_RETIRED.NEAR_CALL", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted direct and indirect near call instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Number of uops executed from any thread.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PEBS": "2", - "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", - "EventCode": "0xC5", + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted macro branch instructions retired.", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "12", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "SampleAfterValue": "2000003", + "UMask": "0xc" }, { - "PEBS": "1", - "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.", - "EventCode": "0xC5", + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", - "EventCode": "0xCC", + "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Increments whenever there is an update to the LBR array.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x80" }, { - "EventCode": "0xCC", + "BriefDescription": "All (macro) branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", - "EventCode": "0xE6", + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "BACLEARS.ANY", - "SampleAfterValue": "100003", - "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 8704efeb8d311..4cd246782dde1 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -1,370 +1,371 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "MetricGroup": "TopdownL1", - "MetricName": "Frontend_Bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound." + "MetricName": "Frontend_Bound" }, { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", "MetricGroup": "TopdownL1_SMT", - "MetricName": "Frontend_Bound_SMT", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + "MetricName": "Frontend_Bound_SMT" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "MetricGroup": "TopdownL1", - "MetricName": "Bad_Speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example." + "MetricName": "Bad_Speculation" }, { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", "MetricGroup": "TopdownL1_SMT", - "MetricName": "Bad_Speculation_SMT", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU." + "MetricName": "Bad_Speculation_SMT" }, { + "MetricConstraint": "NO_NMI_WATCHDOG", + "MetricGroup": "TopdownL1", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", - "MetricGroup": "TopdownL1", - "MetricName": "Backend_Bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound." + "MetricName": "Backend_Bound" }, { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", "MetricGroup": "TopdownL1_SMT", - "MetricName": "Backend_Bound_SMT", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + "MetricName": "Backend_Bound_SMT" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "MetricGroup": "TopdownL1", - "MetricName": "Retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. " + "MetricName": "Retiring" }, { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", "MetricGroup": "TopdownL1_SMT", - "MetricName": "Retiring_SMT", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU." + "MetricName": "Retiring_SMT" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopDownL1", + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricGroup": "Summary", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "BriefDescription": "Uops Per Instruction", "MetricGroup": "Pipeline;Retire", "MetricName": "UPI" }, { - "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", "MetricGroup": "Branches;Fetch_BW;PGO", "MetricName": "IpTB" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;PGO", - "MetricName": "BpTB" - }, - { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", - "MetricGroup": "PGO;IcMiss", - "MetricName": "IFetch_Line_Utilization" - }, - { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fetch_BW", - "MetricName": "DSB_Coverage" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", - "MetricGroup": "Pipeline;Summary", + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricGroup": "Pipeline", "MetricName": "CPI" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", - "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", "MetricGroup": "TopDownL1_SMT", "MetricName": "SLOTS_SMT" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "Instruction_Type", - "MetricName": "IpL" - }, - { - "BriefDescription": "Instructions per Store (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "Instruction_Type", - "MetricName": "IpS" - }, - { - "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Instruction_Type", - "MetricName": "IpB" - }, - { - "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches", - "MetricName": "IpCall" - }, - { - "BriefDescription": "Total number of retired Instructions", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary", - "MetricName": "Instructions" - }, - { - "BriefDescription": "Instructions Per Cycle (per physical core)", "MetricExpr": "INST_RETIRED.ANY / cycles", - "MetricGroup": "SMT", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT;TopDownL1", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", - "MetricGroup": "SMT", + "MetricGroup": "SMT;TopDownL1", "MetricName": "CoreIPC_SMT" }, { + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / cycles", "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles", "MetricGroup": "FLOPS", "MetricName": "FLOPc" }, { + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", "MetricGroup": "FLOPS_SMT", "MetricName": "FLOPc_SMT" }, { + "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 )", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Pipeline", + "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", "MetricGroup": "BrMispredicts", "MetricName": "Branch_Misprediction_Cost" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", - "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", "MetricGroup": "BrMispredicts_SMT", "MetricName": "Branch_Misprediction_Cost_SMT" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", "MetricGroup": "BrMispredicts", "MetricName": "IpMispredict" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricGroup": "Instruction_Type", + "MetricName": "IpLoad" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricGroup": "Instruction_Type", + "MetricName": "IpStore" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricGroup": "Branches;Instruction_Type", + "MetricName": "IpBranch" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTkBranch" + }, + { + "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )", + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricGroup": "FLOPS;FP_Arith;Instruction_Type", + "MetricName": "IpFLOP" + }, + { + "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", + "MetricGroup": "Summary;TopDownL1", + "MetricName": "Instructions" + }, + { + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Fetch_BW", + "MetricName": "DSB_Coverage" + }, + { "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_NMI_WATCHDOG", "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", "MetricGroup": "TLB", - "MetricName": "Page_Walks_Utilization", - "MetricConstraint": "NO_NMI_WATCHDOG" + "MetricName": "Page_Walks_Utilization" }, { + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", "MetricGroup": "TLB_SMT", "MetricName": "Page_Walks_Utilization_SMT" }, { - "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", "MetricGroup": "Memory_BW", "MetricName": "L1D_Cache_Fill_BW" }, { - "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", "MetricGroup": "Memory_BW", "MetricName": "L2_Cache_Fill_BW" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricGroup": "Memory_BW", "MetricName": "L3_Cache_Fill_BW" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", - "MetricGroup": "Memory_BW", + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW;Offcore", "MetricName": "L3_Cache_Access_BW" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricGroup": "Cache_Misses", "MetricName": "L1MPKI" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricGroup": "Cache_Misses", "MetricName": "L2MPKI" }, { - "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "Cache_Misses", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;Offcore", "MetricName": "L2MPKI_All" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricGroup": "Cache_Misses", "MetricName": "L2HPKI_All" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", "MetricGroup": "Cache_Misses", "MetricName": "L3MPKI" }, { - "BriefDescription": "Average CPU Utilization", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", - "MetricGroup": "Summary", + "BriefDescription": "Average CPU Utilization", + "MetricGroup": "HPC;Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time", - "MetricGroup": "FLOPS;Summary", + "MetricGroup": "FLOPS;HPC", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 )", "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", - "MetricGroup": "SMT;Summary", + "MetricGroup": "SMT", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Summary", + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricGroup": "OS", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", - "MetricGroup": "Memory_BW", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "HPC;Memory_BW;SoC", "MetricName": "DRAM_BW_Use" }, { + "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,cmask\\=1@", "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,thresh\\=1@", - "MetricGroup": "Memory_BW", - "MetricName": "DRAM_Parallel_Reads" + "MetricGroup": "Memory_BW;SoC", + "MetricName": "MEM_Parallel_Reads" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions. )", "MetricExpr": "INST_RETIRED.ANY / ( BR_INST_RETIRED.FAR_BRANCH / 2 )", - "MetricGroup": "", + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricGroup": "Branches;OS", "MetricName": "IpFarBranch" }, { - "BriefDescription": "C3 residency percent per core", "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C3 residency percent per core", "MetricGroup": "Power", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C6 residency percent per core", "MetricGroup": "Power", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C7 residency percent per core", "MetricGroup": "Power", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C2 residency percent per package", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C3 residency percent per package", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C6 residency percent per package", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C7 residency percent per package", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency" } diff --git a/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json index 2bcba7daca14d..432530d15c26a 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json @@ -1,284 +1,284 @@ [ { - "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", - "EventCode": "0x08", + "BriefDescription": "Store misses in all DTLB levels that cause page walks", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", "SampleAfterValue": "100003", - "BriefDescription": "Load misses in all DTLB levels that cause page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "EventCode": "0x08", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "SampleAfterValue": "2000003", - "BriefDescription": "Page walk completed due to a demand data load to a 4K page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", - "EventCode": "0x08", + "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "SampleAfterValue": "2000003", - "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "EventCode": "0x08", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "SampleAfterValue": "2000003", - "BriefDescription": "Page walk completed due to a demand data load to a 1G page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", + "SampleAfterValue": "100003", + "UMask": "0x10" }, { - "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", - "EventCode": "0x08", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.", - "EventCode": "0x08", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAE", + "EventName": "ITLB.ITLB_FLUSH", + "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", + "SampleAfterValue": "100007", + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.", - "EventCode": "0x08", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "SampleAfterValue": "100003", - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "100003", + "UMask": "0x10" }, { - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", - "EventCode": "0x08", + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", "Counter": "0,1,2,3", - "UMask": "0x20", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", "SampleAfterValue": "2000003", - "BriefDescription": "Loads that miss the DTLB and hit the STLB.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "DTLB flush attempts of the thread-specific entries", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", - "SampleAfterValue": "100003", - "BriefDescription": "Store misses in all DTLB levels that cause page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100007", + "UMask": "0x1" }, { - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "EventCode": "0x49", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "SampleAfterValue": "100003", - "BriefDescription": "Page walk completed due to a demand data store to a 4K page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", - "EventCode": "0x49", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", "SampleAfterValue": "100003", - "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages. The page walks can end with or without a page fault.", - "EventCode": "0x49", + "BriefDescription": "Misses at all ITLB levels that cause page walks", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", "SampleAfterValue": "100003", - "BriefDescription": "Page walk completed due to a demand data store to a 1G page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", - "EventCode": "0x49", + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", "SampleAfterValue": "100003", - "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.", - "EventCode": "0x49", + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" }, { - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", - "EventCode": "0x49", + "BriefDescription": "Page walk completed due to a demand data store to a 4K page", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", - "EventCode": "0x49", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "BriefDescription": "Stores that miss the DTLB and hit the STLB.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", - "EventCode": "0x4F", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "EPT.WALK_PENDING", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" }, { - "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", - "EventCode": "0x85", + "BriefDescription": "Page walk completed due to a demand data load to a 4K page", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", - "SampleAfterValue": "100003", - "BriefDescription": "Misses at all ITLB levels that cause page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", - "EventCode": "0x85", + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", "SampleAfterValue": "100003", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.", - "EventCode": "0x85", + "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "SampleAfterValue": "100003", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", - "EventCode": "0x85", + "BriefDescription": "Load misses in all DTLB levels that cause page walks", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", "SampleAfterValue": "100003", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", - "EventCode": "0x85", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "ITLB_MISSES.WALK_COMPLETED", - "SampleAfterValue": "100003", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4f", + "EventName": "EPT.WALK_PENDING", + "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", - "EventCode": "0x85", + "BriefDescription": "STLB flush attempts", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "ITLB_MISSES.WALK_PENDING", - "SampleAfterValue": "100003", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.STLB_ANY", + "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", + "SampleAfterValue": "100007", + "UMask": "0x20" }, { - "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", - "EventCode": "0x85", + "BriefDescription": "Page walk completed due to a demand data load to a 1G page", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "ITLB_MISSES.WALK_ACTIVE", - "SampleAfterValue": "100003", - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "EventCode": "0x85", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "ITLB_MISSES.STLB_HIT", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.", "SampleAfterValue": "100003", - "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", - "EventCode": "0xAE", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ITLB.ITLB_FLUSH", - "SampleAfterValue": "100007", - "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", - "EventCode": "0xBD", + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "TLB_FLUSH.DTLB_THREAD", - "SampleAfterValue": "100007", - "BriefDescription": "DTLB flush attempts of the thread-specific entries", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" }, { - "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", - "EventCode": "0xBD", + "BriefDescription": "Page walk completed due to a demand data store to a 1G page", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "TLB_FLUSH.STLB_ANY", - "SampleAfterValue": "100007", - "BriefDescription": "STLB flush attempts", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json index 24df183693faa..e750a21976f1c 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json @@ -1,1663 +1,1675 @@ [ { - "EventCode": "0x24", - "UMask": "0x21", - "BriefDescription": "Demand Data Read miss L2, no rejects", + "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x24", - "UMask": "0x22", - "BriefDescription": "RFO requests that miss L2 cache", + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "EventCode": "0x24", - "UMask": "0x24", - "BriefDescription": "L2 cache misses when fetching instructions", + "BriefDescription": "Counts all demand code reads that have any response type.", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x24", - "UMask": "0x27", + "EventName": "L2_RQSTS.PF_MISS", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x38" + }, + { "BriefDescription": "Demand requests that miss L2 cache", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", "PublicDescription": "Demand requests that miss L2 cache.", "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x27" }, { - "EventCode": "0x24", - "UMask": "0x38", - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", + "BriefDescription": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.PF_MISS", - "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x24", - "UMask": "0x3f", - "BriefDescription": "All requests that miss L2 cache", + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.MISS", - "PublicDescription": "All requests that miss L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "SampleAfterValue": "50021", + "UMask": "0x4" }, { - "EventCode": "0x24", - "UMask": "0xc1", - "BriefDescription": "Demand Data Read requests that hit L2 cache", + "BriefDescription": "L2 writebacks that access L2 cache", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0x24", - "UMask": "0xc2", - "BriefDescription": "RFO requests that hit L2 cache", + "BriefDescription": "L2 cache lines filling L2", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "UMask": "0x1f" }, { - "EventCode": "0x24", - "UMask": "0xc4", - "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x24", - "UMask": "0xd8", - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", + "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.PF_HIT", - "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x24", - "UMask": "0xe1", - "BriefDescription": "Demand Data Read requests", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x24", - "UMask": "0xe2", - "BriefDescription": "RFO requests to L2 cache", + "BriefDescription": "Demand Data Read requests sent to uncore", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.ALL_RFO", - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x24", - "UMask": "0xe4", - "BriefDescription": "L2 code requests", + "BriefDescription": "Retired load instructions missed L3 cache as data sources", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "SampleAfterValue": "100007", + "UMask": "0x20" }, { - "EventCode": "0x24", - "UMask": "0xe7", - "BriefDescription": "Demand requests to L2 cache", + "BriefDescription": "All retired store instructions.", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Demand requests to L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x82" }, { - "EventCode": "0x24", - "UMask": "0xf8", - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", + "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.ALL_PF", - "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.SILENT", "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x24", - "UMask": "0xff", - "BriefDescription": "All L2 requests", + "BriefDescription": "Counts all prefetch data reads that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "All L2 requests.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x2E", - "UMask": "0x41", - "BriefDescription": "Core-originated cacheable demand requests missed L3", + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "LONGEST_LAT_CACHE.MISS", - "Errata": "SKL057", - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x2E", - "UMask": "0x4f", - "BriefDescription": "Core-originated cacheable demand requests that refer to L3", + "BriefDescription": "Core-originated cacheable demand requests missed L3", "Counter": "0,1,2,3", - "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "CounterHTOff": "0,1,2,3,4,5,6,7", "Errata": "SKL057", - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x41" }, { - "EventCode": "0x48", - "UMask": "0x1", - "BriefDescription": "Cycles with L1D load Misses outstanding.", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_PF", + "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "SampleAfterValue": "200003", + "UMask": "0xf8" }, { - "EventCode": "0x48", - "UMask": "0x1", - "BriefDescription": "L1D miss outstandings duration in cycles", + "BriefDescription": "Retired load instructions whose data sources was remote HITM", "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PEBS": "1", + "PublicDescription": "Retired load instructions whose data sources was remote HITM.", + "SampleAfterValue": "100007", + "UMask": "0x4" }, { - "EventCode": "0x48", - "UMask": "0x1", - "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "BriefDescription": "Counts all prefetch data reads that have any response type.", "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", - "AnyThread": "1", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x48", - "UMask": "0x2", - "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", + "BriefDescription": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x51", - "UMask": "0x1", - "BriefDescription": "L1D data line replacements", + "BriefDescription": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "L1D.REPLACEMENT", - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", - "UMask": "0x1", - "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "CounterMask": "1", - "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0x60", - "UMask": "0x1", - "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", - "UMask": "0x1", - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "BriefDescription": "RFO requests that miss L2 cache", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", - "CounterMask": "6", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x22" }, { - "EventCode": "0x60", - "UMask": "0x2", - "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", + "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped.", + "SampleAfterValue": "200003", + "UMask": "0x2" }, { - "EventCode": "0x60", - "UMask": "0x2", - "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "CounterMask": "1", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "SampleAfterValue": "200003", + "UMask": "0x4" }, { - "EventCode": "0x60", - "UMask": "0x4", - "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", - "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", - "UMask": "0x4", - "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "BriefDescription": "All requests that miss L2 cache", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "CounterMask": "1", - "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "All requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x3f" }, { - "EventCode": "0x60", - "UMask": "0x8", - "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "BriefDescription": "L2 code requests", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "CounterMask": "1", - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4" }, { - "EventCode": "0x60", - "UMask": "0x8", - "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", + "PEBS": "1", + "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", + "SampleAfterValue": "100007", + "UMask": "0x8" }, { - "EventCode": "0xB0", - "UMask": "0x1", - "BriefDescription": "Demand Data Read requests sent to uncore", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xB0", - "UMask": "0x2", - "BriefDescription": "Cacheable and noncachaeble code read requests", + "BriefDescription": "Counts all demand & prefetch data reads that have any response type.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xB0", - "UMask": "0x4", - "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x2" }, { - "EventCode": "0xB0", - "UMask": "0x8", - "BriefDescription": "Demand and prefetch data reads", + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x2" }, { - "EventCode": "0xB0", - "UMask": "0x80", - "BriefDescription": "Any memory transaction that reached the SQ.", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", - "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xB2", - "UMask": "0x1", - "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", + "BriefDescription": "Retired load instructions missed L1 cache as data sources", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", - "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "SampleAfterValue": "100003", + "UMask": "0x8" }, { - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0020", + "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xD0", - "UMask": "0x11", - "BriefDescription": "Retired load instructions that miss the STLB. (Precise Event)", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PublicDescription": "Retired load instructions that miss the STLB.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xD0", - "UMask": "0x12", - "BriefDescription": "Retired store instructions that miss the STLB. (Precise Event)", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "L2 cache misses when fetching instructions", "Counter": "0,1,2,3", - "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PublicDescription": "Retired store instructions that miss the STLB.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24" + }, + { + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "L1_Hit_Indication": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xD0", - "UMask": "0x21", - "BriefDescription": "Retired load instructions with locked access. (Precise Event)", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", "Counter": "0,1,2,3", - "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0xD0", - "UMask": "0x41", - "BriefDescription": "Retired load instructions that split across a cacheline boundary. (Precise Event)", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts demand data reads that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xD0", - "UMask": "0x42", - "BriefDescription": "Retired store instructions that split across a cacheline boundary. (Precise Event)", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "L1_Hit_Indication": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xD0", - "UMask": "0x81", - "BriefDescription": "All retired load instructions. (Precise Event)", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xD0", - "UMask": "0x82", - "BriefDescription": "All retired store instructions. (Precise Event)", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PublicDescription": "All retired store instructions.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "2000003", - "L1_Hit_Indication": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "EventCode": "0xD1", - "UMask": "0x1", - "BriefDescription": "Retired load instructions with L1 cache hits as data sources", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Demand requests to L2 cache", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PublicDescription": "Demand requests to L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xe7" }, { - "EventCode": "0xD1", - "UMask": "0x2", - "BriefDescription": "Retired load instructions with L2 cache hits as data sources", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xD1", - "UMask": "0x4", - "BriefDescription": "Retired load instructions with L3 cache hits as data sources", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PublicDescription": "Retired load instructions with L3 cache hits as data sources.", - "SampleAfterValue": "50021", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xD1", - "UMask": "0x8", - "BriefDescription": "Retired load instructions missed L1 cache as data sources", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xD1", - "UMask": "0x10", - "BriefDescription": "Retired load instructions missed L2 cache as data sources", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PublicDescription": "Retired load instructions missed L2 cache as data sources.", - "SampleAfterValue": "50021", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xD1", - "UMask": "0x20", - "BriefDescription": "Retired load instructions missed L3 cache as data sources", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PublicDescription": "Retired load instructions missed L3 cache as data sources.", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xD1", - "UMask": "0x40", - "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xD2", - "UMask": "0x1", - "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", - "Data_LA": "1", - "PEBS": "1", + "AnyThread": "1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "SampleAfterValue": "20011", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0xD2", - "UMask": "0x2", - "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", - "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", - "SampleAfterValue": "20011", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xD2", - "UMask": "0x4", - "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Core-originated cacheable demand requests that refer to L3", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", - "SampleAfterValue": "20011", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL057", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x4f" }, { - "EventCode": "0xD2", - "UMask": "0x8", - "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xD3", - "UMask": "0x1", - "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xD3", - "UMask": "0x2", - "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xD3", - "UMask": "0x4", - "BriefDescription": "Retired load instructions whose data sources was remote HITM", + "BriefDescription": "Retired load instructions that miss the STLB.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", "PEBS": "1", - "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "SampleAfterValue": "100003", + "UMask": "0x11" }, { - "EventCode": "0xD3", - "UMask": "0x8", - "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts demand data reads that have any response type.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xD4", - "UMask": "0x4", - "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xF0", - "UMask": "0x40", - "BriefDescription": "L2 writebacks that access L2 cache", + "BriefDescription": "L1D data line replacements", "Counter": "0,1,2,3", - "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0xF1", - "UMask": "0x1f", - "BriefDescription": "L2 cache lines filling L2", + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "L2_LINES_IN.ALL", - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xF2", - "UMask": "0x1", - "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.", + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", "Counter": "0,1,2,3", - "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x4" }, { - "EventCode": "0xF2", - "UMask": "0x2", - "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped", + "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", "Counter": "0,1,2,3", - "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "SampleAfterValue": "100007", + "UMask": "0x40" }, { - "EventCode": "0xF2", - "UMask": "0x4", "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", - "Deprecated": "1", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xF2", "EventName": "L2_LINES_OUT.USELESS_PREF", - "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0xF2", - "UMask": "0x4", - "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", "Counter": "0,1,2,3", - "EventName": "L2_LINES_OUT.USELESS_HWPF", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.PF_HIT", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0xd8" }, { - "EventCode": "0xF4", - "UMask": "0x10", - "BriefDescription": "Number of cache line split locks sent to uncore.", + "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", "Counter": "0,1,2,3", - "EventName": "SQ_MISC.SPLIT_LOCK", - "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "Offcore": "1", + "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads have any response type.", - "MSRValue": "0x0000010001", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads have any response type.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { + "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010122", "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD TBD", - "MSRValue": "0x01003C0001", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD TBD", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD TBD", - "MSRValue": "0x04003C0001", + "BriefDescription": "Demand Data Read miss L2, no rejects", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0x21" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD TBD", - "MSRValue": "0x10003C0001", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD TBD", - "MSRValue": "0x3F803C0001", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", - "MSRValue": "0x0000010002", + "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) have any response type.", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", - "MSRValue": "0x01003C0002", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", - "MSRValue": "0x04003C0002", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", - "MSRValue": "0x10003C0002", + "BriefDescription": "All retired load instructions.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x81" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", - "MSRValue": "0x3F803C0002", + "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", - "MSRValue": "0x0000010004", + "BriefDescription": "Demand Data Read requests", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0xe1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", - "MSRValue": "0x01003C0004", + "BriefDescription": "All L2 requests", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "All L2 requests.", + "SampleAfterValue": "200003", + "UMask": "0xff" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", - "MSRValue": "0x04003C0004", + "BriefDescription": "Cycles with L1D load Misses outstanding.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", - "MSRValue": "0x10003C0004", + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", - "MSRValue": "0x3F803C0004", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", - "MSRValue": "0x0000010010", + "BriefDescription": "Number of cache line split locks sent to uncore.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF4", + "EventName": "SQ_MISC.SPLIT_LOCK", + "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x10" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", - "MSRValue": "0x01003C0010", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", - "MSRValue": "0x04003C0010", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", - "MSRValue": "0x10003C0010", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0xc4" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", - "MSRValue": "0x3F803C0010", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", - "MSRValue": "0x0000010020", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", - "MSRValue": "0x01003C0020", + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", - "MSRValue": "0x04003C0020", + "BriefDescription": "RFO requests that hit L2 cache", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc2" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", - "MSRValue": "0x10003C0020", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", - "MSRValue": "0x3F803C0020", + "BriefDescription": "L1D miss outstandings duration in cycles", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", - "MSRValue": "0x0000010080", + "BriefDescription": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", - "MSRValue": "0x01003C0080", + "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", + "SampleAfterValue": "200003", + "UMask": "0xc1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", - "MSRValue": "0x04003C0080", + "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", + "SampleAfterValue": "20011", + "UMask": "0x4" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", - "MSRValue": "0x10003C0080", + "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", - "MSRValue": "0x3F803C0080", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", - "MSRValue": "0x0000010100", + "BriefDescription": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", - "MSRValue": "0x01003C0100", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", - "MSRValue": "0x04003C0100", + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x42" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", - "MSRValue": "0x10003C0100", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", - "MSRValue": "0x3F803C0100", + "BriefDescription": "Any memory transaction that reached the SQ.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x80" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.", - "MSRValue": "0x0000010400", + "BriefDescription": "Cacheable and noncachaeble code read requests", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", - "MSRValue": "0x01003C0400", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", - "MSRValue": "0x04003C0400", + "BriefDescription": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", - "MSRValue": "0x10003C0400", + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", - "MSRValue": "0x3F803C0400", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD have any response type.", - "MSRValue": "0x0000010490", + "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x01003C0490", + "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x04003C0490", + "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x10003C0490", + "BriefDescription": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x3F803C0490", + "BriefDescription": "Counts all demand code reads that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD have any response type.", - "MSRValue": "0x0000010120", + "BriefDescription": "Counts prefetch RFOs that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x01003C0120", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x04003C0120", + "BriefDescription": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x10003C0120", + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x3F803C0120", + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD have any response type.", - "MSRValue": "0x0000010491", + "BriefDescription": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x01003C0491", + "BriefDescription": "Retired load instructions with locked access.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x21" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x04003C0491", + "BriefDescription": "Demand and prefetch data reads", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x10003C0491", + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "SampleAfterValue": "100007", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x3F803C0491", + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD have any response type.", - "MSRValue": "0x0000010122", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x01003C0122", + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x41" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x04003C0122", + "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB2", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x10003C0122", + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x3F803C0122", + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads", - "MSRValue": "0x08007C0001", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs)", - "MSRValue": "0x08007C0002", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "MSRValue": "0x08007C0004", + "BriefDescription": "Counts prefetch RFOs that have any response type.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads", - "MSRValue": "0x08007C0010", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs", - "MSRValue": "0x08007C0020", + "BriefDescription": "Retired store instructions that miss the STLB.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x12" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads", - "MSRValue": "0x08007C0080", + "BriefDescription": "RFO requests to L2 cache", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "SampleAfterValue": "200003", + "UMask": "0xe2" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs", - "MSRValue": "0x08007C0100", + "BriefDescription": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests", - "MSRValue": "0x08007C0400", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD", - "MSRValue": "0x08007C0490", + "BriefDescription": "Retired load instructions missed L2 cache as data sources", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PEBS": "1", + "PublicDescription": "Retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "50021", + "UMask": "0x10" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD", - "MSRValue": "0x08007C0120", + "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD", - "MSRValue": "0x08007C0491", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD", - "MSRValue": "0x08007C0122", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "PublicDescription": "TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json index c5d0babe89fce..e197cde15047d 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json @@ -1,85 +1,85 @@ [ { - "EventCode": "0xC7", - "UMask": "0x1", - "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT14 RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0xC7", - "UMask": "0x2", - "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.", "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0xC7", - "UMask": "0x4", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xC7", - "UMask": "0x8", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0xC7", - "UMask": "0x10", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 16 calculations per element.", "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x80" }, { - "EventCode": "0xC7", - "UMask": "0x20", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0xC7", - "UMask": "0x40", - "BriefDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8)", + "BriefDescription": "Cycles with any input/output SSE or FP assist", "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.ANY", + "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", + "SampleAfterValue": "100003", + "UMask": "0x1e" }, { - "EventCode": "0xC7", - "UMask": "0x80", - "BriefDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16)", + "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xCA", - "UMask": "0x1e", - "BriefDescription": "Cycles with any input/output SSE or FP assist", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "EventName": "FP_ASSIST.ANY", - "CounterMask": "1", - "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "UMask": "0x8" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json index 4dc583cfb5459..cdf95bd2a73d0 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json @@ -1,482 +1,516 @@ [ { - "EventCode": "0x79", - "UMask": "0x4", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", "Counter": "0,1,2,3", - "EventName": "IDQ.MITE_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE_16B.IFDATA_STALL", + "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0x79", - "UMask": "0x4", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", "Counter": "0,1,2,3", - "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x408006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x79", - "UMask": "0x8", "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "EventName": "IDQ.DSB_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES", "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0x79", - "UMask": "0x8", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x79", - "UMask": "0x10", - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_DSB_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xE6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x79", - "UMask": "0x18", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", - "CounterMask": "1", - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0x79", - "UMask": "0x18", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "4", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x79", - "UMask": "0x20", - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_MITE_UOPS", - "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x401006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0x79", - "UMask": "0x24", - "BriefDescription": "Cycles MITE is delivering any Uop", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", - "CounterMask": "1", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0x79", - "UMask": "0x24", - "BriefDescription": "Cycles MITE is delivering 4 Uops", + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", "Counter": "0,1,2,3", - "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", - "CounterMask": "4", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x79", - "UMask": "0x30", "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES", "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x30" }, { - "EventCode": "0x79", - "UMask": "0x30", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles MITE is delivering any Uop", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x24" + }, + { + "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1" }, { - "EdgeDetect": "1", - "EventCode": "0x79", - "UMask": "0x30", "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_SWITCHES", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x30" }, { - "EventCode": "0x80", - "UMask": "0x4", - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", "Counter": "0,1,2,3", - "EventName": "ICACHE_16B.IFDATA_STALL", - "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0x83", - "UMask": "0x1", - "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "EventName": "ICACHE_64B.IFTAG_HIT", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "EventCode": "0x83", - "UMask": "0x2", - "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "EventName": "ICACHE_64B.IFTAG_MISS", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x404006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0x83", - "UMask": "0x4", - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", "Counter": "0,1,2,3", - "EventName": "ICACHE_64B.IFTAG_STALL", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "Invert": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x9C", - "UMask": "0x1", - "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", - "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", - "CounterMask": "1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x9C", - "UMask": "0x1", - "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", - "CounterMask": "1", - "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0x9C", - "UMask": "0x1", - "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", - "CounterMask": "2", - "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_STALL", + "SampleAfterValue": "200003", + "UMask": "0x4" }, { - "EventCode": "0x9C", - "UMask": "0x1", - "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", - "CounterMask": "3", - "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0x9C", - "UMask": "0x1", - "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "CounterMask": "4", - "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x18" }, { - "EventCode": "0x9C", - "UMask": "0x1", - "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", "Counter": "0,1,2,3", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xAB", - "UMask": "0x2", - "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x400406", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", - "TakenAlone": "1", + "MSRValue": "0x420006", + "PEBS": "1", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x200206", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", + "MSRValue": "0x400806", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", + "Counter": "0,1,2,3,4,5,6,7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x400106", + "PEBS": "2", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x400206", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", - "TakenAlone": "1", + "MSRValue": "0x400206", + "PEBS": "1", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.", - "PEBS": "1", - "MSRValue": "0x15", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.STLB_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", - "TakenAlone": "1", + "MSRValue": "0x400406", + "PEBS": "1", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.", - "PEBS": "1", - "MSRValue": "0x14", + "BriefDescription": "Cycles MITE is delivering 4 Uops", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.ITLB_MISS", - "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", - "TakenAlone": "1", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x24" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.", - "PEBS": "1", - "MSRValue": "0x13", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.L2_MISS", - "MSRIndex": "0x3F7", - "TakenAlone": "1", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_CYCLES", + "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.", - "PEBS": "1", - "MSRValue": "0x12", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.L1I_MISS", - "MSRIndex": "0x3F7", - "TakenAlone": "1", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "SampleAfterValue": "2000003", + "UMask": "0x30" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.", - "PEBS": "1", - "MSRValue": "0x11", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.DSB_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", - "TakenAlone": "1", + "MSRValue": "0x410006", + "PEBS": "1", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x200206", "PEBS": "1", - "MSRValue": "0x300206", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", "MSRIndex": "0x3F7", - "TakenAlone": "1", + "MSRValue": "0x300206", + "PEBS": "1", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x100206", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", - "TakenAlone": "1", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x420006", - "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", - "MSRIndex": "0x3F7", "TakenAlone": "1", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x410006", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", - "MSRIndex": "0x3F7", - "TakenAlone": "1", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x18" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x408006", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", - "MSRIndex": "0x3F7", - "TakenAlone": "1", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.COUNT", + "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x404006", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", - "TakenAlone": "1", + "MSRValue": "0x402006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x402006", + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", - "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", - "TakenAlone": "1", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.", - "PEBS": "1", - "MSRValue": "0x401006", + "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", - "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", - "TakenAlone": "1", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_MISS", + "SampleAfterValue": "200003", + "UMask": "0x2" }, { - "EventCode": "0xC6", - "UMask": "0x1", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", - "PEBS": "1", - "MSRValue": "0x400806", + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", "Counter": "0,1,2,3", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", - "TakenAlone": "1", + "MSRValue": "0x12", + "PEBS": "1", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json index 48a9cdf81307c..6c3fd89d204dd 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/memory.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json @@ -1,1396 +1,1403 @@ [ { - "EventCode": "0x54", - "UMask": "0x1", - "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "TX_MEM.ABORT_CONFLICT", - "PublicDescription": "Number of times a TSX line had a cache conflict.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x54", - "UMask": "0x2", - "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", + "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "TX_MEM.ABORT_CAPACITY", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x54", - "UMask": "0x4", - "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", + "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", - "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x54", - "UMask": "0x8", - "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", - "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x54", - "UMask": "0x10", - "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", - "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x54", - "UMask": "0x20", - "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", - "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x54", - "UMask": "0x40", - "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", + "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", "Counter": "0,1,2,3", - "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", - "PublicDescription": "Number of times we could not allocate Lock Buffer.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_TIMER", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x5d", - "UMask": "0x1", - "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "TX_EXEC.MISC1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x5d", - "UMask": "0x2", - "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", "Counter": "0,1,2,3", - "EventName": "TX_EXEC.MISC2", - "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0x5d", - "UMask": "0x4", - "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "TX_EXEC.MISC3", - "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x5d", - "UMask": "0x8", - "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", "Counter": "0,1,2,3", - "EventName": "TX_EXEC.MISC4", - "PublicDescription": "RTM region detected inside HLE.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0x5d", - "UMask": "0x10", - "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", + "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "TX_EXEC.MISC5", - "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", - "UMask": "0x10", - "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", - "UMask": "0x10", - "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", + "BriefDescription": "Counts all prefetch data reads that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", - "CounterMask": "6", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", - "UMask": "0x10", - "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xA3", - "UMask": "0x2", - "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", - "CounterMask": "2", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xA3", - "UMask": "0x6", - "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", - "CounterMask": "6", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xB0", - "UMask": "0x10", - "BriefDescription": "Demand Data Read requests who miss L3 cache", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Demand Data Read requests who miss L3 cache.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xC3", - "UMask": "0x2", - "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "Errata": "SKL089", - "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xC8", - "UMask": "0x1", - "BriefDescription": "Number of times an HLE execution started.", + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "HLE_RETIRED.START", - "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC8", - "UMask": "0x2", - "BriefDescription": "Number of times an HLE execution successfully committed", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", "Counter": "0,1,2,3", - "EventName": "HLE_RETIRED.COMMIT", - "PublicDescription": "Number of times HLE commit succeeded.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC8", - "UMask": "0x4", - "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", - "PEBS": "1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "HLE_RETIRED.ABORTED", - "PublicDescription": "Number of times HLE abort was triggered. (PEBS)", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC8", - "UMask": "0x8", - "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "HLE_RETIRED.ABORTED_MEM", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC8", - "UMask": "0x10", - "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "HLE_RETIRED.ABORTED_TIMER", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC8", - "UMask": "0x20", - "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", + "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", "Counter": "0,1,2,3", - "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", - "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", + "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0xC8", - "UMask": "0x40", - "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", "Counter": "0,1,2,3", - "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Number of times a TSX line had a cache conflict.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xC8", - "UMask": "0x80", - "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "HLE_RETIRED.ABORTED_EVENTS", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC9", - "UMask": "0x1", - "BriefDescription": "Number of times an RTM execution started.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", "Counter": "0,1,2,3", - "EventName": "RTM_RETIRED.START", - "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC9", - "UMask": "0x2", - "BriefDescription": "Number of times an RTM execution successfully committed", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "RTM_RETIRED.COMMIT", - "PublicDescription": "Number of times RTM commit succeeded.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC9", - "UMask": "0x4", - "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", - "PEBS": "1", + "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", "Counter": "0,1,2,3", - "EventName": "RTM_RETIRED.ABORTED", - "PublicDescription": "Number of times RTM abort was triggered. (PEBS)", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEM", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xC9", - "UMask": "0x8", - "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", + "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", "Counter": "0,1,2,3", - "EventName": "RTM_RETIRED.ABORTED_MEM", - "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", + "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xC9", - "UMask": "0x10", - "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "RTM_RETIRED.ABORTED_TIMER", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC9", - "UMask": "0x20", - "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", + "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", "Counter": "0,1,2,3", - "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC5", + "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0xC9", - "UMask": "0x40", - "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", + "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", "Counter": "0,1,2,3", - "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC4", + "PublicDescription": "RTM region detected inside HLE.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xC9", - "UMask": "0x80", - "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", "Counter": "0,1,2,3", - "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC3", + "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0xCD", - "UMask": "0x1", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", - "PEBS": "2", - "MSRValue": "0x200", + "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", - "MSRIndex": "0x3F6", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", - "TakenAlone": "1", - "SampleAfterValue": "101", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC2", + "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0xCD", - "UMask": "0x1", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", - "PEBS": "2", - "MSRValue": "0x100", + "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", - "MSRIndex": "0x3F6", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", - "TakenAlone": "1", - "SampleAfterValue": "503", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC1", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0xCD", - "UMask": "0x1", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", - "PEBS": "2", - "MSRValue": "0x80", + "BriefDescription": "Number of times an RTM execution successfully committed", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", - "MSRIndex": "0x3F6", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", - "TakenAlone": "1", - "SampleAfterValue": "1009", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Number of times RTM commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0xCD", - "UMask": "0x1", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", - "PEBS": "2", - "MSRValue": "0x40", + "BriefDescription": "Counts prefetch RFOs that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", - "MSRIndex": "0x3F6", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", - "TakenAlone": "1", - "SampleAfterValue": "2003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xCD", - "UMask": "0x1", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", - "PEBS": "2", - "MSRValue": "0x20", + "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", - "MSRIndex": "0x3F6", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", - "TakenAlone": "1", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "EventCode": "0xCD", - "UMask": "0x1", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", - "PEBS": "2", - "MSRValue": "0x10", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", - "MSRIndex": "0x3F6", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", - "TakenAlone": "1", - "SampleAfterValue": "20011", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xCD", - "UMask": "0x1", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", - "PEBS": "2", - "MSRValue": "0x8", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", - "MSRIndex": "0x3F6", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", - "TakenAlone": "1", - "SampleAfterValue": "50021", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xCD", - "UMask": "0x1", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", - "PEBS": "2", - "MSRValue": "0x4", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", - "MSRIndex": "0x3F6", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", - "TakenAlone": "1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD TBD", - "MSRValue": "0x3FBC000001", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD", - "MSRValue": "0x083FC00001", + "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD", - "MSRValue": "0x103FC00001", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD", - "MSRValue": "0x063FC00001", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD", - "MSRValue": "0x063B800001", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand data reads TBD", - "MSRValue": "0x0604000001", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD", - "MSRValue": "0x3FBC000002", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD", - "MSRValue": "0x083FC00002", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD", - "MSRValue": "0x103FC00002", + "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD", - "MSRValue": "0x063FC00002", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD", - "MSRValue": "0x063B800002", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all demand data writes (RFOs) TBD", - "MSRValue": "0x0604000002", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all demand data writes (RFOs) TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", - "MSRValue": "0x3FBC000004", + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", - "MSRValue": "0x083FC00004", + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", - "MSRValue": "0x103FC00004", + "BriefDescription": "Number of times an HLE execution successfully committed", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.COMMIT", + "PublicDescription": "Number of times HLE commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", - "MSRValue": "0x063FC00004", + "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", + "PublicDescription": "Number of times we could not allocate Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", - "MSRValue": "0x063B800004", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", - "MSRValue": "0x0604000004", + "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", - "MSRValue": "0x3FBC000010", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", - "MSRValue": "0x083FC00010", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", - "MSRValue": "0x103FC00010", + "BriefDescription": "Demand Data Read requests who miss L3 cache", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Demand Data Read requests who miss L3 cache.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x10" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", - "MSRValue": "0x063FC00010", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", - "MSRValue": "0x063B800010", + "BriefDescription": "Counts demand data reads that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD", - "MSRValue": "0x0604000010", + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", - "MSRValue": "0x3FBC000020", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", - "MSRValue": "0x083FC00020", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", - "MSRValue": "0x103FC00020", + "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", - "MSRValue": "0x063FC00020", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", - "MSRValue": "0x063B800020", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "TakenAlone": "1", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", - "MSRValue": "0x0604000020", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", - "MSRValue": "0x3FBC000080", + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", - "MSRValue": "0x083FC00080", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", - "MSRValue": "0x103FC00080", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", - "MSRValue": "0x063FC00080", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", - "MSRValue": "0x063B800080", + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times RTM abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", - "MSRValue": "0x0604000080", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", - "MSRValue": "0x3FBC000100", + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times HLE abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", - "MSRValue": "0x083FC00100", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "TakenAlone": "1", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", - "MSRValue": "0x103FC00100", + "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", + "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", - "MSRValue": "0x063FC00100", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", - "MSRValue": "0x063B800100", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", - "MSRValue": "0x0604000100", + "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", - "MSRValue": "0x3FBC000400", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", - "MSRValue": "0x083FC00400", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "TakenAlone": "1", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", - "MSRValue": "0x103FC00400", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", - "MSRValue": "0x063FC00400", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", - "MSRValue": "0x063B800400", + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", - "MSRValue": "0x0604000400", + "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x3FBC000490", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x083FC00490", + "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x103FC00490", + "BriefDescription": "Number of times an RTM execution started.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x063FC00490", + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL089", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x063B800490", + "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", + "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x0604000490", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x3FBC000120", + "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x083FC00120", + "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x103FC00120", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x063FC00120", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x063B800120", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x0604000120", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "SampleAfterValue": "2000003", + "UMask": "0x80" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x3FBC000491", + "BriefDescription": "Number of times an HLE execution started.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.START", + "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x083FC00491", + "BriefDescription": "Counts all demand code reads that miss in the L3.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x103FC00491", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "TakenAlone": "1", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x063FC00491", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x063B800491", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x0604000491", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD TBD", - "MSRValue": "0x3FBC000122", + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x6" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x083FC00122", + "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "SampleAfterValue": "2000003", + "UMask": "0x80" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x103FC00122", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x063FC00122", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x063B800122", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "TakenAlone": "1", + "UMask": "0x1" }, { - "Offcore": "1", - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "TBD TBD", - "MSRValue": "0x0604000122", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "PublicDescription": "TBD TBD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json index 778a541463eb6..f6b147ba8ef64 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/other.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json @@ -1,164 +1,116 @@ [ { - "EventCode": "0x28", - "UMask": "0x7", - "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.", + "BriefDescription": "Core cycles the core was throttled due to a pending power level request.", "Counter": "0,1,2,3", - "EventName": "CORE_POWER.LVL0_TURBO_LICENSE", - "PublicDescription": "Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x28", - "UMask": "0x18", - "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.", - "Counter": "0,1,2,3", - "EventName": "CORE_POWER.LVL1_TURBO_LICENSE", - "PublicDescription": "Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.", + "EventName": "CORE_POWER.THROTTLE", + "PublicDescription": "Core cycles the out-of-order engine was throttled due to a pending power level request.", "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0x28", - "UMask": "0x20", - "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", + "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", "Counter": "0,1,2,3", - "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", - "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture). This includes high current AVX 512-bit instructions.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xFE", + "EventName": "IDI_MISC.WB_DOWNGRADE", + "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "EventCode": "0x28", - "UMask": "0x40", - "BriefDescription": "Core cycles the core was throttled due to a pending power level request.", + "BriefDescription": "Number of PREFETCHW instructions executed.", "Counter": "0,1,2,3", - "EventName": "CORE_POWER.THROTTLE", - "PublicDescription": "Core cycles the out-of-order engine was throttled due to a pending power level request.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x32", - "UMask": "0x1", - "BriefDescription": "Number of PREFETCHNTA instructions executed.", - "Counter": "0,1,2,3", - "EventName": "SW_PREFETCH_ACCESS.NTA", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0x32", - "UMask": "0x2", - "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.", "Counter": "0,1,2,3", - "EventName": "SW_PREFETCH_ACCESS.T0", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL0_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.", + "SampleAfterValue": "200003", + "UMask": "0x7" }, { - "EventCode": "0x32", - "UMask": "0x4", - "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.", "Counter": "0,1,2,3", - "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL1_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "UMask": "0x18" }, { - "EventCode": "0x32", - "UMask": "0x8", - "BriefDescription": "Number of PREFETCHW instructions executed.", + "BriefDescription": "Number of PREFETCHT0 instructions executed.", "Counter": "0,1,2,3", - "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T0", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xCB", - "UMask": "0x1", "BriefDescription": "Number of hardware interrupts received by the processor.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCB", "EventName": "HW_INTERRUPTS.RECEIVED", "PublicDescription": "Counts the number of hardware interruptions received by the processor.", "SampleAfterValue": "203", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xEF", - "UMask": "0x1", - "Counter": "0,1,2,3", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xEF", - "UMask": "0x2", - "Counter": "0,1,2,3", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xEF", - "UMask": "0x4", - "Counter": "0,1,2,3", - "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xEF", - "UMask": "0x8", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", "Counter": "0,1,2,3", - "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture). This includes high current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "UMask": "0x20" }, { - "EventCode": "0xEF", - "UMask": "0x10", + "BriefDescription": "Number of PREFETCHNTA instructions executed.", "Counter": "0,1,2,3", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.NTA", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xEF", - "UMask": "0x20", + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", "Counter": "0,1,2,3", - "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0xEF", - "UMask": "0x40", "Counter": "0,1,2,3", - "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x09", + "EventName": "MEMORY_DISAMBIGUATION.HISTORY_RESET", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xFE", - "UMask": "0x2", "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xFE", "EventName": "IDI_MISC.WB_UPGRADE", "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xFE", - "UMask": "0x4", - "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", - "Counter": "0,1,2,3", - "EventName": "IDI_MISC.WB_DOWNGRADE", - "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json index 369f56c1d1b5a..3bfc6943ddf99 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json @@ -1,967 +1,959 @@ [ { - "UMask": "0x1", - "BriefDescription": "Instructions retired from execution.", - "Counter": "Fixed counter 0", - "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 0" - }, - { - "UMask": "0x2", - "BriefDescription": "Core cycles when the thread is not in halt state", - "Counter": "Fixed counter 1", - "EventName": "CPU_CLK_UNHALTED.THREAD", - "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", - "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 1" - }, - { - "UMask": "0x2", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "Counter": "Fixed counter 1", - "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 1" + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.ANY_P", + "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", + "SampleAfterValue": "2000003" }, { - "UMask": "0x3", - "BriefDescription": "Reference cycles when the core is not in halt state.", - "Counter": "Fixed counter 2", - "EventName": "CPU_CLK_UNHALTED.REF_TSC", - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 2" + "UMask": "0x1" }, { - "EventCode": "0x03", - "UMask": "0x2", - "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .", + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "EventCode": "0x03", - "UMask": "0x8", - "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", "Counter": "0,1,2,3", - "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x14", + "EventName": "ARITH.DIVIDER_ACTIVE", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0x07", - "UMask": "0x1", "BriefDescription": "False dependencies in MOB due to partial compare on address.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x07", "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x0D", - "UMask": "0x1", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", + "BriefDescription": "Far branch instructions retired.", "Counter": "0,1,2,3", - "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PEBS": "1", + "PublicDescription": "This event counts far branch instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x40" }, { - "EventCode": "0x0D", - "UMask": "0x1", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", + "BriefDescription": "Counts the number of x87 uops dispatched.", "Counter": "0,1,2,3", - "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", - "AnyThread": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x0D", - "UMask": "0x80", - "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", + "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", "Counter": "0,1,2,3", - "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4C", + "EventName": "LOAD_HIT_PRE.SW_PF", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "Invert": "1", - "EventCode": "0x0E", - "UMask": "0x1", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", + "BriefDescription": "Mispredicted direct and indirect near call instructions retired.", "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.STALL_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.", + "SampleAfterValue": "400009", + "UMask": "0x2" }, { - "EventCode": "0x0E", - "UMask": "0x1", - "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", + "BriefDescription": "Total execution stalls.", "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0x0E", - "UMask": "0x2", - "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", - "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "5", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x5" }, { - "EventCode": "0x0E", - "UMask": "0x20", "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", "EventName": "UOPS_ISSUED.SLOW_LEA", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0x14", - "UMask": "0x1", - "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "BriefDescription": "Cycles with less than 10 actually retired uops.", "Counter": "0,1,2,3", - "EventName": "ARITH.DIVIDER_ACTIVE", - "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "10", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "Invert": "1", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0x3C", - "UMask": "0x0", "BriefDescription": "Thread cycles when thread is not in halt state", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", "EventName": "CPU_CLK_UNHALTED.THREAD_P", "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "SampleAfterValue": "2000003" }, { - "EventCode": "0x3C", - "UMask": "0x0", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", - "AnyThread": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EdgeDetect": "1", - "EventCode": "0x3C", - "UMask": "0x0", - "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", - "CounterMask": "1", - "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x3C", - "UMask": "0x1", "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", - "SampleAfterValue": "2503", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0x3C", - "UMask": "0x1", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", + "BriefDescription": "Number of machine clears (nukes) of any type.", "Counter": "0,1,2,3", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "AnyThread": "1", - "SampleAfterValue": "2503", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.COUNT", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x3C", - "UMask": "0x1", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", "AnyThread": "1", - "SampleAfterValue": "2503", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0x3C", - "UMask": "0x1", - "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", - "SampleAfterValue": "2503", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Number of uops to be executed per-thread each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0x3C", - "UMask": "0x2", - "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x3C", - "UMask": "0x2", - "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "2503", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0x4C", - "UMask": "0x1", - "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", + "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", "Counter": "0,1,2,3", - "EventName": "LOAD_HIT_PRE.SW_PF", - "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "EventCode": "0x59", - "UMask": "0x1", - "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", - "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "8", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EdgeDetect": "1", - "Invert": "1", - "EventCode": "0x5E", - "UMask": "0x1", - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", - "EventName": "RS_EVENTS.EMPTY_END", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x5E", - "UMask": "0x1", - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", "Counter": "0,1,2,3", - "EventName": "RS_EVENTS.EMPTY_CYCLES", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x87", - "UMask": "0x1", - "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", - "EventName": "ILD_STALL.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0xA1", - "UMask": "0x1", "BriefDescription": "Cycles per thread when uops are executed in port 0", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_0", "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA1", - "UMask": "0x2", "BriefDescription": "Cycles per thread when uops are executed in port 1", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_1", "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xA1", - "UMask": "0x4", "BriefDescription": "Cycles per thread when uops are executed in port 2", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_2", "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0xA1", - "UMask": "0x8", "BriefDescription": "Cycles per thread when uops are executed in port 3", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_3", "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xA1", - "UMask": "0x10", "BriefDescription": "Cycles per thread when uops are executed in port 4", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_4", "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0xA1", - "UMask": "0x20", "BriefDescription": "Cycles per thread when uops are executed in port 5", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_5", "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0xA1", - "UMask": "0x40", "BriefDescription": "Cycles per thread when uops are executed in port 6", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_6", "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0xA1", - "UMask": "0x80", "BriefDescription": "Cycles per thread when uops are executed in port 7", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_7", "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x80" }, { - "EventCode": "0xa2", - "UMask": "0x1", - "BriefDescription": "Resource-related stall cycles", + "AnyThread": "1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", "Counter": "0,1,2,3", - "EventName": "RESOURCE_STALLS.ANY", - "PublicDescription": "Counts resource-related stall cycles.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA2", - "UMask": "0x8", - "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", - "Counter": "0,1,2,3", - "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "Counter": "1", + "CounterHTOff": "1", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.PREC_DIST", + "PEBS": "2", + "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", - "UMask": "0x1", - "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", - "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_4_UOPS", + "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", - "UMask": "0x4", - "BriefDescription": "Total execution stalls.", + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", - "CounterMask": "4", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xA3", - "UMask": "0x5", - "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "CounterMask": "5", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x2" }, { - "EventCode": "0xA3", - "UMask": "0x8", - "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", - "CounterMask": "8", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_END", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", - "UMask": "0xc", - "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", - "CounterMask": "12", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0xA3", - "UMask": "0x10", - "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", - "CounterMask": "16", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x59", + "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", - "UMask": "0x14", - "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", - "CounterMask": "20", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "EventCode": "0xA6", - "UMask": "0x1", - "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", + "BriefDescription": "Not taken branch instructions retired.", "Counter": "0,1,2,3", - "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" }, { - "EventCode": "0xA6", - "UMask": "0x2", - "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xA6", - "UMask": "0x4", - "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xA6", - "UMask": "0x8", - "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xA6", - "UMask": "0x10", - "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", - "Counter": "0,1,2,3", - "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 2", + "CounterHTOff": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x3" }, { - "EventCode": "0xA6", - "UMask": "0x40", - "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", + "BriefDescription": "All mispredicted macro branch instructions retired.", "Counter": "0,1,2,3", - "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.ANY", + "SampleAfterValue": "100003", + "UMask": "0x3f" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xA8", - "UMask": "0x1", "BriefDescription": "Number of Uops delivered by the LSD.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA8", "EventName": "LSD.UOPS", "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA8", - "UMask": "0x1", - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", "Counter": "0,1,2,3", - "EventName": "LSD.CYCLES_4_UOPS", - "CounterMask": "4", - "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" }, { - "EventCode": "0xA8", - "UMask": "0x1", - "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "Counter": "0,1,2,3", - "EventName": "LSD.CYCLES_ACTIVE", - "CounterMask": "1", - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x87", + "EventName": "ILD_STALL.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", - "CounterMask": "4", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "16", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "BriefDescription": "Taken branch instructions retired.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", - "CounterMask": "3", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "This event counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20" }, { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", - "CounterMask": "2", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x8" }, { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", - "CounterMask": "1", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "Invert": "1", - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.STALL_CYCLES", - "CounterMask": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "BriefDescription": "Core cycles when the thread is not in halt state", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.THREAD", - "PublicDescription": "Number of uops to be executed per-thread each cycle.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0xB1", - "UMask": "0x2", - "BriefDescription": "Number of uops executed on the core.", + "BriefDescription": "Direct and indirect near call instructions retired.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Number of uops executed from any thread.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "This event counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2" }, { - "Invert": "1", - "EventCode": "0xB1", - "UMask": "0x2", - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", - "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.PAUSE_INST", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0xB1", - "UMask": "0x2", - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "BriefDescription": "Resource-related stall cycles", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "CounterMask": "4", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.ANY", + "PublicDescription": "Counts resource-related stall cycles.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xB1", - "UMask": "0x2", - "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "BriefDescription": "Self-modifying code (SMC) detected.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "CounterMask": "3", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "EventCode": "0xB1", - "UMask": "0x2", - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "CounterMask": "2", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" }, { - "EventCode": "0xB1", - "UMask": "0x2", - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xB1", - "UMask": "0x10", - "BriefDescription": "Counts the number of x87 uops dispatched.", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x20" }, { - "EventCode": "0xC0", - "UMask": "0x0", - "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", "Counter": "0,1,2,3", - "EventName": "INST_RETIRED.ANY_P", - "Errata": "SKL091, SKL044", - "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", + "CounterHTOff": "0,1,2,3", + "CounterMask": "20", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x14" }, { - "EventCode": "0xC0", - "UMask": "0x1", - "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", - "PEBS": "2", - "Counter": "1", - "EventName": "INST_RETIRED.PREC_DIST", - "Errata": "SKL091, SKL044", - "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.", + "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", - "CounterHTOff": "1" + "UMask": "0x1" }, { - "Invert": "1", - "EventCode": "0xC0", - "UMask": "0x1", "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", - "PEBS": "2", "Counter": "0,2,3", - "EventName": "INST_RETIRED.TOTAL_CYCLES_PS", + "CounterHTOff": "0,2,3", "CounterMask": "10", "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.TOTAL_CYCLES_PS", + "Invert": "1", + "PEBS": "2", "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", "SampleAfterValue": "2000003", - "CounterHTOff": "0,2,3" + "UMask": "0x1" }, { - "EventCode": "0xC1", - "UMask": "0x3f", - "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", + "BriefDescription": "Retirement slots used.", "Counter": "0,1,2,3", - "EventName": "OTHER_ASSISTS.ANY", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "Counts the retirement slots used.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "Invert": "1", - "EventCode": "0xC2", - "UMask": "0x2", - "BriefDescription": "Cycles with less than 10 actually retired uops.", + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.TOTAL_CYCLES", - "CounterMask": "10", - "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "SampleAfterValue": "2000003" }, { - "Invert": "1", - "EventCode": "0xC2", - "UMask": "0x2", - "BriefDescription": "Cycles without actually retired uops.", + "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.STALL_CYCLES", - "CounterMask": "1", - "PublicDescription": "This event counts cycles without actually retired uops.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xC2", - "UMask": "0x2", - "BriefDescription": "Retirement slots used.", + "BriefDescription": "Increments whenever there is an update to the LBR array.", "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "PublicDescription": "Counts the retirement slots used.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EdgeDetect": "1", - "EventCode": "0xC3", - "UMask": "0x1", - "BriefDescription": "Number of machine clears (nukes) of any type.", + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", "Counter": "0,1,2,3", - "EventName": "MACHINE_CLEARS.COUNT", - "CounterMask": "1", - "PublicDescription": "Number of machine clears (nukes) of any type.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0xC3", - "UMask": "0x4", - "BriefDescription": "Self-modifying code (SMC) detected.", + "BriefDescription": "Return instructions retired.", "Counter": "0,1,2,3", - "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "PublicDescription": "This event counts return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8" }, { - "EventCode": "0xC4", - "UMask": "0x0", - "BriefDescription": "All (macro) branch instructions retired.", + "BriefDescription": "Instructions retired from execution.", + "Counter": "Fixed counter 0", + "CounterHTOff": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "Errata": "SKL091", - "PublicDescription": "Counts all (macro) branch instructions retired.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0xC4", - "UMask": "0x1", - "BriefDescription": "Conditional branch instructions retired.", - "PEBS": "1", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.CONDITIONAL", - "Errata": "SKL091", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "EventCode": "0xC4", - "UMask": "0x2", - "BriefDescription": "Direct and indirect near call instructions retired.", - "PEBS": "1", + "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.NEAR_CALL", - "Errata": "SKL091", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", + "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", + "SampleAfterValue": "100007" }, { - "EventCode": "0xC4", - "UMask": "0x4", "BriefDescription": "All (macro) branch instructions retired.", - "PEBS": "2", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "CounterHTOff": "0,1,2,3", "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3" + "UMask": "0x4" }, { - "EventCode": "0xC4", - "UMask": "0x8", - "BriefDescription": "Return instructions retired.", - "PEBS": "1", + "BriefDescription": "Mispredicted macro branch instructions retired.", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "Errata": "SKL091", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x4" }, { - "EventCode": "0xC4", - "UMask": "0x10", - "BriefDescription": "Counts all not taken macro branch instructions retired.", - "PEBS": "1", + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.NOT_TAKEN", - "Errata": "SKL091", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0xC4", - "UMask": "0x20", - "BriefDescription": "Taken branch instructions retired.", - "PEBS": "1", + "BriefDescription": "Not taken branch instructions retired.", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "CounterHTOff": "0,1,2,3,4,5,6,7", "Errata": "SKL091", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0xC4", - "UMask": "0x40", - "BriefDescription": "Counts the number of far branch instructions retired.", - "PEBS": "1", + "BriefDescription": "Conditional branch instructions retired.", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "CounterHTOff": "0,1,2,3,4,5,6,7", "Errata": "SKL091", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xC5", - "UMask": "0x0", - "BriefDescription": "All mispredicted macro branch instructions retired.", - "Counter": "0,1,2,3", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "This event counts conditional branch instructions retired.", "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xC5", - "UMask": "0x1", "BriefDescription": "Mispredicted conditional branch instructions retired.", - "PEBS": "1", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.CONDITIONAL", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.", + "PEBS": "1", + "PublicDescription": "This event counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xC5", - "UMask": "0x2", - "BriefDescription": "Mispredicted direct and indirect near call instructions retired.", - "PEBS": "1", + "BriefDescription": "Number of uops executed on the core.", "Counter": "0,1,2,3", - "EventName": "BR_MISP_RETIRED.NEAR_CALL", - "PublicDescription": "This event counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Number of uops executed from any thread.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0xC5", - "UMask": "0x4", - "BriefDescription": "Mispredicted macro branch instructions retired.", - "PEBS": "2", + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", - "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "12", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "SampleAfterValue": "2000003", + "UMask": "0xc" }, { - "EventCode": "0xC5", - "UMask": "0x20", - "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", - "PEBS": "1", + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "EventCode": "0xCC", - "UMask": "0x20", - "BriefDescription": "Increments whenever there is an update to the LBR array.", + "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", "Counter": "0,1,2,3", - "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x80" }, { - "EventCode": "0xCC", - "UMask": "0x40", - "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", + "BriefDescription": "All (macro) branch instructions retired.", "Counter": "0,1,2,3", - "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xE6", - "UMask": "0x1", - "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "EventName": "BACLEARS.ANY", - "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 390bdab1be9dc..0dd8b13b5cfb0 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -4,14 +4,14 @@ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", "MetricGroup": "TopdownL1", "MetricName": "Frontend_Bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound." + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound." }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", "MetricGroup": "TopdownL1_SMT", "MetricName": "Frontend_Bound_SMT", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU." }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", @@ -22,13 +22,14 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", "MetricGroup": "TopdownL1_SMT", "MetricName": "Bad_Speculation_SMT", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU." }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_NMI_WATCHDOG", "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", "MetricGroup": "TopdownL1", "MetricName": "Backend_Bound", @@ -36,7 +37,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )", "MetricGroup": "TopdownL1_SMT", "MetricName": "Backend_Bound_SMT", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU." @@ -50,7 +51,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", "MetricGroup": "TopdownL1_SMT", "MetricName": "Retiring_SMT", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU." @@ -58,7 +59,7 @@ { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopDownL1", + "MetricGroup": "Summary", "MetricName": "IPC" }, { @@ -74,24 +75,6 @@ "MetricName": "IpTB" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;PGO", - "MetricName": "BpTB" - }, - { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", - "MetricGroup": "PGO;IcMiss", - "MetricName": "IFetch_Line_Utilization" - }, - { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fetch_BW", - "MetricName": "DSB_Coverage" - }, - { "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", "MetricGroup": "Pipeline;Summary", @@ -104,86 +87,104 @@ "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", "MetricExpr": "4 * cycles", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", - "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "MetricGroup": "TopDownL1_SMT", "MetricName": "SLOTS_SMT" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurance rate)", + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "Instruction_Type", - "MetricName": "IpL" + "MetricName": "IpLoad" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurance rate)", + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "Instruction_Type", - "MetricName": "IpS" + "MetricName": "IpStore" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Instruction_Type", - "MetricName": "IpB" + "MetricName": "IpBranch" }, { - "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches", "MetricName": "IpCall" }, { + "BriefDescription": "Branch instructions per taken branch. ", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTkBranch" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )", + "MetricGroup": "FLOPS;FP_Arith;Instruction_Type", + "MetricName": "IpFLOP" + }, + { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary", + "MetricGroup": "Summary;TopDownL1", "MetricName": "Instructions" }, { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fetch_BW", + "MetricName": "DSB_Coverage" + }, + { "BriefDescription": "Instructions Per Cycle (per physical core)", "MetricExpr": "INST_RETIRED.ANY / cycles", - "MetricGroup": "SMT", + "MetricGroup": "SMT;TopDownL1", "MetricName": "CoreIPC" }, { "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", - "MetricGroup": "SMT", + "MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "SMT;TopDownL1", "MetricName": "CoreIPC_SMT" }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles", + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / cycles", "MetricGroup": "FLOPS", "MetricName": "FLOPc" }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "MetricGroup": "FLOPS_SMT", "MetricName": "FLOPc_SMT" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Pipeline", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 )", + "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", - "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "BrMispredicts", "MetricName": "Branch_Misprediction_Cost" }, { "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", - "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "BrMispredicts_SMT", "MetricName": "Branch_Misprediction_Cost_SMT" }, @@ -213,14 +214,14 @@ }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_NMI_WATCHDOG", "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", "MetricGroup": "TLB", - "MetricName": "Page_Walks_Utilization", - "MetricConstraint": "NO_NMI_WATCHDOG" + "MetricName": "Page_Walks_Utilization" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )", "MetricGroup": "TLB_SMT", "MetricName": "Page_Walks_Utilization_SMT" }, @@ -245,7 +246,7 @@ { "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", - "MetricGroup": "Memory_BW", + "MetricGroup": "Memory_BW;Offcore", "MetricName": "L3_Cache_Access_BW" }, { @@ -263,7 +264,7 @@ { "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "Cache_Misses", + "MetricGroup": "Cache_Misses;Offcore", "MetricName": "L2MPKI_All" }, { @@ -298,7 +299,7 @@ }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time", + "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" }, @@ -310,44 +311,56 @@ }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 )", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Summary", + "MetricGroup": "OS", "MetricName": "Kernel_Utilization" }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", - "MetricGroup": "Memory_BW", + "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time", + "MetricGroup": "Memory_BW;SoC", "MetricName": "DRAM_BW_Use" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1000000000 * ( cha@event\\=0x36\\,umask\\=0x21@ / cha@event\\=0x35\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )", - "MetricGroup": "Memory_Lat", - "MetricName": "DRAM_Read_Latency" + "MetricExpr": "1000000000 * ( cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433@ / cha@event\\=0x35\\,umask\\=0x21\\,config\\=0x40433@ ) / ( cha_0@event\\=0x0@ / duration_time )", + "MetricGroup": "Memory_Lat;SoC", + "MetricName": "MEM_Read_Latency" }, { "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "cha@event\\=0x36\\,umask\\=0x21@ / cha@event\\=0x36\\,umask\\=0x21\\,thresh\\=1@", - "MetricGroup": "Memory_BW", - "MetricName": "DRAM_Parallel_Reads" + "MetricExpr": "cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433@ / cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433\\,thresh\\=1@", + "MetricGroup": "Memory_BW;SoC", + "MetricName": "MEM_Parallel_Reads" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "( UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3 ) * 4 / 1000000000 / duration_time", + "MetricGroup": "IO_BW;SoC;Server", + "MetricName": "IO_Write_BW" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", + "MetricExpr": "( UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 ) * 4 / 1000000000 / duration_time", + "MetricGroup": "IO_BW;SoC;Server", + "MetricName": "IO_Read_BW" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "cha_0@event\\=0x0@", - "MetricGroup": "", + "MetricGroup": "SoC", "MetricName": "Socket_CLKS" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions. )", + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", "MetricExpr": "INST_RETIRED.ANY / ( BR_INST_RETIRED.FAR_BRANCH / 2 )", - "MetricGroup": "", + "MetricGroup": "Branches;OS", "MetricName": "IpFarBranch" }, { diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json index 9c7e5f8beee29..b80b5d66385db 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json @@ -94,17 +94,7 @@ "Unit": "iMC" }, { - "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", - "Counter": "0,1,2,3", - "EventCode": "0x4", - "EventName": "LLC_MISSES.MEM_READ", - "PerPkg": "1", - "ScaleUnit": "64Bytes", - "UMask": "0x3", - "Unit": "iMC" - }, - { - "BriefDescription": "All DRAM Read CAS Commands issued (does not include underfills) ", + "BriefDescription": "All DRAM Read CAS Commands issued (does not include underfills)", "Counter": "0,1,2,3", "EventCode": "0x4", "EventName": "UNC_M_CAS_COUNT.RD_REG", @@ -119,18 +109,18 @@ "EventCode": "0x4", "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL", "PerPkg": "1", - "PublicDescription": "Counts CAS (Column Access Select) underfill read commands issued to DRAM due to a partial write, on a per channel basis. CAS commands are issued to specify the address to read or write on DRAM, and this command counts underfill reads. Partial writes must be completed by first reading in the underfill from DRAM and then merging in the partial write data before writing the full line back to DRAM. This event will generally count about the same as the number of partial writes, but may be slightly less because of partials hitting in the WPQ (due to a previous write request). ", + "PublicDescription": "Counts CAS (Column Access Select) underfill read commands issued to DRAM due to a partial write, on a per channel basis. CAS commands are issued to specify the address to read or write on DRAM, and this command counts underfill reads. Partial writes must be completed by first reading in the underfill from DRAM and then merging in the partial write data before writing the full line back to DRAM. This event will generally count about the same as the number of partial writes, but may be slightly less because of partials hitting in the WPQ (due to a previous write request).", "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "BriefDescription": "DRAM CAS (Column Address Strobe) Commands.; DRAM WR_CAS (w/ and w/out auto-pre) in Write Major Mode", "Counter": "0,1,2,3", "EventCode": "0x4", - "EventName": "LLC_MISSES.MEM_WRITE", + "EventName": "UNC_M_CAS_COUNT.WR_WMM", "PerPkg": "1", - "ScaleUnit": "64Bytes", - "UMask": "0xC", + "PublicDescription": "Counts the total number or DRAM Write CAS commands issued on this channel while in Write-Major-Mode.", + "UMask": "0x4", "Unit": "iMC" }, { @@ -139,7 +129,7 @@ "EventCode": "0x10", "EventName": "UNC_M_RPQ_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of read requests allocated into the Read Pending Queue (RPQ). This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. The requests deallocate after the read CAS command has been issued to DRAM. This event counts both Isochronous and non-Isochronous requests which were issued to the RPQ. ", + "PublicDescription": "Counts the number of read requests allocated into the Read Pending Queue (RPQ). This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. The requests deallocate after the read CAS command has been issued to DRAM. This event counts both Isochronous and non-Isochronous requests which were issued to the RPQ.", "Unit": "iMC" }, { @@ -166,7 +156,7 @@ "EventCode": "0x81", "EventName": "UNC_M_WPQ_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests.", + "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happenning in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts???", "Unit": "iMC" } ] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json index adb42c72f5c89..d7a0270de9835 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json @@ -119,18 +119,15 @@ "EventName": "UPI_DATA_BANDWIDTH_TX", "PerPkg": "1", "ScaleUnit": "7.11E-06Bytes", - "UMask": "0x0F", + "UMask": "0xf", "Unit": "UPI LL" }, { - "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", + "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", "Counter": "0,1", "EventCode": "0x83", - "EventName": "LLC_MISSES.PCIE_READ", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", "FCMask": "0x07", - "Filter": "ch_mask=0x1f", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "MetricName": "LLC_MISSES.PCIE_READ", "PerPkg": "1", "PortMask": "0x01", "ScaleUnit": "4Bytes", @@ -138,118 +135,117 @@ "Unit": "IIO" }, { - "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", + "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", "Counter": "0,1", "EventCode": "0x83", - "EventName": "LLC_MISSES.PCIE_WRITE", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", "FCMask": "0x07", - "Filter": "ch_mask=0x1f", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "MetricName": "LLC_MISSES.PCIE_WRITE", "PerPkg": "1", - "PortMask": "0x01", + "PortMask": "0x02", "ScaleUnit": "4Bytes", - "UMask": "0x01", + "UMask": "0x04", "Unit": "IIO" }, { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", + "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", "Counter": "0,1", "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", "FCMask": "0x07", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "MetricName": "LLC_MISSES.PCIE_WRITE", "PerPkg": "1", - "PortMask": "0x01", + "PortMask": "0x04", "ScaleUnit": "4Bytes", - "UMask": "0x01", + "UMask": "0x04", "Unit": "IIO" }, { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", + "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", "Counter": "0,1", "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", "FCMask": "0x07", "PerPkg": "1", - "PortMask": "0x02", + "PortMask": "0x08", "ScaleUnit": "4Bytes", - "UMask": "0x01", + "UMask": "0x04", "Unit": "IIO" }, { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", + "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", "Counter": "0,1", "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "EventName": "LLC_MISSES.PCIE_READ", "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", "PerPkg": "1", - "PortMask": "0x04", + "PortMask": "0x01", "ScaleUnit": "4Bytes", - "UMask": "0x01", + "UMask": "0x04", "Unit": "IIO" }, { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", + "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", "Counter": "0,1", "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", "FCMask": "0x07", "PerPkg": "1", - "PortMask": "0x08", + "PortMask": "0x01", "ScaleUnit": "4Bytes", "UMask": "0x01", "Unit": "IIO" }, { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", + "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", "Counter": "0,1", "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", "FCMask": "0x07", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "MetricName": "LLC_MISSES.PCIE_READ", "PerPkg": "1", - "PortMask": "0x01", + "PortMask": "0x02", "ScaleUnit": "4Bytes", - "UMask": "0x04", + "UMask": "0x01", "Unit": "IIO" }, { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", + "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", "Counter": "0,1", "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", "FCMask": "0x07", "PerPkg": "1", - "PortMask": "0x02", + "PortMask": "0x04", "ScaleUnit": "4Bytes", - "UMask": "0x04", + "UMask": "0x01", "Unit": "IIO" }, { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", + "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", "Counter": "0,1", "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", "FCMask": "0x07", "PerPkg": "1", - "PortMask": "0x04", + "PortMask": "0x08", "ScaleUnit": "4Bytes", - "UMask": "0x04", + "UMask": "0x01", "Unit": "IIO" }, { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", + "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", "Counter": "0,1", "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "EventName": "LLC_MISSES.PCIE_WRITE", "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", "PerPkg": "1", - "PortMask": "0x08", + "PortMask": "0x01", "ScaleUnit": "4Bytes", - "UMask": "0x04", + "UMask": "0x01", "Unit": "IIO" }, { @@ -313,6 +309,16 @@ "Unit": "CHA" }, { + "BriefDescription": "FaST wire asserted; Horizontal", + "Counter": "0,1,2,3", + "EventCode": "0xA5", + "EventName": "UNC_CHA_FAST_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x02", + "Unit": "CHA" + }, + { "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", "Counter": "0,1,2,3", "EventCode": "0x5F", @@ -343,6 +349,46 @@ "Unit": "CHA" }, { + "BriefDescription": "Lines Victimized; Lines in E state", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in F State", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in M state", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in S State", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x04", + "Unit": "CHA" + }, + { "BriefDescription": "Number of times that an RFO hit in S state.", "Counter": "0,1,2,3", "EventCode": "0x39", @@ -373,6 +419,65 @@ "Unit": "CHA" }, { + "BriefDescription": "Ingress (from CMS) Allocations; IRQ", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; IRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for E-state entries.", + "Counter": "0,1,2,3", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.E_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for M-state entries.", + "Counter": "0,1,2,3", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.M_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for S-state entries.", + "Counter": "0,1,2,3", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.S_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x04", + "Unit": "CHA" + }, + { "BriefDescription": "RspCnflct* Snoop Responses Received", "Counter": "0,1,2,3", "EventCode": "0x5C", @@ -449,7 +554,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x01", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", "UMask": "0x04", "Unit": "IIO" }, @@ -461,7 +566,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", "UMask": "0x04", "Unit": "IIO" }, @@ -473,7 +578,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", "UMask": "0x04", "Unit": "IIO" }, @@ -485,7 +590,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", "UMask": "0x04", "Unit": "IIO" }, @@ -497,7 +602,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x01", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", "UMask": "0x01", "Unit": "IIO" }, @@ -509,35 +614,227 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", "UMask": "0x01", "Unit": "IIO" }, { - "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU ", + "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", "Counter": "2,3", "EventCode": "0xC0", "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", "UMask": "0x01", "Unit": "IIO" }, { - "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU ", + "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", "Counter": "2,3", "EventCode": "0xC0", "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", "UMask": "0x01", "Unit": "IIO" }, { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part1", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part2", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part3", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part1 by a different IIO unit", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part2 by a different IIO unit", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part3 by a different IIO unit", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part1 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part2 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part3 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", "Counter": "0,1,2,3", "EventCode": "0xC1", @@ -545,7 +842,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x01", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", "UMask": "0x04", "Unit": "IIO" }, @@ -557,7 +854,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", "UMask": "0x04", "Unit": "IIO" }, @@ -569,7 +866,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", "UMask": "0x04", "Unit": "IIO" }, @@ -581,7 +878,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", "UMask": "0x04", "Unit": "IIO" }, @@ -593,7 +890,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x01", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", "UMask": "0x01", "Unit": "IIO" }, @@ -605,35 +902,131 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", "UMask": "0x01", "Unit": "IIO" }, { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU ", + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", "UMask": "0x01", "Unit": "IIO" }, { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU ", + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", "Counter": "0,1,2,3", "EventCode": "0xC1", "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", "UMask": "0x01", "Unit": "IIO" }, { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part0", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part1", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part2", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part3", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part0 by a different IIO unit", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part1 by a different IIO unit", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part2 by a different IIO unit", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part3 by a different IIO unit", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", "Counter": "0,1,2,3", "EventCode": "0x84", @@ -730,6 +1123,102 @@ "Unit": "IIO" }, { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part1 to the MMIO space of an IIO target.In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken", "Counter": "0,1,2,3", "EventCode": "0x22", @@ -813,7 +1302,7 @@ "Unit": "M2M" }, { - "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state) ", + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", "Counter": "0,1,2,3", "EventCode": "0x2D", "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", @@ -823,7 +1312,7 @@ "Unit": "M2M" }, { - "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state) ", + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", "Counter": "0,1,2,3", "EventCode": "0x2D", "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", @@ -833,7 +1322,7 @@ "Unit": "M2M" }, { - "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state) ", + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", "Counter": "0,1,2,3", "EventCode": "0x2D", "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", @@ -863,7 +1352,7 @@ "Unit": "M2M" }, { - "BriefDescription": "Multi-socket cacheline Directory update from/to Any state ", + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", "Counter": "0,1,2,3", "EventCode": "0x2E", "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", @@ -918,7 +1407,7 @@ "EventCode": "0x37", "EventName": "UNC_M2M_IMC_READS.ALL", "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). ", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller).", "UMask": "0x4", "Unit": "M2M" }, @@ -943,6 +1432,16 @@ "Unit": "M2M" }, { + "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", + "Counter": "0,1,2,3", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.NI", + "PerPkg": "1", + "PublicDescription": "M2M Writes Issued to iMC; All, regardless of priority.", + "UMask": "0x80", + "Unit": "M2M" + }, + { "BriefDescription": "Partial Non-Isochronous writes to the iMC", "Counter": "0,1,2,3", "EventCode": "0x38", @@ -976,12 +1475,77 @@ "EventCode": "0x1", "EventName": "UNC_M2M_RxC_AD_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop). This is generally used for reads, and ", + "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop). This is generally used for reads, and", "Unit": "M2M" }, { - "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.", + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "AD Ingress (from CMS) Occupancy", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_M2M_RxC_BL_INSERTS", + "PerPkg": "1", + "PublicDescription": "BL Ingress (from CMS) Allocations", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "BL Ingress (from CMS) Occupancy", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_M2M_TxC_AD_INSERTS", + "PerPkg": "1", + "PublicDescription": "AD Egress (to CMS) Allocations", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "AD Egress (to CMS) Occupancy", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations; All", + "Counter": "0,1,2,3", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "BL Egress (to CMS) Allocations; All", + "UMask": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy; All", "Counter": "0,1,2,3", + "EventCode": "0x16", + "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.ALL", + "PerPkg": "1", + "PublicDescription": "BL Egress (to CMS) Occupancy; All", + "UMask": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.", + "Counter": "0,1,2", "EventCode": "0x29", "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", "PerPkg": "1", @@ -1114,23 +1678,23 @@ "Unit": "UPI LL" }, { - "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", + "BriefDescription": "Null FLITs transmitted from any slot", "Counter": "0,1,2,3", "EventCode": "0x2", - "EventName": "UPI_DATA_BANDWIDTH_TX", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", "PerPkg": "1", - "ScaleUnit": "7.11E-06Bytes", - "UMask": "0x0F", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel Ulra Path Interconnect (UPI) slots on this UPI unit.", + "UMask": "0x27", "Unit": "UPI LL" }, { - "BriefDescription": "Null FLITs transmitted from any slot", + "BriefDescription": "Valid Flits Sent; Data", "Counter": "0,1,2,3", "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "EventName": "UNC_UPI_TxL_FLITS.DATA", "PerPkg": "1", - "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel Ulra Path Interconnect (UPI) slots on this UPI unit.", - "UMask": "0x27", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", "Unit": "UPI LL" }, { diff --git a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json index 7f466c97e485d..bbeee10580969 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json @@ -1,284 +1,284 @@ [ { - "EventCode": "0x08", - "UMask": "0x1", - "BriefDescription": "Load misses in all DTLB levels that cause page walks", + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", - "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0x08", - "UMask": "0x2", - "BriefDescription": "Page walk completed due to a demand data load to a 4K page", + "BriefDescription": "Store misses in all DTLB levels that cause page walks", "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x08", - "UMask": "0x4", - "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page", + "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page", "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "EventCode": "0x08", - "UMask": "0x8", - "BriefDescription": "Page walk completed due to a demand data load to a 1G page", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", + "SampleAfterValue": "100003", + "UMask": "0x10" }, { - "EventCode": "0x08", - "UMask": "0xe", - "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0x08", - "UMask": "0x10", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAE", + "EventName": "ITLB.ITLB_FLUSH", + "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", + "SampleAfterValue": "100007", + "UMask": "0x1" }, { - "EventCode": "0x08", - "UMask": "0x10", - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x08", - "UMask": "0x20", "BriefDescription": "Loads that miss the DTLB and hit the STLB.", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x49", - "UMask": "0x1", - "BriefDescription": "Store misses in all DTLB levels that cause page walks", - "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", - "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0x49", - "UMask": "0x2", - "BriefDescription": "Page walk completed due to a demand data store to a 4K page", - "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x49", - "UMask": "0x4", - "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x49", - "UMask": "0x8", - "BriefDescription": "Page walk completed due to a demand data store to a 1G page", - "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages. The page walks can end with or without a page fault.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "EventCode": "0x49", - "UMask": "0xe", - "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "BriefDescription": "DTLB flush attempts of the thread-specific entries", "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100007", + "UMask": "0x1" }, { - "EventCode": "0x49", - "UMask": "0x10", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x49", - "UMask": "0x10", "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x49", - "UMask": "0x20", - "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "BriefDescription": "Misses at all ITLB levels that cause page walks", "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x4F", - "UMask": "0x10", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", "Counter": "0,1,2,3", - "EventName": "EPT.WALK_PENDING", - "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x20" }, { - "EventCode": "0x85", - "UMask": "0x1", - "BriefDescription": "Misses at all ITLB levels that cause page walks", + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", - "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0xe" }, { - "EventCode": "0x85", - "UMask": "0x2", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0xe" }, { - "EventCode": "0x85", - "UMask": "0x4", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "BriefDescription": "Page walk completed due to a demand data store to a 4K page", "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0x85", - "UMask": "0x8", "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0x85", - "UMask": "0xe", "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_COMPLETED", "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0xe" }, { - "EventCode": "0x85", - "UMask": "0x10", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Page walk completed due to a demand data load to a 4K page", "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0x85", - "UMask": "0x10", - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page", "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.WALK_ACTIVE", - "CounterMask": "1", - "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "EventCode": "0x85", - "UMask": "0x20", - "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "BriefDescription": "Load misses in all DTLB levels that cause page walks", "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.STLB_HIT", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xAE", - "UMask": "0x1", - "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", - "Counter": "0,1,2,3", - "EventName": "ITLB.ITLB_FLUSH", - "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xBD", - "UMask": "0x1", - "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", "Counter": "0,1,2,3", - "EventName": "TLB_FLUSH.DTLB_THREAD", - "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", - "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4F", + "EventName": "EPT.WALK_PENDING", + "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "EventCode": "0xBD", - "UMask": "0x20", "BriefDescription": "STLB flush attempts", "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", "EventName": "TLB_FLUSH.STLB_ANY", "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", "SampleAfterValue": "100007", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" + }, + { + "BriefDescription": "Page walk completed due to a demand data load to a 1G page", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Page walk completed due to a demand data store to a 1G page", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index fc9c158bfa134..e1f3f5c8c550c 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -48,11 +48,58 @@ #include <linux/list.h> #include "jsmn.h" #include "json.h" -#include "jevents.h" +#include "pmu-events.h" int verbose; char *prog; +struct json_event { + char *name; + char *compat; + char *event; + char *desc; + char *long_desc; + char *pmu; + char *unit; + char *perpkg; + char *aggr_mode; + char *metric_expr; + char *metric_name; + char *metric_group; + char *deprecated; + char *metric_constraint; +}; + +enum aggr_mode_class convert(const char *aggr_mode) +{ + if (!strcmp(aggr_mode, "PerCore")) + return PerCore; + else if (!strcmp(aggr_mode, "PerChip")) + return PerChip; + + pr_err("%s: Wrong AggregationMode value '%s'\n", prog, aggr_mode); + return -1; +} + +typedef int (*func)(void *data, struct json_event *je); + +static LIST_HEAD(sys_event_tables); + +struct sys_event_table { + struct list_head list; + char *soc_id; +}; + +static void free_sys_event_tables(void) +{ + struct sys_event_table *et, *next; + + list_for_each_entry_safe(et, next, &sys_event_tables, list) { + free(et->soc_id); + free(et); + } +} + int eprintf(int level, int var, const char *fmt, ...) { @@ -71,11 +118,6 @@ int eprintf(int level, int var, const char *fmt, ...) return ret; } -__attribute__((weak)) char *get_cpu_str(void) -{ - return NULL; -} - static void addfield(char *map, char **dst, const char *sep, const char *a, jsmntok_t *bt) { @@ -239,7 +281,10 @@ static struct map { { "hisi_sccl,ddrc", "hisi_sccl,ddrc" }, { "hisi_sccl,hha", "hisi_sccl,hha" }, { "hisi_sccl,l3c", "hisi_sccl,l3c" }, + /* it's not realistic to keep adding these, we need something more scalable ... */ + { "imx8_ddr", "imx8_ddr" }, { "L3PMC", "amd_l3" }, + { "DFPMC", "amd_df" }, {} }; @@ -318,12 +363,7 @@ static void print_events_table_prefix(FILE *fp, const char *tblname) close_table = 1; } -static int print_events_table_entry(void *data, char *name, char *event, - char *desc, char *long_desc, - char *pmu, char *unit, char *perpkg, - char *metric_expr, - char *metric_name, char *metric_group, - char *deprecated, char *metric_constraint) +static int print_events_table_entry(void *data, struct json_event *je) { struct perf_entry_data *pd = data; FILE *outfp = pd->outfp; @@ -335,30 +375,34 @@ static int print_events_table_entry(void *data, char *name, char *event, */ fprintf(outfp, "{\n"); - if (name) - fprintf(outfp, "\t.name = \"%s\",\n", name); - if (event) - fprintf(outfp, "\t.event = \"%s\",\n", event); - fprintf(outfp, "\t.desc = \"%s\",\n", desc); + if (je->name) + fprintf(outfp, "\t.name = \"%s\",\n", je->name); + if (je->event) + fprintf(outfp, "\t.event = \"%s\",\n", je->event); + fprintf(outfp, "\t.desc = \"%s\",\n", je->desc); + if (je->compat) + fprintf(outfp, "\t.compat = \"%s\",\n", je->compat); fprintf(outfp, "\t.topic = \"%s\",\n", topic); - if (long_desc && long_desc[0]) - fprintf(outfp, "\t.long_desc = \"%s\",\n", long_desc); - if (pmu) - fprintf(outfp, "\t.pmu = \"%s\",\n", pmu); - if (unit) - fprintf(outfp, "\t.unit = \"%s\",\n", unit); - if (perpkg) - fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg); - if (metric_expr) - fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr); - if (metric_name) - fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name); - if (metric_group) - fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group); - if (deprecated) - fprintf(outfp, "\t.deprecated = \"%s\",\n", deprecated); - if (metric_constraint) - fprintf(outfp, "\t.metric_constraint = \"%s\",\n", metric_constraint); + if (je->long_desc && je->long_desc[0]) + fprintf(outfp, "\t.long_desc = \"%s\",\n", je->long_desc); + if (je->pmu) + fprintf(outfp, "\t.pmu = \"%s\",\n", je->pmu); + if (je->unit) + fprintf(outfp, "\t.unit = \"%s\",\n", je->unit); + if (je->perpkg) + fprintf(outfp, "\t.perpkg = \"%s\",\n", je->perpkg); + if (je->aggr_mode) + fprintf(outfp, "\t.aggr_mode = \"%d\",\n", convert(je->aggr_mode)); + if (je->metric_expr) + fprintf(outfp, "\t.metric_expr = \"%s\",\n", je->metric_expr); + if (je->metric_name) + fprintf(outfp, "\t.metric_name = \"%s\",\n", je->metric_name); + if (je->metric_group) + fprintf(outfp, "\t.metric_group = \"%s\",\n", je->metric_group); + if (je->deprecated) + fprintf(outfp, "\t.deprecated = \"%s\",\n", je->deprecated); + if (je->metric_constraint) + fprintf(outfp, "\t.metric_constraint = \"%s\",\n", je->metric_constraint); fprintf(outfp, "},\n"); return 0; @@ -368,11 +412,13 @@ struct event_struct { struct list_head list; char *name; char *event; + char *compat; char *desc; char *long_desc; char *pmu; char *unit; char *perpkg; + char *aggr_mode; char *metric_expr; char *metric_name; char *metric_group; @@ -380,17 +426,17 @@ struct event_struct { char *metric_constraint; }; -#define ADD_EVENT_FIELD(field) do { if (field) { \ - es->field = strdup(field); \ +#define ADD_EVENT_FIELD(field) do { if (je->field) { \ + es->field = strdup(je->field); \ if (!es->field) \ goto out_free; \ } } while (0) #define FREE_EVENT_FIELD(field) free(es->field) -#define TRY_FIXUP_FIELD(field) do { if (es->field && !*field) {\ - *field = strdup(es->field); \ - if (!*field) \ +#define TRY_FIXUP_FIELD(field) do { if (es->field && !je->field) {\ + je->field = strdup(es->field); \ + if (!je->field) \ return -ENOMEM; \ } } while (0) @@ -402,6 +448,7 @@ struct event_struct { op(pmu); \ op(unit); \ op(perpkg); \ + op(aggr_mode); \ op(metric_expr); \ op(metric_name); \ op(metric_group); \ @@ -421,11 +468,7 @@ static void free_arch_std_events(void) } } -static int save_arch_std_events(void *data, char *name, char *event, - char *desc, char *long_desc, char *pmu, - char *unit, char *perpkg, char *metric_expr, - char *metric_name, char *metric_group, - char *deprecated, char *metric_constraint) +static int save_arch_std_events(void *data, struct json_event *je) { struct event_struct *es; @@ -485,23 +528,15 @@ static char *real_event(const char *name, char *event) } static int -try_fixup(const char *fn, char *arch_std, char **event, char **desc, - char **name, char **long_desc, char **pmu, char **filter, - char **perpkg, char **unit, char **metric_expr, char **metric_name, - char **metric_group, unsigned long long eventcode, - char **deprecated, char **metric_constraint) +try_fixup(const char *fn, char *arch_std, struct json_event *je, char **event) { /* try to find matching event from arch standard values */ struct event_struct *es; list_for_each_entry(es, &arch_std_events, list) { if (!strcmp(arch_std, es->name)) { - if (!eventcode && es->event) { - /* allow EventCode to be overridden */ - free(*event); - *event = NULL; - } FOR_ALL_EVENT_STRUCT_FIELDS(TRY_FIXUP_FIELD); + *event = je->event; return 0; } } @@ -512,14 +547,9 @@ try_fixup(const char *fn, char *arch_std, char **event, char **desc, } /* Call func with each event in the json file */ -int json_events(const char *fn, - int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc, - char *pmu, char *unit, char *perpkg, - char *metric_expr, - char *metric_name, char *metric_group, - char *deprecated, char *metric_constraint), - void *data) +static int json_events(const char *fn, + int (*func)(void *data, struct json_event *je), + void *data) { int err; size_t size; @@ -537,18 +567,10 @@ int json_events(const char *fn, EXPECT(tokens->type == JSMN_ARRAY, tokens, "expected top level array"); tok = tokens + 1; for (i = 0; i < tokens->size; i++) { - char *event = NULL, *desc = NULL, *name = NULL; - char *long_desc = NULL; + char *event = NULL; char *extra_desc = NULL; - char *pmu = NULL; char *filter = NULL; - char *perpkg = NULL; - char *unit = NULL; - char *metric_expr = NULL; - char *metric_name = NULL; - char *metric_group = NULL; - char *deprecated = NULL; - char *metric_constraint = NULL; + struct json_event je = {}; char *arch_std = NULL; unsigned long long eventcode = 0; struct msrmap *msr = NULL; @@ -583,14 +605,16 @@ int json_events(const char *fn, eventcode |= strtoul(code, NULL, 0) << 21; free(code); } else if (json_streq(map, field, "EventName")) { - addfield(map, &name, "", "", val); + addfield(map, &je.name, "", "", val); + } else if (json_streq(map, field, "Compat")) { + addfield(map, &je.compat, "", "", val); } else if (json_streq(map, field, "BriefDescription")) { - addfield(map, &desc, "", "", val); - fixdesc(desc); + addfield(map, &je.desc, "", "", val); + fixdesc(je.desc); } else if (json_streq(map, field, "PublicDescription")) { - addfield(map, &long_desc, "", "", val); - fixdesc(long_desc); + addfield(map, &je.long_desc, "", "", val); + fixdesc(je.long_desc); } else if (json_streq(map, field, "PEBS") && nz) { precise = val; } else if (json_streq(map, field, "MSRIndex") && nz) { @@ -610,34 +634,36 @@ int json_events(const char *fn, ppmu = field_to_perf(unit_to_pmu, map, val); if (ppmu) { - pmu = strdup(ppmu); + je.pmu = strdup(ppmu); } else { - if (!pmu) - pmu = strdup("uncore_"); - addfield(map, &pmu, "", "", val); - for (s = pmu; *s; s++) + if (!je.pmu) + je.pmu = strdup("uncore_"); + addfield(map, &je.pmu, "", "", val); + for (s = je.pmu; *s; s++) *s = tolower(*s); } - addfield(map, &desc, ". ", "Unit: ", NULL); - addfield(map, &desc, "", pmu, NULL); - addfield(map, &desc, "", " ", NULL); + addfield(map, &je.desc, ". ", "Unit: ", NULL); + addfield(map, &je.desc, "", je.pmu, NULL); + addfield(map, &je.desc, "", " ", NULL); } else if (json_streq(map, field, "Filter")) { addfield(map, &filter, "", "", val); } else if (json_streq(map, field, "ScaleUnit")) { - addfield(map, &unit, "", "", val); + addfield(map, &je.unit, "", "", val); } else if (json_streq(map, field, "PerPkg")) { - addfield(map, &perpkg, "", "", val); + addfield(map, &je.perpkg, "", "", val); + } else if (json_streq(map, field, "AggregationMode")) { + addfield(map, &je.aggr_mode, "", "", val); } else if (json_streq(map, field, "Deprecated")) { - addfield(map, &deprecated, "", "", val); + addfield(map, &je.deprecated, "", "", val); } else if (json_streq(map, field, "MetricName")) { - addfield(map, &metric_name, "", "", val); + addfield(map, &je.metric_name, "", "", val); } else if (json_streq(map, field, "MetricGroup")) { - addfield(map, &metric_group, "", "", val); + addfield(map, &je.metric_group, "", "", val); } else if (json_streq(map, field, "MetricConstraint")) { - addfield(map, &metric_constraint, "", "", val); + addfield(map, &je.metric_constraint, "", "", val); } else if (json_streq(map, field, "MetricExpr")) { - addfield(map, &metric_expr, "", "", val); - for (s = metric_expr; *s; s++) + addfield(map, &je.metric_expr, "", "", val); + for (s = je.metric_expr; *s; s++) *s = tolower(*s); } else if (json_streq(map, field, "ArchStdEvent")) { addfield(map, &arch_std, "", "", val); @@ -646,7 +672,7 @@ int json_events(const char *fn, } /* ignore unknown fields */ } - if (precise && desc && !strstr(desc, "(Precise Event)")) { + if (precise && je.desc && !strstr(je.desc, "(Precise Event)")) { if (json_streq(map, precise, "2")) addfield(map, &extra_desc, " ", "(Must be precise)", NULL); @@ -656,48 +682,45 @@ int json_events(const char *fn, } snprintf(buf, sizeof buf, "event=%#llx", eventcode); addfield(map, &event, ",", buf, NULL); - if (desc && extra_desc) - addfield(map, &desc, " ", extra_desc, NULL); - if (long_desc && extra_desc) - addfield(map, &long_desc, " ", extra_desc, NULL); + if (je.desc && extra_desc) + addfield(map, &je.desc, " ", extra_desc, NULL); + if (je.long_desc && extra_desc) + addfield(map, &je.long_desc, " ", extra_desc, NULL); if (filter) addfield(map, &event, ",", filter, NULL); if (msr != NULL) addfield(map, &event, ",", msr->pname, msrval); - if (name) - fixname(name); + if (je.name) + fixname(je.name); if (arch_std) { /* * An arch standard event is referenced, so try to * fixup any unassigned values. */ - err = try_fixup(fn, arch_std, &event, &desc, &name, - &long_desc, &pmu, &filter, &perpkg, - &unit, &metric_expr, &metric_name, - &metric_group, eventcode, - &deprecated, &metric_constraint); + err = try_fixup(fn, arch_std, &je, &event); if (err) goto free_strings; } - err = func(data, name, real_event(name, event), desc, long_desc, - pmu, unit, perpkg, metric_expr, metric_name, - metric_group, deprecated, metric_constraint); + je.event = real_event(je.name, event); + err = func(data, &je); free_strings: free(event); - free(desc); - free(name); - free(long_desc); + free(je.desc); + free(je.name); + free(je.compat); + free(je.long_desc); free(extra_desc); - free(pmu); + free(je.pmu); free(filter); - free(perpkg); - free(deprecated); - free(unit); - free(metric_expr); - free(metric_name); - free(metric_group); - free(metric_constraint); + free(je.perpkg); + free(je.aggr_mode); + free(je.deprecated); + free(je.unit); + free(je.metric_expr); + free(je.metric_name); + free(je.metric_group); + free(je.metric_constraint); free(arch_std); if (err) @@ -750,6 +773,15 @@ static char *file_name_to_table_name(char *fname) return tblname; } +static bool is_sys_dir(char *fname) +{ + size_t len = strlen(fname), len2 = strlen("/sys"); + + if (len2 > len) + return false; + return !strcmp(fname+len-len2, "/sys"); +} + static void print_mapping_table_prefix(FILE *outfp) { fprintf(outfp, "struct pmu_events_map pmu_events_map[] = {\n"); @@ -784,6 +816,33 @@ static void print_mapping_test_table(FILE *outfp) fprintf(outfp, "},\n"); } +static void print_system_event_mapping_table_prefix(FILE *outfp) +{ + fprintf(outfp, "\nstruct pmu_sys_events pmu_sys_event_tables[] = {"); +} + +static void print_system_event_mapping_table_suffix(FILE *outfp) +{ + fprintf(outfp, "\n\t{\n\t\t.table = 0\n\t},"); + fprintf(outfp, "\n};\n"); +} + +static int process_system_event_tables(FILE *outfp) +{ + struct sys_event_table *sys_event_table; + + print_system_event_mapping_table_prefix(outfp); + + list_for_each_entry(sys_event_table, &sys_event_tables, list) { + fprintf(outfp, "\n\t{\n\t\t.table = %s,\n\t},", + sys_event_table->soc_id); + } + + print_system_event_mapping_table_suffix(outfp); + + return 0; +} + static int process_mapfile(FILE *outfp, char *fpath) { int n = 16384; @@ -889,6 +948,8 @@ static void create_empty_mapping(const char *output_file) fprintf(outfp, "#include \"pmu-events/pmu-events.h\"\n"); print_mapping_table_prefix(outfp); print_mapping_table_suffix(outfp); + print_system_event_mapping_table_prefix(outfp); + print_system_event_mapping_table_suffix(outfp); fclose(outfp); } @@ -981,15 +1042,20 @@ static int process_one_file(const char *fpath, const struct stat *sb, int level = ftwbuf->level; int err = 0; - if (level == 2 && is_dir) { + if (level >= 2 && is_dir) { + int count = 0; /* * For level 2 directory, bname will include parent name, * like vendor/platform. So search back from platform dir * to find this. + * Something similar for level 3 directory, but we're a PMU + * category folder, like vendor/platform/cpu. */ bname = (char *) fpath + ftwbuf->base - 2; for (;;) { if (*bname == '/') + count++; + if (count == level - 1) break; bname--; } @@ -1002,13 +1068,13 @@ static int process_one_file(const char *fpath, const struct stat *sb, level, sb->st_size, bname, fpath); /* base dir or too deep */ - if (level == 0 || level > 3) + if (level == 0 || level > 4) return 0; /* model directory, reset topic */ if ((level == 1 && is_dir && is_leaf_dir(fpath)) || - (level == 2 && is_dir)) { + (level >= 2 && is_dir && is_leaf_dir(fpath))) { if (close_table) print_events_table_suffix(eventsfp); @@ -1024,6 +1090,22 @@ static int process_one_file(const char *fpath, const struct stat *sb, return -1; } + if (is_sys_dir(bname)) { + struct sys_event_table *sys_event_table; + + sys_event_table = malloc(sizeof(*sys_event_table)); + if (!sys_event_table) + return -1; + + sys_event_table->soc_id = strdup(tblname); + if (!sys_event_table->soc_id) { + free(sys_event_table); + return -1; + } + list_add_tail(&sys_event_table->list, + &sys_event_tables); + } + print_events_table_prefix(eventsfp, tblname); return 0; } @@ -1103,12 +1185,13 @@ static int process_one_file(const char *fpath, const struct stat *sb, */ int main(int argc, char *argv[]) { - int rc, ret = 0; + int rc, ret = 0, empty_map = 0; int maxfds; char ldirname[PATH_MAX]; const char *arch; const char *output_file; const char *start_dirname; + char *err_string_ext = ""; struct stat stbuf; prog = basename(argv[0]); @@ -1136,7 +1219,8 @@ int main(int argc, char *argv[]) /* If architecture does not have any event lists, bail out */ if (stat(ldirname, &stbuf) < 0) { pr_info("%s: Arch %s has no PMU event lists\n", prog, arch); - goto empty_map; + empty_map = 1; + goto err_close_eventsfp; } /* Include pmu-events.h first */ @@ -1153,75 +1237,70 @@ int main(int argc, char *argv[]) */ maxfds = get_maxfds(); - mapfile = NULL; rc = nftw(ldirname, preprocess_arch_std_files, maxfds, 0); - if (rc && verbose) { - pr_info("%s: Error preprocessing arch standard files %s\n", - prog, ldirname); - goto empty_map; - } else if (rc < 0) { - /* Make build fail */ - fclose(eventsfp); - free_arch_std_events(); - return 1; - } else if (rc) { - goto empty_map; - } + if (rc) + goto err_processing_std_arch_event_dir; rc = nftw(ldirname, process_one_file, maxfds, 0); - if (rc && verbose) { - pr_info("%s: Error walking file tree %s\n", prog, ldirname); - goto empty_map; - } else if (rc < 0) { - /* Make build fail */ - fclose(eventsfp); - free_arch_std_events(); - ret = 1; - goto out_free_mapfile; - } else if (rc) { - goto empty_map; - } + if (rc) + goto err_processing_dir; sprintf(ldirname, "%s/test", start_dirname); + rc = nftw(ldirname, preprocess_arch_std_files, maxfds, 0); + if (rc) + goto err_processing_std_arch_event_dir; + rc = nftw(ldirname, process_one_file, maxfds, 0); - if (rc && verbose) { - pr_info("%s: Error walking file tree %s rc=%d for test\n", - prog, ldirname, rc); - goto empty_map; - } else if (rc < 0) { - /* Make build fail */ - free_arch_std_events(); - ret = 1; - goto out_free_mapfile; - } else if (rc) { - goto empty_map; - } + if (rc) + goto err_processing_dir; if (close_table) print_events_table_suffix(eventsfp); if (!mapfile) { pr_info("%s: No CPU->JSON mapping?\n", prog); - goto empty_map; + empty_map = 1; + goto err_close_eventsfp; } - if (process_mapfile(eventsfp, mapfile)) { + rc = process_mapfile(eventsfp, mapfile); + if (rc) { pr_info("%s: Error processing mapfile %s\n", prog, mapfile); /* Make build fail */ - fclose(eventsfp); - free_arch_std_events(); ret = 1; + goto err_close_eventsfp; } + rc = process_system_event_tables(eventsfp); + fclose(eventsfp); + if (rc) { + ret = 1; + goto err_out; + } - goto out_free_mapfile; + free_arch_std_events(); + free(mapfile); + return 0; -empty_map: +err_processing_std_arch_event_dir: + err_string_ext = " for std arch event"; +err_processing_dir: + if (verbose) { + pr_info("%s: Error walking file tree %s%s\n", prog, ldirname, + err_string_ext); + empty_map = 1; + } else if (rc < 0) { + ret = 1; + } else { + empty_map = 1; + } +err_close_eventsfp: fclose(eventsfp); - create_empty_mapping(output_file); + if (empty_map) + create_empty_mapping(output_file); +err_out: free_arch_std_events(); -out_free_mapfile: free(mapfile); return ret; } diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h deleted file mode 100644 index 2afc8304529e8..0000000000000 --- a/tools/perf/pmu-events/jevents.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef JEVENTS_H -#define JEVENTS_H 1 - -int json_events(const char *fn, - int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc, - char *pmu, - char *unit, char *perpkg, char *metric_expr, - char *metric_name, char *metric_group, - char *deprecated, char *metric_constraint), - void *data); -char *get_cpu_str(void); - -#ifndef min -#define min(x, y) ({ \ - typeof(x) _min1 = (x); \ - typeof(y) _min2 = (y); \ - (void) (&_min1 == &_min2); \ - _min1 < _min2 ? _min1 : _min2; }) -#endif - -#endif diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index c8f306b572f49..d1172f6aebf1a 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -2,11 +2,17 @@ #ifndef PMU_EVENTS_H #define PMU_EVENTS_H +enum aggr_mode_class { + PerChip = 1, + PerCore +}; + /* * Describe each PMU event. Each CPU has a table of PMU events. */ struct pmu_event { const char *name; + const char *compat; const char *event; const char *desc; const char *topic; @@ -14,6 +20,7 @@ struct pmu_event { const char *pmu; const char *unit; const char *perpkg; + const char *aggr_mode; const char *metric_expr; const char *metric_name; const char *metric_group; @@ -37,10 +44,15 @@ struct pmu_events_map { struct pmu_event *table; }; +struct pmu_sys_events { + struct pmu_event *table; +}; + /* * Global table mapping each known CPU for the architecture to its * table of PMU events. */ extern struct pmu_events_map pmu_events_map[]; +extern struct pmu_sys_events pmu_sys_event_tables[]; #endif diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py index eb76f6516247e..461848c7f57dc 100755 --- a/tools/perf/python/tracepoint.py +++ b/tools/perf/python/tracepoint.py @@ -1,4 +1,4 @@ -#! /usr/bin/python +#! /usr/bin/env python # SPDX-License-Identifier: GPL-2.0 # -*- python -*- # -*- coding: utf-8 -*- diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py index ff87ccf5b7085..04f3db29b9bc1 100755 --- a/tools/perf/python/twatch.py +++ b/tools/perf/python/twatch.py @@ -1,4 +1,4 @@ -#! /usr/bin/python +#! /usr/bin/env python # SPDX-License-Identifier: GPL-2.0-only # -*- python -*- # -*- coding: utf-8 -*- diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py index 0c4841acf75da..7e884d46f9206 100644 --- a/tools/perf/scripts/python/futex-contention.py +++ b/tools/perf/scripts/python/futex-contention.py @@ -12,41 +12,46 @@ from __future__ import print_function -import os, sys -sys.path.append(os.environ['PERF_EXEC_PATH'] + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') +import os +import sys +sys.path.append(os.environ['PERF_EXEC_PATH'] + + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') from Util import * process_names = {} thread_thislock = {} thread_blocktime = {} -lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time -process_names = {} # long-lived pid-to-execname mapping +lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time +process_names = {} # long-lived pid-to-execname mapping + def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, - nr, uaddr, op, val, utime, uaddr2, val3): - cmd = op & FUTEX_CMD_MASK - if cmd != FUTEX_WAIT: - return # we don't care about originators of WAKE events + nr, uaddr, op, val, utime, uaddr2, val3): + cmd = op & FUTEX_CMD_MASK + if cmd != FUTEX_WAIT: + return # we don't care about originators of WAKE events + + process_names[tid] = comm + thread_thislock[tid] = uaddr + thread_blocktime[tid] = nsecs(s, ns) - process_names[tid] = comm - thread_thislock[tid] = uaddr - thread_blocktime[tid] = nsecs(s, ns) def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, - nr, ret): - if tid in thread_blocktime: - elapsed = nsecs(s, ns) - thread_blocktime[tid] - add_stats(lock_waits, (tid, thread_thislock[tid]), elapsed) - del thread_blocktime[tid] - del thread_thislock[tid] + nr, ret): + if tid in thread_blocktime: + elapsed = nsecs(s, ns) - thread_blocktime[tid] + add_stats(lock_waits, (tid, thread_thislock[tid]), elapsed) + del thread_blocktime[tid] + del thread_thislock[tid] + def trace_begin(): - print("Press control+C to stop and show the summary") + print("Press control+C to stop and show the summary") -def trace_end(): - for (tid, lock) in lock_waits: - min, max, avg, count = lock_waits[tid, lock] - print("%s[%d] lock %x contended %d times, %d avg ns" % - (process_names[tid], tid, lock, count, avg)) +def trace_end(): + for (tid, lock) in lock_waits: + min, max, avg, count = lock_waits[tid, lock] + print("%s[%d] lock %x contended %d times, %d avg ns [max: %d ns, min %d ns]" % + (process_names[tid], tid, lock, count, avg, max, min)) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 84352fc49a205..aa4dc4f5abde0 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -60,6 +60,9 @@ perf-y += api-io.o perf-y += demangle-java-test.o perf-y += pfm.o perf-y += parse-metric.o +perf-y += pe-file-parsing.o +perf-y += expand-cgroup.o +perf-y += perf-time-to-tsc.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index a9599ab8c4710..ec972e0892abe 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -30,9 +30,9 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> -#include "../perf-sys.h" #include <subcmd/exec-cmd.h> #include "event.h" +#include "util.h" #include "tests.h" #define ENV "PERF_TEST_ATTR" diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 15cea518f5add..b4b9a9488d516 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -109,7 +109,7 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m return TEST_FAIL; } - err = perf_evlist__create_maps(evlist, &opts.target); + err = evlist__create_maps(evlist, &opts.target); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); goto out_delete_evlist; @@ -127,7 +127,7 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m goto out_delete_evlist; } - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); err = evlist__open(evlist); if (err < 0) { diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index cd77e334e5777..f57e075b0ed2f 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -9,12 +9,10 @@ #include <util/util.h> #include <util/bpf-loader.h> #include <util/evlist.h> -#include <linux/bpf.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/string.h> #include <api/fs/fs.h> -#include <bpf/bpf.h> #include <perf/mmap.h> #include "tests.h" #include "llvm.h" @@ -25,6 +23,8 @@ #define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test" #ifdef HAVE_LIBBPF_SUPPORT +#include <linux/bpf.h> +#include <bpf/bpf.h> static int epoll_pwait_loop(void) { @@ -144,23 +144,23 @@ static int do_test(struct bpf_object *obj, int (*func)(void), pid[sizeof(pid) - 1] = '\0'; opts.target.tid = opts.target.pid = pid; - /* Instead of perf_evlist__new_default, don't add default events */ + /* Instead of evlist__new_default, don't add default events */ evlist = evlist__new(); if (!evlist) { pr_debug("Not enough memory to create evlist\n"); return TEST_FAIL; } - err = perf_evlist__create_maps(evlist, &opts.target); + err = evlist__create_maps(evlist, &opts.target); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); goto out_delete_evlist; } - perf_evlist__splice_list_tail(evlist, &parse_state.list); + evlist__splice_list_tail(evlist, &parse_state.list); evlist->nr_groups = parse_state.nr_groups; - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); err = evlist__open(evlist); if (err < 0) { diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index d328caaba45d4..7273823d0d025 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -142,6 +142,7 @@ static struct test generic_tests[] = { .skip_if_fail = false, .get_nr = test__wp_subtest_get_nr, .get_desc = test__wp_subtest_get_desc, + .skip_reason = test__wp_subtest_skip_reason, }, }, { @@ -342,6 +343,19 @@ static struct test generic_tests[] = { .func = test__parse_metric, }, { + .desc = "PE file support", + .func = test__pe_file_parsing, + }, + { + .desc = "Event expansion for cgroups", + .func = test__expand_cgroup_events, + }, + { + .desc = "Convert perf time to TSC", + .func = test__perf_time_to_tsc, + .is_supported = test__tsc_is_supported, + }, + { .func = NULL, }, }; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 035c9123549a9..7c098d49c77e5 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -378,8 +378,8 @@ static int process_sample_event(struct machine *machine, struct thread *thread; int ret; - if (perf_evlist__parse_sample(evlist, event, &sample)) { - pr_debug("perf_evlist__parse_sample failed\n"); + if (evlist__parse_sample(evlist, event, &sample)) { + pr_debug("evlist__parse_sample failed\n"); return -1; } @@ -637,7 +637,7 @@ static int do_test_code_reading(bool try_kcore) evlist = evlist__new(); if (!evlist) { - pr_debug("perf_evlist__new failed\n"); + pr_debug("evlist__new failed\n"); goto out_put; } @@ -651,7 +651,7 @@ static int do_test_code_reading(bool try_kcore) goto out_put; } - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); evsel = evlist__first(evlist); diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 2491d167bf764..83638097c3bc1 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -95,7 +95,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -__no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread) +noinline int test_dwarf_unwind__thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -126,7 +126,7 @@ __no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -__no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2) +noinline int test_dwarf_unwind__compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -145,7 +145,7 @@ __no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2) return p1 - p2; } -__no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread) +noinline int test_dwarf_unwind__krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -164,12 +164,12 @@ __no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread) return global_unwind_retval; } -__no_tail_call noinline int test_dwarf_unwind__krava_2(struct thread *thread) +noinline int test_dwarf_unwind__krava_2(struct thread *thread) { return test_dwarf_unwind__krava_3(thread); } -__no_tail_call noinline int test_dwarf_unwind__krava_1(struct thread *thread) +noinline int test_dwarf_unwind__krava_1(struct thread *thread) { return test_dwarf_unwind__krava_2(thread); } diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index db68894a6f40a..04ce4401f7752 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -26,13 +26,13 @@ static int attach__enable_on_exec(struct evlist *evlist) pr_debug("attaching to spawned child, enable on exec\n"); - err = perf_evlist__create_maps(evlist, &target); + err = evlist__create_maps(evlist, &target); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); return err; } - err = perf_evlist__prepare_workload(evlist, &target, argv, false, NULL); + err = evlist__prepare_workload(evlist, &target, argv, false, NULL); if (err < 0) { pr_debug("Couldn't run the workload!\n"); return err; @@ -47,7 +47,7 @@ static int attach__enable_on_exec(struct evlist *evlist) return err; } - return perf_evlist__start_workload(evlist) == 1 ? TEST_OK : TEST_FAIL; + return evlist__start_workload(evlist) == 1 ? TEST_OK : TEST_FAIL; } static int detach__enable_on_exec(struct evlist *evlist) diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index bdcf032f85162..656218179222c 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -85,11 +85,10 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct evlist *evlist; struct evsel *evsel; struct event_name tmp; + struct evlist *evlist = evlist__new_default(); - evlist = perf_evlist__new_default(); TEST_ASSERT_VAL("failed to get evlist", evlist); evsel = evlist__first(evlist); diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 0e224a0a55d9a..f9e34bd26cf33 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -5,8 +5,7 @@ #include "tests.h" #include "debug.h" -static int perf_evsel__test_field(struct evsel *evsel, const char *name, - int size, bool should_be_signed) +static int evsel__test_field(struct evsel *evsel, const char *name, int size, bool should_be_signed) { struct tep_format_field *field = evsel__field(evsel, name); int is_signed; @@ -43,25 +42,25 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes return -1; } - if (perf_evsel__test_field(evsel, "prev_comm", 16, false)) + if (evsel__test_field(evsel, "prev_comm", 16, false)) ret = -1; - if (perf_evsel__test_field(evsel, "prev_pid", 4, true)) + if (evsel__test_field(evsel, "prev_pid", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "prev_prio", 4, true)) + if (evsel__test_field(evsel, "prev_prio", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true)) + if (evsel__test_field(evsel, "prev_state", sizeof(long), true)) ret = -1; - if (perf_evsel__test_field(evsel, "next_comm", 16, false)) + if (evsel__test_field(evsel, "next_comm", 16, false)) ret = -1; - if (perf_evsel__test_field(evsel, "next_pid", 4, true)) + if (evsel__test_field(evsel, "next_pid", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "next_prio", 4, true)) + if (evsel__test_field(evsel, "next_prio", 4, true)) ret = -1; evsel__delete(evsel); @@ -73,16 +72,16 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes return -1; } - if (perf_evsel__test_field(evsel, "comm", 16, false)) + if (evsel__test_field(evsel, "comm", 16, false)) ret = -1; - if (perf_evsel__test_field(evsel, "pid", 4, true)) + if (evsel__test_field(evsel, "pid", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "prio", 4, true)) + if (evsel__test_field(evsel, "prio", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "target_cpu", 4, true)) + if (evsel__test_field(evsel, "target_cpu", 4, true)) ret = -1; evsel__delete(evsel); diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c new file mode 100644 index 0000000000000..0e46aeb843ce4 --- /dev/null +++ b/tools/perf/tests/expand-cgroup.c @@ -0,0 +1,240 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "tests.h" +#include "debug.h" +#include "evlist.h" +#include "cgroup.h" +#include "rblist.h" +#include "metricgroup.h" +#include "parse-events.h" +#include "pmu-events/pmu-events.h" +#include "pfm.h" +#include <subcmd/parse-options.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +static int test_expand_events(struct evlist *evlist, + struct rblist *metric_events) +{ + int i, ret = TEST_FAIL; + int nr_events; + bool was_group_event; + int nr_members; /* for the first evsel only */ + const char cgrp_str[] = "A,B,C"; + const char *cgrp_name[] = { "A", "B", "C" }; + int nr_cgrps = ARRAY_SIZE(cgrp_name); + char **ev_name; + struct evsel *evsel; + + TEST_ASSERT_VAL("evlist is empty", !evlist__empty(evlist)); + + nr_events = evlist->core.nr_entries; + ev_name = calloc(nr_events, sizeof(*ev_name)); + if (ev_name == NULL) { + pr_debug("memory allocation failure\n"); + return TEST_FAIL; + } + i = 0; + evlist__for_each_entry(evlist, evsel) { + ev_name[i] = strdup(evsel->name); + if (ev_name[i] == NULL) { + pr_debug("memory allocation failure\n"); + goto out; + } + i++; + } + /* remember grouping info */ + was_group_event = evsel__is_group_event(evlist__first(evlist)); + nr_members = evlist__first(evlist)->core.nr_members; + + ret = evlist__expand_cgroup(evlist, cgrp_str, metric_events, false); + if (ret < 0) { + pr_debug("failed to expand events for cgroups\n"); + goto out; + } + + ret = TEST_FAIL; + if (evlist->core.nr_entries != nr_events * nr_cgrps) { + pr_debug("event count doesn't match\n"); + goto out; + } + + i = 0; + evlist__for_each_entry(evlist, evsel) { + if (strcmp(evsel->name, ev_name[i % nr_events])) { + pr_debug("event name doesn't match:\n"); + pr_debug(" evsel[%d]: %s\n expected: %s\n", + i, evsel->name, ev_name[i % nr_events]); + goto out; + } + if (strcmp(evsel->cgrp->name, cgrp_name[i / nr_events])) { + pr_debug("cgroup name doesn't match:\n"); + pr_debug(" evsel[%d]: %s\n expected: %s\n", + i, evsel->cgrp->name, cgrp_name[i / nr_events]); + goto out; + } + + if ((i % nr_events) == 0) { + if (evsel__is_group_event(evsel) != was_group_event) { + pr_debug("event group doesn't match: got %s, expect %s\n", + evsel__is_group_event(evsel) ? "true" : "false", + was_group_event ? "true" : "false"); + goto out; + } + if (evsel->core.nr_members != nr_members) { + pr_debug("event group member doesn't match: %d vs %d\n", + evsel->core.nr_members, nr_members); + goto out; + } + } + i++; + } + ret = TEST_OK; + +out: for (i = 0; i < nr_events; i++) + free(ev_name[i]); + free(ev_name); + return ret; +} + +static int expand_default_events(void) +{ + int ret; + struct rblist metric_events; + struct evlist *evlist = evlist__new_default(); + + TEST_ASSERT_VAL("failed to get evlist", evlist); + + rblist__init(&metric_events); + ret = test_expand_events(evlist, &metric_events); + evlist__delete(evlist); + return ret; +} + +static int expand_group_events(void) +{ + int ret; + struct evlist *evlist; + struct rblist metric_events; + struct parse_events_error err; + const char event_str[] = "{cycles,instructions}"; + + symbol_conf.event_group = true; + + evlist = evlist__new(); + TEST_ASSERT_VAL("failed to get evlist", evlist); + + ret = parse_events(evlist, event_str, &err); + if (ret < 0) { + pr_debug("failed to parse event '%s', err %d, str '%s'\n", + event_str, ret, err.str); + parse_events_print_error(&err, event_str); + goto out; + } + + rblist__init(&metric_events); + ret = test_expand_events(evlist, &metric_events); +out: + evlist__delete(evlist); + return ret; +} + +static int expand_libpfm_events(void) +{ + int ret; + struct evlist *evlist; + struct rblist metric_events; + const char event_str[] = "CYCLES"; + struct option opt = { + .value = &evlist, + }; + + symbol_conf.event_group = true; + + evlist = evlist__new(); + TEST_ASSERT_VAL("failed to get evlist", evlist); + + ret = parse_libpfm_events_option(&opt, event_str, 0); + if (ret < 0) { + pr_debug("failed to parse libpfm event '%s', err %d\n", + event_str, ret); + goto out; + } + if (evlist__empty(evlist)) { + pr_debug("libpfm was not enabled\n"); + goto out; + } + + rblist__init(&metric_events); + ret = test_expand_events(evlist, &metric_events); +out: + evlist__delete(evlist); + return ret; +} + +static int expand_metric_events(void) +{ + int ret; + struct evlist *evlist; + struct rblist metric_events; + const char metric_str[] = "CPI"; + + struct pmu_event pme_test[] = { + { + .metric_expr = "instructions / cycles", + .metric_name = "IPC", + }, + { + .metric_expr = "1 / IPC", + .metric_name = "CPI", + }, + { + .metric_expr = NULL, + .metric_name = NULL, + }, + }; + struct pmu_events_map ev_map = { + .cpuid = "test", + .version = "1", + .type = "core", + .table = pme_test, + }; + + evlist = evlist__new(); + TEST_ASSERT_VAL("failed to get evlist", evlist); + + rblist__init(&metric_events); + ret = metricgroup__parse_groups_test(evlist, &ev_map, metric_str, + false, false, &metric_events); + if (ret < 0) { + pr_debug("failed to parse '%s' metric\n", metric_str); + goto out; + } + + ret = test_expand_events(evlist, &metric_events); + +out: + metricgroup__rblist_exit(&metric_events); + evlist__delete(evlist); + return ret; +} + +int test__expand_cgroup_events(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + int ret; + + ret = expand_default_events(); + TEST_ASSERT_EQUAL("failed to expand default events", ret, 0); + + ret = expand_group_events(); + TEST_ASSERT_EQUAL("failed to expand event group", ret, 0); + + ret = expand_libpfm_events(); + TEST_ASSERT_EQUAL("failed to expand event group", ret, 0); + + ret = expand_metric_events(); + TEST_ASSERT_EQUAL("failed to expand metric events", ret, 0); + + return ret; +} diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index 50a0c9fcde7da..e6f1b2a38e032 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -92,7 +92,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un CHECK__(parse_events(evlist, "dummy:u", NULL)); CHECK__(parse_events(evlist, "cycles:u", NULL)); - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); evsel = evlist__first(evlist); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index ae6cda81c2093..98da8a8757abc 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -2,13 +2,13 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <bpf/libbpf.h> -#include <util/llvm-utils.h> -#include "llvm.h" #include "tests.h" #include "debug.h" #ifdef HAVE_LIBBPF_SUPPORT +#include <bpf/libbpf.h> +#include <util/llvm-utils.h> +#include "llvm.h" static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) { struct bpf_object *obj; @@ -19,14 +19,6 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) bpf_object__close(obj); return TEST_OK; } -#else -static int test__bpf_parsing(void *obj_buf __maybe_unused, - size_t obj_buf_sz __maybe_unused) -{ - pr_debug("Skip bpf parsing\n"); - return TEST_OK; -} -#endif static struct { const char *source; @@ -170,3 +162,19 @@ const char *test__llvm_subtest_get_desc(int subtest) return bpf_source_table[subtest].desc; } +#else //HAVE_LIBBPF_SUPPORT +int test__llvm(struct test *test __maybe_unused, int subtest __maybe_unused) +{ + return TEST_SKIP; +} + +int test__llvm_subtest_get_nr(void) +{ + return 0; +} + +const char *test__llvm_subtest_get_desc(int subtest __maybe_unused) +{ + return NULL; +} +#endif // HAVE_LIBBPF_SUPPORT diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 9b651dfe0a6b8..a90fa043c066a 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -91,6 +91,7 @@ make_no_sdt := NO_SDT=1 make_no_syscall_tbl := NO_SYSCALL_TABLE=1 make_with_clangllvm := LIBCLANGLLVM=1 make_with_libpfm4 := LIBPFM4=1 +make_with_gtk2 := GTK2=1 make_tags := tags make_cscope := cscope make_help := help @@ -154,6 +155,7 @@ run += make_no_syscall_tbl run += make_with_babeltrace run += make_with_clangllvm run += make_with_libpfm4 +run += make_with_gtk2 run += make_help run += make_doc run += make_perf_o diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 7b0dbfc0e17d4..57093aeacc6f4 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -69,7 +69,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse evlist = evlist__new(); if (evlist == NULL) { - pr_debug("perf_evlist__new\n"); + pr_debug("evlist__new\n"); goto out_free_cpus; } @@ -126,14 +126,14 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse goto out_delete_evlist; } - err = perf_evlist__parse_sample(evlist, event, &sample); + err = evlist__parse_sample(evlist, event, &sample); if (err) { pr_err("Can't parse sample, err = %d\n", err); goto out_delete_evlist; } err = -1; - evsel = perf_evlist__id2evsel(evlist, sample.id); + evsel = evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { pr_debug("event with id %" PRIu64 " doesn't map to an evsel\n", sample.id); diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 1f5f5e79ae253..5e4af2f0f14ae 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -42,7 +42,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest char sbuf[STRERR_BUFSIZE]; if (evlist == NULL) { - pr_debug("%s: perf_evlist__new\n", __func__); + pr_debug("%s: evlist__new\n", __func__); goto out; } @@ -54,9 +54,9 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest evlist__add(evlist, evsel); - err = perf_evlist__create_maps(evlist, &opts.target); + err = evlist__create_maps(evlist, &opts.target); if (err < 0) { - pr_debug("%s: perf_evlist__create_maps\n", __func__); + pr_debug("%s: evlist__create_maps\n", __func__); goto out_delete_evlist; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index aae0fd9045c1c..a7f6661e6112d 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -115,7 +115,7 @@ static int test__checkevent_symbolic_name_config(struct evlist *evlist) TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); /* - * The period value gets configured within perf_evlist__config, + * The period value gets configured within evlist__config, * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", @@ -443,7 +443,7 @@ static int test__checkevent_pmu(struct evlist *evlist) TEST_ASSERT_VAL("wrong config1", 1 == evsel->core.attr.config1); TEST_ASSERT_VAL("wrong config2", 3 == evsel->core.attr.config2); /* - * The period value gets configured within perf_evlist__config, + * The period value gets configured within evlist__config, * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); @@ -520,8 +520,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist) TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); /* - * The period, time and callgraph value gets configured - * within perf_evlist__config, + * The period, time and callgraph value gets configured within evlist__config, * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); @@ -533,8 +532,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist) TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", 2 == evsel->core.attr.config); /* - * The period, time and callgraph value gets configured - * within perf_evlist__config, + * The period, time and callgraph value gets configured within evlist__config, * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); @@ -557,6 +555,7 @@ static int test__checkevent_pmu_events(struct evlist *evlist) TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); + TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive); return 0; } @@ -575,6 +574,7 @@ static int test__checkevent_pmu_events_mix(struct evlist *evlist) TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); + TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive); /* cpu/pmu-event/u*/ evsel = evsel__next(evsel); @@ -587,6 +587,7 @@ static int test__checkevent_pmu_events_mix(struct evlist *evlist) TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); + TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.pinned); return 0; } @@ -1277,6 +1278,49 @@ static int test__pinned_group(struct evlist *evlist) return 0; } +static int test__checkevent_exclusive_modifier(struct evlist *evlist) +{ + struct evsel *evsel = evlist__first(evlist); + + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); + TEST_ASSERT_VAL("wrong exclusive", evsel->core.attr.exclusive); + + return test__checkevent_symbolic_name(evlist); +} + +static int test__exclusive_group(struct evlist *evlist) +{ + struct evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); + + /* cycles - group leader */ + evsel = leader = evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong exclusive", evsel->core.attr.exclusive); + + /* cache-misses - can not be pinned, but will go on with the leader */ + evsel = evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive); + + /* branch-misses - ditto */ + evsel = evsel__next(evsel); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive); + + return 0; +} static int test__checkevent_breakpoint_len(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); @@ -1765,7 +1809,17 @@ static struct evlist_test test__events[] = { .name = "cycles:k", .check = test__sym_event_dc, .id = 55, - } + }, + { + .name = "instructions:uep", + .check = test__checkevent_exclusive_modifier, + .id = 56, + }, + { + .name = "{cycles,cache-misses,branch-misses}:e", + .check = test__exclusive_group, + .id = 57, + }, }; static struct evlist_test test__events_pmu[] = { diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index cd7331aac3bdf..ce7be37f0d88a 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -11,8 +11,6 @@ #include "debug.h" #include "expr.h" #include "stat.h" -#include <perf/cpumap.h> -#include <perf/evlist.h> static struct pmu_event pme_test[] = { { @@ -159,6 +157,7 @@ static int __compute_metric(const char *name, struct value *vals, } perf_evlist__set_maps(&evlist->core, cpus, NULL); + runtime_stat__init(&st); /* Parse the metric into metric_events list. */ err = metricgroup__parse_groups_test(evlist, &map, name, @@ -167,12 +166,11 @@ static int __compute_metric(const char *name, struct value *vals, if (err) goto out; - err = perf_evlist__alloc_stats(evlist, false); + err = evlist__alloc_stats(evlist, false); if (err) goto out; /* Load the runtime stats with given numbers for events. */ - runtime_stat__init(&st); load_runtime_stat(&st, evlist, vals); /* And execute the metric */ @@ -185,7 +183,7 @@ out: /* ... clenup. */ metricgroup__rblist_exit(&metric_events); runtime_stat__exit(&st); - perf_evlist__free_stats(evlist); + evlist__free_stats(evlist); perf_cpu_map__put(cpus); evlist__delete(evlist); return err; diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index adf3c9c4a4163..471273676701b 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -27,8 +27,8 @@ static int process_event(struct evlist **pevlist, union perf_event *event) if (!*pevlist) return -1; - if (perf_evlist__parse_sample(*pevlist, event, &sample)) { - pr_debug("perf_evlist__parse_sample failed\n"); + if (evlist__parse_sample(*pevlist, event, &sample)) { + pr_debug("evlist__parse_sample failed\n"); return -1; } diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c new file mode 100644 index 0000000000000..58b90c42eb38c --- /dev/null +++ b/tools/perf/tests/pe-file-parsing.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdbool.h> +#include <inttypes.h> +#include <stdlib.h> +#include <string.h> +#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <subcmd/exec-cmd.h> + +#include "debug.h" +#include "util/build-id.h" +#include "util/symbol.h" +#include "util/dso.h" + +#include "tests.h" + +#ifdef HAVE_LIBBFD_SUPPORT + +static int run_dir(const char *d) +{ + char filename[PATH_MAX]; + char debugfile[PATH_MAX]; + struct build_id bid; + char debuglink[PATH_MAX]; + char expect_build_id[] = { + 0x5a, 0x0f, 0xd8, 0x82, 0xb5, 0x30, 0x84, 0x22, + 0x4b, 0xa4, 0x7b, 0x62, 0x4c, 0x55, 0xa4, 0x69, + }; + char expect_debuglink[PATH_MAX] = "pe-file.exe.debug"; + struct dso *dso; + struct symbol *sym; + int ret; + + scnprintf(filename, PATH_MAX, "%s/pe-file.exe", d); + ret = filename__read_build_id(filename, &bid); + TEST_ASSERT_VAL("Failed to read build_id", + ret == sizeof(expect_build_id)); + TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id, + sizeof(expect_build_id))); + + ret = filename__read_debuglink(filename, debuglink, PATH_MAX); + TEST_ASSERT_VAL("Failed to read debuglink", ret == 0); + TEST_ASSERT_VAL("Wrong debuglink", + !strcmp(debuglink, expect_debuglink)); + + scnprintf(debugfile, PATH_MAX, "%s/%s", d, debuglink); + ret = filename__read_build_id(debugfile, &bid); + TEST_ASSERT_VAL("Failed to read debug file build_id", + ret == sizeof(expect_build_id)); + TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id, + sizeof(expect_build_id))); + + dso = dso__new(filename); + TEST_ASSERT_VAL("Failed to get dso", dso); + + ret = dso__load_bfd_symbols(dso, debugfile); + TEST_ASSERT_VAL("Failed to load symbols", ret == 0); + + dso__sort_by_name(dso); + sym = dso__find_symbol_by_name(dso, "main"); + TEST_ASSERT_VAL("Failed to find main", sym); + dso__delete(dso); + + return TEST_OK; +} + +int test__pe_file_parsing(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + struct stat st; + char path_dir[PATH_MAX]; + + /* First try development tree tests. */ + if (!lstat("./tests", &st)) + return run_dir("./tests"); + + /* Then installed path. */ + snprintf(path_dir, PATH_MAX, "%s/tests", get_argv_exec_path()); + + if (!lstat(path_dir, &st)) + return run_dir(path_dir); + + return TEST_SKIP; +} + +#else + +int test__pe_file_parsing(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + return TEST_SKIP; +} + +#endif diff --git a/tools/perf/tests/pe-file.c b/tools/perf/tests/pe-file.c new file mode 100644 index 0000000000000..eb3df5e9886f8 --- /dev/null +++ b/tools/perf/tests/pe-file.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 + +// pe-file.exe and pe-file.exe.debug built with; +// x86_64-w64-mingw32-gcc -o pe-file.exe pe-file.c +// -Wl,--file-alignment,4096 -Wl,--build-id +// x86_64-w64-mingw32-objcopy --only-keep-debug +// --compress-debug-sections pe-file.exe pe-file.exe.debug +// x86_64-w64-mingw32-objcopy --strip-debug +// --add-gnu-debuglink=pe-file.exe.debug pe-file.exe + +int main(int argc, char const *argv[]) +{ + return 0; +} diff --git a/tools/perf/tests/pe-file.exe b/tools/perf/tests/pe-file.exe Binary files differnew file mode 100644 index 0000000000000..838a46dae724a --- /dev/null +++ b/tools/perf/tests/pe-file.exe diff --git a/tools/perf/tests/pe-file.exe.debug b/tools/perf/tests/pe-file.exe.debug Binary files differnew file mode 100644 index 0000000000000..287d6718d6c99 --- /dev/null +++ b/tools/perf/tests/pe-file.exe.debug diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 67d3f5aad0167..0df471bf1590e 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -53,7 +53,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus }; cpu_set_t cpu_mask; size_t cpu_mask_size = sizeof(cpu_mask); - struct evlist *evlist = perf_evlist__new_dummy(); + struct evlist *evlist = evlist__new_dummy(); struct evsel *evsel; struct perf_sample sample; const char *cmd = "sleep"; @@ -71,7 +71,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus char sbuf[STRERR_BUFSIZE]; if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */ - evlist = perf_evlist__new_default(); + evlist = evlist__new_default(); if (evlist == NULL) { pr_debug("Not enough memory to create evlist\n"); @@ -81,10 +81,10 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus /* * Create maps of threads and cpus to monitor. In this case * we start with all threads and cpus (-1, -1) but then in - * perf_evlist__prepare_workload we'll fill in the only thread + * evlist__prepare_workload we'll fill in the only thread * we're monitoring, the one forked there. */ - err = perf_evlist__create_maps(evlist, &opts.target); + err = evlist__create_maps(evlist, &opts.target); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); goto out_delete_evlist; @@ -92,11 +92,11 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus /* * Prepare the workload in argv[] to run, it'll fork it, and then wait - * for perf_evlist__start_workload() to exec it. This is done this way + * for evlist__start_workload() to exec it. This is done this way * so that we have time to open the evlist (calling sys_perf_event_open * on all the fds) and then mmap them. */ - err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL); + err = evlist__prepare_workload(evlist, &opts.target, argv, false, NULL); if (err < 0) { pr_debug("Couldn't run the workload!\n"); goto out_delete_evlist; @@ -109,7 +109,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus evsel__set_sample_bit(evsel, CPU); evsel__set_sample_bit(evsel, TID); evsel__set_sample_bit(evsel, TIME); - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask); if (err < 0) { @@ -161,7 +161,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus /* * Now! */ - perf_evlist__start_workload(evlist); + evlist__start_workload(evlist); while (1) { int before = total_events; @@ -182,7 +182,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus if (type < PERF_RECORD_MAX) nr_events[type]++; - err = perf_evlist__parse_sample(evlist, event, &sample); + err = evlist__parse_sample(evlist, event, &sample); if (err < 0) { if (verbose > 0) perf_event__fprintf(event, NULL, stderr); diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 026d32ed078e6..7cff02664d0e6 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -18,10 +18,8 @@ #include "thread_map.h" #include "record.h" #include "tsc.h" -#include "util/mmap.h" -#include "tests/tests.h" - -#include "arch-tests.h" +#include "mmap.h" +#include "tests.h" #define CHECK__(x) { \ while ((x) < 0) { \ @@ -82,7 +80,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe CHECK__(parse_events(evlist, "cycles:u", NULL)); - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); evsel = evlist__first(evlist); @@ -171,3 +169,16 @@ out_err: evlist__delete(evlist); return err; } + +bool test__tsc_is_supported(void) +{ + /* + * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. + * Just enable the test for x86_64/i386 and Arm64 archs. + */ +#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) + return true; +#else + return false; +#endif +} diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index d3517a74d95e3..0ca6a5a535237 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -14,8 +14,10 @@ #include "util/parse-events.h" struct perf_pmu_test_event { + /* used for matching against events from generated pmu-events.c */ struct pmu_event event; + /* used for matching against event aliases */ /* extra events for aliases */ const char *alias_str; @@ -78,6 +80,17 @@ static struct perf_pmu_test_event test_cpu_events[] = { .alias_str = "umask=0,(null)=0x30d40,event=0x3a", .alias_long_desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", }, + { + .event = { + .name = "l3_cache_rd", + .event = "event=0x40", + .desc = "L3 cache access, read", + .long_desc = "Attributable Level 3 cache access, read", + .topic = "cache", + }, + .alias_str = "event=0x40", + .alias_long_desc = "Attributable Level 3 cache access, read", + }, { /* sentinel */ .event = { .name = NULL, @@ -357,6 +370,7 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count) } +/* Test that aliases generated are as expected */ static int test_aliases(void) { struct perf_pmu *pmu = NULL; @@ -561,7 +575,7 @@ static int metric_parse_fake(const char *str) } } - if (expr__parse(&result, &ctx, str, 1)) + if (expr__parse(&result, &ctx, str, 0)) pr_err("expr__parse failed\n"); else ret = 0; diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 40ab72149ce1f..98c6d474aa6f2 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -18,6 +18,7 @@ int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unuse PYTHONPATH, PYTHON, verbose > 0 ? "" : "2> /dev/null") < 0) return -1; + pr_debug("python usage test: \"%s\"\n", cmd); ret = system(cmd) ? -1 : 0; free(cmd); return ret; diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index a0bdaf390ac8e..2393916f6128a 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -154,6 +154,9 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_CGROUP) COMP(cgroup); + if (type & PERF_SAMPLE_DATA_PAGE_SIZE) + COMP(data_page_size); + if (type & PERF_SAMPLE_AUX) { COMP(aux_sample.size); if (memcmp(s1->aux_sample.data, s2->aux_sample.data, @@ -234,6 +237,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) }, .phys_addr = 113, .cgroup = 114, + .data_page_size = 115, .aux_sample = { .size = sizeof(aux_data), .data = (void *)aux_data, @@ -340,7 +344,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u * were added. Please actually update the test rather than just change * the condition below. */ - if (PERF_SAMPLE_MAX > PERF_SAMPLE_CGROUP << 1) { + if (PERF_SAMPLE_MAX > PERF_SAMPLE_CODE_PAGE_SIZE << 1) { pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n"); return -1; } diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c index 60f0e9ee04fb0..ed76c693f65ec 100644 --- a/tools/perf/tests/sdt.c +++ b/tools/perf/tests/sdt.c @@ -28,16 +28,16 @@ static int target_function(void) static int build_id_cache__add_file(const char *filename) { char sbuild_id[SBUILD_ID_SIZE]; - u8 build_id[BUILD_ID_SIZE]; + struct build_id bid; int err; - err = filename__read_build_id(filename, &build_id, sizeof(build_id)); + err = filename__read_build_id(filename, &bid); if (err < 0) { pr_debug("Failed to read build id of %s\n", filename); return err; } - build_id__sprintf(build_id, sizeof(build_id), sbuild_id); + build_id__sprintf(&bid, sbuild_id); err = build_id_cache__add_s(sbuild_id, filename, NULL, false, false); if (err < 0) pr_debug("Failed to add build id cache of %s\n", filename); diff --git a/tools/perf/tests/shell/buildid.sh b/tools/perf/tests/shell/buildid.sh new file mode 100755 index 0000000000000..4861a20edee22 --- /dev/null +++ b/tools/perf/tests/shell/buildid.sh @@ -0,0 +1,101 @@ +#!/bin/sh +# build id cache operations +# SPDX-License-Identifier: GPL-2.0 + +# skip if there's no readelf +if ! [ -x "$(command -v readelf)" ]; then + echo "failed: no readelf, install binutils" + exit 2 +fi + +# skip if there's no compiler +if ! [ -x "$(command -v cc)" ]; then + echo "failed: no compiler, install gcc" + exit 2 +fi + +ex_md5=$(mktemp /tmp/perf.ex.MD5.XXX) +ex_sha1=$(mktemp /tmp/perf.ex.SHA1.XXX) + +echo 'int main(void) { return 0; }' | cc -Wl,--build-id=sha1 -o ${ex_sha1} -x c - +echo 'int main(void) { return 0; }' | cc -Wl,--build-id=md5 -o ${ex_md5} -x c - + +echo "test binaries: ${ex_sha1} ${ex_md5}" + +check() +{ + id=`readelf -n ${1} 2>/dev/null | grep 'Build ID' | awk '{print $3}'` + + echo "build id: ${id}" + + link=${build_id_dir}/.build-id/${id:0:2}/${id:2} + echo "link: ${link}" + + if [ ! -h $link ]; then + echo "failed: link ${link} does not exist" + exit 1 + fi + + file=${build_id_dir}/.build-id/${id:0:2}/`readlink ${link}`/elf + echo "file: ${file}" + + if [ ! -x $file ]; then + echo "failed: file ${file} does not exist" + exit 1 + fi + + diff ${file} ${1} + if [ $? -ne 0 ]; then + echo "failed: ${file} do not match" + exit 1 + fi + + echo "OK for ${1}" +} + +test_add() +{ + build_id_dir=$(mktemp -d /tmp/perf.debug.XXX) + perf="perf --buildid-dir ${build_id_dir}" + + ${perf} buildid-cache -v -a ${1} + if [ $? -ne 0 ]; then + echo "failed: add ${1} to build id cache" + exit 1 + fi + + check ${1} + + rm -rf ${build_id_dir} +} + +test_record() +{ + data=$(mktemp /tmp/perf.data.XXX) + build_id_dir=$(mktemp -d /tmp/perf.debug.XXX) + perf="perf --buildid-dir ${build_id_dir}" + + ${perf} record --buildid-all -o ${data} ${1} + if [ $? -ne 0 ]; then + echo "failed: record ${1}" + exit 1 + fi + + check ${1} + + rm -rf ${build_id_dir} + rm -rf ${data} +} + +# add binaries manual via perf buildid-cache -a +test_add ${ex_sha1} +test_add ${ex_md5} + +# add binaries via perf record post processing +test_record ${ex_sha1} +test_record ${ex_md5} + +# cleanup +rm ${ex_sha1} ${ex_md5} + +exit ${err} diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh new file mode 100755 index 0000000000000..ebebd3596cf99 --- /dev/null +++ b/tools/perf/tests/shell/stat+shadow_stat.sh @@ -0,0 +1,78 @@ +#!/bin/sh +# perf stat metrics (shadow stat) test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +# skip if system-wide mode is forbidden +perf stat -a true > /dev/null 2>&1 || exit 2 + +test_global_aggr() +{ + perf stat -a --no-big-num -e cycles,instructions sleep 1 2>&1 | \ + grep -e cycles -e instructions | \ + while read num evt hash ipc rest + do + # skip not counted events + if [ "$num" = "<not" ]; then + continue + fi + + # save cycles count + if [ "$evt" = "cycles" ]; then + cyc=$num + continue + fi + + # skip if no cycles + if [ -z "$cyc" ]; then + continue + fi + + # use printf for rounding and a leading zero + res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)` + if [ "$ipc" != "$res" ]; then + echo "IPC is different: $res != $ipc ($num / $cyc)" + exit 1 + fi + done +} + +test_no_aggr() +{ + perf stat -a -A --no-big-num -e cycles,instructions sleep 1 2>&1 | \ + grep ^CPU | \ + while read cpu num evt hash ipc rest + do + # skip not counted events + if [ "$num" = "<not" ]; then + continue + fi + + # save cycles count + if [ "$evt" = "cycles" ]; then + results="$results $cpu:$num" + continue + fi + + cyc=${results##* $cpu:} + cyc=${cyc%% *} + + # skip if no cycles + if [ -z "$cyc" ]; then + continue + fi + + # use printf for rounding and a leading zero + res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)` + if [ "$ipc" != "$res" ]; then + echo "IPC is different for $cpu: $res != $ipc ($num / $cyc)" + exit 1 + fi + done +} + +test_global_aggr +test_no_aggr + +exit 0 diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh new file mode 100755 index 0000000000000..18fde2f179cd2 --- /dev/null +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -0,0 +1,183 @@ +#!/bin/sh +# Check Arm CoreSight trace data recording and synthesized samples + +# Uses the 'perf record' to record trace data with Arm CoreSight sinks; +# then verify if there have any branch samples and instruction samples +# are generated by CoreSight with 'perf script' and 'perf report' +# commands. + +# SPDX-License-Identifier: GPL-2.0 +# Leo Yan <leo.yan@linaro.org>, 2020 + +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +file=$(mktemp /tmp/temporary_file.XXXXX) + +skip_if_no_cs_etm_event() { + perf list | grep -q 'cs_etm//' && return 0 + + # cs_etm event doesn't exist + return 2 +} + +skip_if_no_cs_etm_event || exit 2 + +cleanup_files() +{ + rm -f ${perfdata} + rm -f ${file} +} + +trap cleanup_files exit + +record_touch_file() { + echo "Recording trace (only user mode) with path: CPU$2 => $1" + rm -f $file + perf record -o ${perfdata} -e cs_etm/@$1/u --per-thread \ + -- taskset -c $2 touch $file +} + +perf_script_branch_samples() { + echo "Looking at perf.data file for dumping branch samples:" + + # Below is an example of the branch samples dumping: + # touch 6512 1 branches:u: ffffb220824c strcmp+0xc (/lib/aarch64-linux-gnu/ld-2.27.so) + # touch 6512 1 branches:u: ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so) + # touch 6512 1 branches:u: ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so) + perf script -F,-time -i ${perfdata} | \ + egrep " +$1 +[0-9]+ .* +branches:(.*:)? +" +} + +perf_report_branch_samples() { + echo "Looking at perf.data file for reporting branch samples:" + + # Below is an example of the branch samples reporting: + # 73.04% 73.04% touch libc-2.27.so [.] _dl_addr + # 7.71% 7.71% touch libc-2.27.so [.] getenv + # 2.59% 2.59% touch ld-2.27.so [.] strcmp + perf report --stdio -i ${perfdata} | \ + egrep " +[0-9]+\.[0-9]+% +[0-9]+\.[0-9]+% +$1 " +} + +perf_report_instruction_samples() { + echo "Looking at perf.data file for instruction samples:" + + # Below is an example of the instruction samples reporting: + # 68.12% touch libc-2.27.so [.] _dl_addr + # 5.80% touch libc-2.27.so [.] getenv + # 4.35% touch ld-2.27.so [.] _dl_fixup + perf report --itrace=i1000i --stdio -i ${perfdata} | \ + egrep " +[0-9]+\.[0-9]+% +$1" +} + +is_device_sink() { + # If the node of "enable_sink" is existed under the device path, this + # means the device is a sink device. Need to exclude 'tpiu' since it + # cannot support perf PMU. + echo "$1" | egrep -q -v "tpiu" + + if [ $? -eq 0 -a -e "$1/enable_sink" ]; then + + pmu_dev="/sys/bus/event_source/devices/cs_etm/sinks/$2" + + # Warn if the device is not supported by PMU + if ! [ -f $pmu_dev ]; then + echo "PMU doesn't support $pmu_dev" + fi + + return 0 + fi + + # Otherwise, it's not a sink device + return 1 +} + +arm_cs_iterate_devices() { + for dev in $1/connections/out\:*; do + + # Skip testing if it's not a directory + ! [ -d $dev ] && continue; + + # Read out its symbol link file name + path=`readlink -f $dev` + + # Extract device name from path, e.g. + # path = '/sys/devices/platform/20010000.etf/tmc_etf0' + # `> device_name = 'tmc_etf0' + device_name=$(basename $path) + + if is_device_sink $path $device_name; then + + record_touch_file $device_name $2 && + perf_script_branch_samples touch && + perf_report_branch_samples touch && + perf_report_instruction_samples touch + + err=$? + + # Exit when find failure + [ $err != 0 ] && exit $err + fi + + arm_cs_iterate_devices $dev $2 + done +} + +arm_cs_etm_traverse_path_test() { + # Iterate for every ETM device + for dev in /sys/bus/coresight/devices/etm*; do + + # Find the ETM device belonging to which CPU + cpu=`cat $dev/cpu` + + echo $dev + echo $cpu + + # Use depth-first search (DFS) to iterate outputs + arm_cs_iterate_devices $dev $cpu + done +} + +arm_cs_etm_system_wide_test() { + echo "Recording trace with system wide mode" + perf record -o ${perfdata} -e cs_etm// -a -- ls + + perf_script_branch_samples perf && + perf_report_branch_samples perf && + perf_report_instruction_samples perf + + err=$? + + # Exit when find failure + [ $err != 0 ] && exit $err +} + +arm_cs_etm_snapshot_test() { + echo "Recording trace with snapshot mode" + perf record -o ${perfdata} -e cs_etm// -S \ + -- dd if=/dev/zero of=/dev/null & + PERFPID=$! + + # Wait for perf program + sleep 1 + + # Send signal to snapshot trace data + kill -USR2 $PERFPID + + # Stop perf program + kill $PERFPID + wait $PERFPID + + perf_script_branch_samples dd && + perf_report_branch_samples dd && + perf_report_instruction_samples dd + + err=$? + + # Exit when find failure + [ $err != 0 ] && exit $err +} + +arm_cs_etm_traverse_path_test +arm_cs_etm_system_wide_test +arm_cs_etm_snapshot_test +exit 0 diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 11cc2af13f2bb..3d31c1d560d60 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -20,7 +20,7 @@ skip_if_no_perf_trace || exit 2 file=$(mktemp /tmp/temporary_file.XXXXX) trace_open_vfs_getname() { - evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') + evts=$(echo $(perf list syscalls:sys_enter_open* 2>/dev/null | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') perf trace -e $evts touch $file 2>&1 | \ egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" } diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 4b9b731977c8c..a49c9e23053bd 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -109,7 +109,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) if (event->header.type != PERF_RECORD_SAMPLE) goto next_event; - err = perf_evlist__parse_sample(evlist, event, &sample); + err = evlist__parse_sample(evlist, event, &sample); if (err < 0) { pr_debug("Error during parse sample\n"); goto out_delete_evlist; diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index db5e1f70053a8..15a2ab765d890 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -128,12 +128,12 @@ static int process_sample_event(struct evlist *evlist, pid_t next_tid, prev_tid; int cpu, err; - if (perf_evlist__parse_sample(evlist, event, &sample)) { - pr_debug("perf_evlist__parse_sample failed\n"); + if (evlist__parse_sample(evlist, event, &sample)) { + pr_debug("evlist__parse_sample failed\n"); return -1; } - evsel = perf_evlist__id2evsel(evlist, sample.id); + evsel = evlist__id2evsel(evlist, sample.id); if (evsel == switch_tracking->switch_evsel) { next_tid = evsel__intval(evsel, &sample, "next_pid"); prev_tid = evsel__intval(evsel, &sample, "prev_pid"); @@ -223,8 +223,8 @@ static int add_event(struct evlist *evlist, struct list_head *events, node->event = event; list_add(&node->list, events); - if (perf_evlist__parse_sample(evlist, event, &sample)) { - pr_debug("perf_evlist__parse_sample failed\n"); + if (evlist__parse_sample(evlist, event, &sample)) { + pr_debug("evlist__parse_sample failed\n"); return -1; } @@ -380,7 +380,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ cycles_evsel = evlist__last(evlist); /* Third event */ - if (!perf_evlist__can_select_event(evlist, sched_switch)) { + if (!evlist__can_select_event(evlist, sched_switch)) { pr_debug("No sched_switch\n"); err = 0; goto out; @@ -406,7 +406,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ pr_debug("cycles event already at front"); goto out_err; } - perf_evlist__to_front(evlist, cycles_evsel); + evlist__to_front(evlist, cycles_evsel); if (cycles_evsel != evlist__first(evlist)) { pr_debug("Failed to move cycles event to front"); goto out_err; @@ -424,7 +424,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; @@ -432,7 +432,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ evsel__set_sample_bit(tracking_evsel, TIME); /* Config events */ - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); /* Check moved event is still at the front */ if (cycles_evsel != evlist__first(evlist)) { diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index adaff90443319..bbf94e4aa1450 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -23,7 +23,7 @@ static void sig_handler(int sig __maybe_unused) } /* - * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since + * evlist__prepare_workload will send a SIGUSR1 if the fork fails, since * we asked by setting its exec_error to this handler. */ static void workload_exec_failed_signal(int signo __maybe_unused, @@ -58,16 +58,16 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused signal(SIGCHLD, sig_handler); - evlist = perf_evlist__new_default(); + evlist = evlist__new_default(); if (evlist == NULL) { - pr_debug("perf_evlist__new_default\n"); + pr_debug("evlist__new_default\n"); return -1; } /* * Create maps of threads and cpus to monitor. In this case * we start with all threads and cpus (-1, -1) but then in - * perf_evlist__prepare_workload we'll fill in the only thread + * evlist__prepare_workload we'll fill in the only thread * we're monitoring, the one forked there. */ cpus = perf_cpu_map__dummy_new(); @@ -83,8 +83,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused cpus = NULL; threads = NULL; - err = perf_evlist__prepare_workload(evlist, &target, argv, false, - workload_exec_failed_signal); + err = evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal); if (err < 0) { pr_debug("Couldn't run the workload!\n"); goto out_delete_evlist; @@ -116,7 +115,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused goto out_delete_evlist; } - perf_evlist__start_workload(evlist); + evlist__start_workload(evlist); retry: md = &evlist->mmap[0]; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 4447a516c6897..8e24a61fe4c28 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -66,6 +66,7 @@ int test__bp_signal_overflow(struct test *test, int subtest); int test__bp_accounting(struct test *test, int subtest); int test__wp(struct test *test, int subtest); const char *test__wp_subtest_get_desc(int subtest); +const char *test__wp_subtest_skip_reason(int subtest); int test__wp_subtest_get_nr(void); int test__task_exit(struct test *test, int subtest); int test__mem(struct test *test, int subtest); @@ -122,10 +123,14 @@ int test__pfm(struct test *test, int subtest); const char *test__pfm_subtest_get_desc(int subtest); int test__pfm_subtest_get_nr(void); int test__parse_metric(struct test *test, int subtest); +int test__pe_file_parsing(struct test *test, int subtest); +int test__expand_cgroup_events(struct test *test, int subtest); +int test__perf_time_to_tsc(struct test *test, int subtest); bool test__bp_signal_is_supported(void); bool test__bp_account_is_supported(void); bool test__wp_is_supported(void); +bool test__tsc_is_supported(void); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 22daf2bdf5faf..74748ed75b2c6 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -40,7 +40,7 @@ static int session_write_header(char *path) session = perf_session__new(&data, false, NULL); TEST_ASSERT_VAL("can't get session", !IS_ERR(session)); - session->evlist = perf_evlist__new_default(); + session->evlist = evlist__new_default(); TEST_ASSERT_VAL("can't get evlist", session->evlist); perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY); @@ -65,9 +65,11 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) .mode = PERF_DATA_MODE_READ, }; int i; + struct aggr_cpu_id id; session = perf_session__new(&data, false, NULL); TEST_ASSERT_VAL("can't get session", !IS_ERR(session)); + cpu__setup_cpunode_map(); /* On platforms with large numbers of CPUs process_cpu_topology() * might issue an error while reading the perf.data file section @@ -85,11 +87,18 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) * "socket_id number is too big. You may need to upgrade the * perf tool." * - * This is the reason why this test might be skipped. + * This is the reason why this test might be skipped. aarch64 and + * s390 always write this part of the header, even when the above + * condition is true (see do_core_id_test in header.c). So always + * run this test on those platforms. */ - if (!session->header.env.cpu) + if (!session->header.env.cpu + && strncmp(session->header.env.arch, "s390", 4) + && strncmp(session->header.env.arch, "aarch64", 7)) return TEST_SKIP; + TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu); + for (i = 0; i < session->header.env.nr_cpus_avail; i++) { if (!cpu_map__has(map, i)) continue; @@ -98,14 +107,57 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) session->header.env.cpu[i].socket_id); } + // Test that core ID contains socket, die and core + for (i = 0; i < map->nr; i++) { + id = cpu_map__get_core(map, i, NULL); + TEST_ASSERT_VAL("Core map - Core ID doesn't match", + session->header.env.cpu[map->map[i]].core_id == id.core); + + TEST_ASSERT_VAL("Core map - Socket ID doesn't match", + session->header.env.cpu[map->map[i]].socket_id == id.socket); + + TEST_ASSERT_VAL("Core map - Die ID doesn't match", + session->header.env.cpu[map->map[i]].die_id == id.die); + TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1); + TEST_ASSERT_VAL("Core map - Thread is set", id.thread == -1); + } + + // Test that die ID contains socket and die for (i = 0; i < map->nr; i++) { - TEST_ASSERT_VAL("Core ID doesn't match", - (session->header.env.cpu[map->map[i]].core_id == (cpu_map__get_core(map, i, NULL) & 0xffff))); + id = cpu_map__get_die(map, i, NULL); + TEST_ASSERT_VAL("Die map - Socket ID doesn't match", + session->header.env.cpu[map->map[i]].socket_id == id.socket); - TEST_ASSERT_VAL("Socket ID doesn't match", - (session->header.env.cpu[map->map[i]].socket_id == cpu_map__get_socket(map, i, NULL))); + TEST_ASSERT_VAL("Die map - Die ID doesn't match", + session->header.env.cpu[map->map[i]].die_id == id.die); + + TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1); + TEST_ASSERT_VAL("Die map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Die map - Thread is set", id.thread == -1); + } + + // Test that socket ID contains only socket + for (i = 0; i < map->nr; i++) { + id = cpu_map__get_socket(map, i, NULL); + TEST_ASSERT_VAL("Socket map - Socket ID doesn't match", + session->header.env.cpu[map->map[i]].socket_id == id.socket); + + TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1); + TEST_ASSERT_VAL("Socket map - Die ID is set", id.die == -1); + TEST_ASSERT_VAL("Socket map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Socket map - Thread is set", id.thread == -1); } + // Test that node ID contains only node + for (i = 0; i < map->nr; i++) { + id = cpu_map__get_node(map, i, NULL); + TEST_ASSERT_VAL("Node map - Node ID doesn't match", + cpu__get_node(map->map[i]) == id.node); + TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1); + TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1); + TEST_ASSERT_VAL("Node map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Node map - Thread is set", id.thread == -1); + } perf_session__delete(session); return 0; diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c index d262d6639829d..9387fa76faa50 100644 --- a/tools/perf/tests/wp.c +++ b/tools/perf/tests/wp.c @@ -174,10 +174,12 @@ static bool wp_ro_supported(void) #endif } -static void wp_ro_skip_msg(void) +static const char *wp_ro_skip_msg(void) { #if defined (__x86_64__) || defined (__i386__) - pr_debug("Hardware does not support read only watchpoints.\n"); + return "missing hardware support"; +#else + return NULL; #endif } @@ -185,7 +187,7 @@ static struct { const char *desc; int (*target_func)(void); bool (*is_supported)(void); - void (*skip_msg)(void); + const char *(*skip_msg)(void); } wp_testcase_table[] = { { .desc = "Read Only Watchpoint", @@ -219,16 +221,23 @@ const char *test__wp_subtest_get_desc(int i) return wp_testcase_table[i].desc; } +const char *test__wp_subtest_skip_reason(int i) +{ + if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) + return NULL; + if (!wp_testcase_table[i].skip_msg) + return NULL; + return wp_testcase_table[i].skip_msg(); +} + int test__wp(struct test *test __maybe_unused, int i) { if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) return TEST_FAIL; if (wp_testcase_table[i].is_supported && - !wp_testcase_table[i].is_supported()) { - wp_testcase_table[i].skip_msg(); + !wp_testcase_table[i].is_supported()) return TEST_SKIP; - } return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL; } diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index e9cb30d8cbfb1..385894b4a8bba 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -436,6 +436,7 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); +extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); extern struct ns_common *get_net_ns(struct ns_common *ns); diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c index 862c8331dded6..3c5e97b93dd5c 100644 --- a/tools/perf/trace/beauty/mmap.c +++ b/tools/perf/trace/beauty/mmap.c @@ -1,40 +1,28 @@ // SPDX-License-Identifier: LGPL-2.1 -#include <uapi/linux/mman.h> #include <linux/log2.h> -static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, - struct syscall_arg *arg) +#include "trace/beauty/generated/mmap_prot_array.c" +static DEFINE_STRARRAY(mmap_prot, "PROT_"); + +static size_t mmap__scnprintf_prot(unsigned long prot, char *bf, size_t size, bool show_prefix) +{ + return strarray__scnprintf_flags(&strarray__mmap_prot, bf, size, show_prefix, prot); +} + +static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, struct syscall_arg *arg) { - const char *prot_prefix = "PROT_"; - int printed = 0, prot = arg->val; - bool show_prefix = arg->show_string_prefix; - - if (prot == PROT_NONE) - return scnprintf(bf, size, "%sNONE", show_prefix ? prot_prefix : ""); -#define P_MMAP_PROT(n) \ - if (prot & PROT_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s%s", printed ? "|" : "", show_prefix ? prot_prefix :"", #n); \ - prot &= ~PROT_##n; \ - } - - P_MMAP_PROT(READ); - P_MMAP_PROT(WRITE); - P_MMAP_PROT(EXEC); - P_MMAP_PROT(SEM); - P_MMAP_PROT(GROWSDOWN); - P_MMAP_PROT(GROWSUP); -#undef P_MMAP_PROT - - if (prot) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot); - - return printed; + unsigned long prot = arg->val; + + if (prot == 0) + return scnprintf(bf, size, "%sNONE", arg->show_string_prefix ? strarray__mmap_prot.prefix : ""); + + return mmap__scnprintf_prot(prot, bf, size, arg->show_string_prefix); } #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot #include "trace/beauty/generated/mmap_flags_array.c" - static DEFINE_STRARRAY(mmap_flags, "MAP_"); +static DEFINE_STRARRAY(mmap_flags, "MAP_"); static size_t mmap__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) { @@ -54,28 +42,22 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags -static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - const char *flags_prefix = "MREMAP_"; - bool show_prefix = arg->show_string_prefix; - int printed = 0, flags = arg->val; +#include "trace/beauty/generated/mremap_flags_array.c" +static DEFINE_STRARRAY(mremap_flags, "MREMAP_"); -#define P_MREMAP_FLAG(n) \ - if (flags & MREMAP_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s%s", printed ? "|" : "", show_prefix ? flags_prefix : "", #n); \ - flags &= ~MREMAP_##n; \ - } +static size_t mremap__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) +{ + return strarray__scnprintf_flags(&strarray__mremap_flags, bf, size, show_prefix, flags); +} - P_MREMAP_FLAG(MAYMOVE); - P_MREMAP_FLAG(FIXED); - P_MREMAP_FLAG(DONTUNMAP); -#undef P_MREMAP_FLAG +static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size, struct syscall_arg *arg) +{ + unsigned long flags = arg->val; - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + if (!(flags & MREMAP_FIXED)) + arg->mask |= (1 << 5); /* Mask 5th ('new_address') args, ignored */ - return printed; + return mremap__scnprintf_flags(flags, bf, size, arg->show_string_prefix); } #define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh index 5f5eefcb3c748..76825710c725f 100755 --- a/tools/perf/trace/beauty/mmap_flags.sh +++ b/tools/perf/trace/beauty/mmap_flags.sh @@ -21,20 +21,20 @@ printf "static const char *mmap_flags[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MAP_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' egrep -q $regex ${arch_mman} && \ (egrep $regex ${arch_mman} | \ - sed -r "s/$regex/\2 \1/g" | \ - xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") + sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") egrep -q $regex ${linux_mman} && \ (egrep $regex ${linux_mman} | \ egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ - sed -r "s/$regex/\2 \1/g" | \ - xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") -([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) && + sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") +([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) && (egrep $regex ${header_dir}/mman-common.h | \ egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ - sed -r "s/$regex/\2 \1/g" | \ - xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") -([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.h>.*' ${arch_mman}) && + sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") +([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.h>.*' ${arch_mman}) && (egrep $regex ${header_dir}/mman.h | \ - sed -r "s/$regex/\2 \1/g" | \ - xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") + sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") printf "};\n" diff --git a/tools/perf/trace/beauty/mmap_prot.sh b/tools/perf/trace/beauty/mmap_prot.sh new file mode 100755 index 0000000000000..664d8d534a509 --- /dev/null +++ b/tools/perf/trace/beauty/mmap_prot.sh @@ -0,0 +1,30 @@ +#!/bin/sh +# SPDX-License-Identifier: LGPL-2.1 + +if [ $# -ne 2 ] ; then + [ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/` + asm_header_dir=tools/include/uapi/asm-generic + arch_header_dir=tools/arch/${hostarch}/include/uapi/asm +else + asm_header_dir=$1 + arch_header_dir=$2 +fi + +common_mman=${asm_header_dir}/mman-common.h +arch_mman=${arch_header_dir}/mman.h + +prefix="PROT" + +printf "static const char *mmap_prot[] = {\n" +regex=`printf '^[[:space:]]*#[[:space:]]*define[[:space:]]+%s_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' ${prefix}` +([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) && +(egrep $regex ${common_mman} | \ + egrep -vw PROT_NONE | \ + sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef ${prefix}_%s\n#define ${prefix}_%s %s\n#endif\n") +[ -f ${arch_mman} ] && egrep -q $regex ${arch_mman} && +(egrep $regex ${arch_mman} | \ + egrep -vw PROT_NONE | \ + sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef ${prefix}_%s\n#define ${prefix}_%s %s\n#endif\n") +printf "};\n" diff --git a/tools/perf/trace/beauty/mremap_flags.sh b/tools/perf/trace/beauty/mremap_flags.sh new file mode 100755 index 0000000000000..d58182300bb13 --- /dev/null +++ b/tools/perf/trace/beauty/mremap_flags.sh @@ -0,0 +1,18 @@ +#!/bin/sh +# SPDX-License-Identifier: LGPL-2.1 + +if [ $# -ne 1 ] ; then + linux_header_dir=tools/include/uapi/linux +else + linux_header_dir=$1 +fi + +linux_mman=${linux_header_dir}/mman.h + +printf "static const char *mremap_flags[] = {\n" +regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MREMAP_([[:alnum:]_]+)[[:space:]]+((0x)?[[:xdigit:]]+)[[:space:]]*.*' +egrep -q $regex ${linux_mman} && \ +(egrep $regex ${linux_mman} | \ + sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MREMAP_%s\n#define MREMAP_%s %s\n#endif\n") +printf "};\n" diff --git a/tools/perf/trace/beauty/tracepoints/x86_msr.sh b/tools/perf/trace/beauty/tracepoints/x86_msr.sh index 831c02cf0586c..27ee1ea1fe941 100755 --- a/tools/perf/trace/beauty/tracepoints/x86_msr.sh +++ b/tools/perf/trace/beauty/tracepoints/x86_msr.sh @@ -15,7 +15,7 @@ x86_msr_index=${arch_x86_header_dir}/msr-index.h printf "static const char *x86_MSRs[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MSR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x00000[[:xdigit:]]+)[[:space:]]*.*' -egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|AMD64|IA32_TSCDEADLINE|IDT_FCR4)' | \ +egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|IA32_(TSCDEADLINE|UCODE_REV)|IDT_FCR4)' | \ sed -r "s/$regex/\2 \1/g" | sort -n | \ xargs printf "\t[%s] = \"%s\",\n" printf "};\n\n" diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index a07626f072087..3b9818ee9546a 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2946,14 +2946,10 @@ next: } } -static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, - const char *helpline, - bool left_exits, - struct hist_browser_timer *hbt, - float min_pcnt, - struct perf_env *env, - bool warn_lost_event, - struct annotation_options *annotation_opts) +static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *helpline, + bool left_exits, struct hist_browser_timer *hbt, float min_pcnt, + struct perf_env *env, bool warn_lost_event, + struct annotation_options *annotation_opts) { struct hists *hists = evsel__hists(evsel); struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env, annotation_opts); @@ -2963,7 +2959,7 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, struct popup_action actions[MAX_OPTIONS]; int nr_options = 0; int key = -1; - char buf[64]; + char buf[128]; int delay_secs = hbt ? hbt->refresh : 0; #define HIST_BROWSER_HELP_COMMON \ @@ -3268,7 +3264,7 @@ do_hotkey: // key came straight from options ui__popup_menu() if (!is_report_browser(hbt)) { struct perf_top *top = hbt->arg; - perf_evlist__toggle_enable(top->evlist); + evlist__toggle_enable(top->evlist); /* * No need to refresh, resort/decay histogram * entries if we are not collecting samples: @@ -3498,19 +3494,17 @@ static int perf_evsel_menu__run(struct evsel_menu *menu, continue; pos = menu->selection; browse_hists: - perf_evlist__set_selected(evlist, pos); + evlist__set_selected(evlist, pos); /* * Give the calling tool a chance to populate the non * default evsel resorted hists tree. */ if (hbt) hbt->timer(hbt->arg); - key = perf_evsel__hists_browse(pos, nr_events, help, - true, hbt, - menu->min_pcnt, - menu->env, - warn_lost_event, - menu->annotation_opts); + key = evsel__hists_browse(pos, nr_events, help, true, hbt, + menu->min_pcnt, menu->env, + warn_lost_event, + menu->annotation_opts); ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: @@ -3565,13 +3559,9 @@ static bool filter_group_entries(struct ui_browser *browser __maybe_unused, return false; } -static int __perf_evlist__tui_browse_hists(struct evlist *evlist, - int nr_entries, const char *help, - struct hist_browser_timer *hbt, - float min_pcnt, - struct perf_env *env, - bool warn_lost_event, - struct annotation_options *annotation_opts) +static int __evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, const char *help, + struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, + bool warn_lost_event, struct annotation_options *annotation_opts) { struct evsel *pos; struct evsel_menu menu = { @@ -3603,7 +3593,7 @@ static int __perf_evlist__tui_browse_hists(struct evlist *evlist, hbt, warn_lost_event); } -static bool perf_evlist__single_entry(struct evlist *evlist) +static bool evlist__single_entry(struct evlist *evlist) { int nr_entries = evlist->core.nr_entries; @@ -3620,23 +3610,18 @@ static bool perf_evlist__single_entry(struct evlist *evlist) return false; } -int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, - struct hist_browser_timer *hbt, - float min_pcnt, - struct perf_env *env, - bool warn_lost_event, - struct annotation_options *annotation_opts) +int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, + float min_pcnt, struct perf_env *env, bool warn_lost_event, + struct annotation_options *annotation_opts) { int nr_entries = evlist->core.nr_entries; - if (perf_evlist__single_entry(evlist)) { + if (evlist__single_entry(evlist)) { single_entry: { struct evsel *first = evlist__first(evlist); - return perf_evsel__hists_browse(first, nr_entries, help, - false, hbt, min_pcnt, - env, warn_lost_event, - annotation_opts); + return evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, + env, warn_lost_event, annotation_opts); } } @@ -3653,10 +3638,8 @@ single_entry: { goto single_entry; } - return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, - hbt, min_pcnt, env, - warn_lost_event, - annotation_opts); + return __evlist__tui_browse_hists(evlist, nr_entries, help, hbt, min_pcnt, env, + warn_lost_event, annotation_opts); } static int block_hists_browser__title(struct hist_browser *browser, char *bf, diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index a9563932fa04e..a2b497f03fd6e 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -57,9 +57,8 @@ struct evlist; struct hist_entry; struct hist_browser_timer; -int perf_evlist__gtk_browse_hists(struct evlist *evlist, const char *help, - struct hist_browser_timer *hbt, - float min_pcnt); +int evlist__gtk_browse_hists(struct evlist *evlist, const char *help, + struct hist_browser_timer *hbt, float min_pcnt); int hist_entry__gtk_annotate(struct hist_entry *he, struct evsel *evsel, struct hist_browser_timer *hbt); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 53ef71a1b15dc..c83be2d57f7eb 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -590,10 +590,8 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists, gtk_container_add(GTK_CONTAINER(window), view); } -int perf_evlist__gtk_browse_hists(struct evlist *evlist, - const char *help, - struct hist_browser_timer *hbt __maybe_unused, - float min_pcnt) +int evlist__gtk_browse_hists(struct evlist *evlist, const char *help, + struct hist_browser_timer *hbt __maybe_unused, float min_pcnt) { struct evsel *pos; GtkWidget *vbox; diff --git a/tools/perf/util/Build b/tools/perf/util/Build index cd5e41960e64a..e2563d0154eb6 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -101,6 +101,8 @@ perf-y += call-path.o perf-y += rwsem.o perf-y += thread-stack.o perf-y += spark.o +perf-y += topdown.o +perf-y += stream.o perf-$(CONFIG_AUXTRACE) += auxtrace.o perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ perf-$(CONFIG_AUXTRACE) += intel-pt.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0a1fcf7875382..ce8c07bc8c562 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -10,10 +10,6 @@ #include <inttypes.h> #include <libgen.h> #include <stdlib.h> -#include <bpf/bpf.h> -#include <bpf/btf.h> -#include <bpf/libbpf.h> -#include <linux/btf.h> #include "util.h" // hex_width() #include "ui/ui.h" #include "sort.h" @@ -152,6 +148,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/arm/annotate/instructions.c" #include "arch/arm64/annotate/instructions.c" #include "arch/csky/annotate/instructions.c" +#include "arch/mips/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" #include "arch/s390/annotate/instructions.c" @@ -175,6 +172,13 @@ static struct arch architectures[] = { .init = csky__annotate_init, }, { + .name = "mips", + .init = mips__annotate_init, + .objdump = { + .comment_char = '#', + }, + }, + { .name = "x86", .init = x86__annotate_init, .instructions = x86__instructions, @@ -1578,8 +1582,7 @@ int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, s char *build_id_msg = NULL; if (dso->has_build_id) { - build_id__sprintf(dso->build_id, - sizeof(dso->build_id), bf + 15); + build_id__sprintf(&dso->bid, bf + 15); build_id_msg = bf; } scnprintf(buf, buflen, @@ -1677,6 +1680,10 @@ fallback: #define PACKAGE "perf" #include <bfd.h> #include <dis-asm.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> +#include <linux/btf.h> static int symbol__disassemble_bpf(struct symbol *sym, struct annotate_args *args) @@ -3127,6 +3134,8 @@ static int annotation__config(const char *var, const char *value, void *data) value); } else if (!strcmp(var, "annotate.use_offset")) { opt->use_offset = perf_config_bool("use_offset", value); + } else if (!strcmp(var, "annotate.disassembler_style")) { + opt->disassembler_style = value; } else { pr_debug("%s variable unknown, ignoring...", var); } diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 93e063f22be50..90d575cee1b90 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -12,6 +12,7 @@ #include <string.h> #include <stdint.h> #include <stdlib.h> +#include <linux/bitops.h> #include <linux/compiler.h> #include <linux/zalloc.h> @@ -21,42 +22,51 @@ #include "arm-spe-decoder.h" -#ifndef BIT -#define BIT(n) (1UL << (n)) -#endif - static u64 arm_spe_calc_ip(int index, u64 payload) { - u8 *addr = (u8 *)&payload; - int ns, el; + u64 ns, el, val; /* Instruction virtual address or Branch target address */ if (index == SPE_ADDR_PKT_HDR_INDEX_INS || index == SPE_ADDR_PKT_HDR_INDEX_BRANCH) { - ns = addr[7] & SPE_ADDR_PKT_NS; - el = (addr[7] & SPE_ADDR_PKT_EL_MASK) >> SPE_ADDR_PKT_EL_OFFSET; + ns = SPE_ADDR_PKT_GET_NS(payload); + el = SPE_ADDR_PKT_GET_EL(payload); + + /* Clean highest byte */ + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); /* Fill highest byte for EL1 or EL2 (VHE) mode */ if (ns && (el == SPE_ADDR_PKT_EL1 || el == SPE_ADDR_PKT_EL2)) - addr[7] = 0xff; - /* Clean highest byte for other cases */ - else - addr[7] = 0x0; + payload |= 0xffULL << SPE_ADDR_PKT_ADDR_BYTE7_SHIFT; /* Data access virtual address */ } else if (index == SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT) { - /* Fill highest byte if bits [48..55] is 0xff */ - if (addr[6] == 0xff) - addr[7] = 0xff; - /* Otherwise, cleanup tags */ - else - addr[7] = 0x0; + /* Clean tags */ + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); + + /* + * Armv8 ARM (ARM DDI 0487F.c), chapter "D10.2.1 Address packet" + * defines the data virtual address payload format, the top byte + * (bits [63:56]) is assigned as top-byte tag; so we only can + * retrieve address value from bits [55:0]. + * + * According to Documentation/arm64/memory.rst, if detects the + * specific pattern in bits [55:52] of payload which falls in + * the kernel space, should fixup the top byte and this allows + * perf tool to parse DSO symbol for data address correctly. + * + * For this reason, if detects the bits [55:52] is 0xf, will + * fill 0xff into the top byte. + */ + val = SPE_ADDR_PKT_ADDR_GET_BYTE_6(payload); + if ((val & 0xf0ULL) == 0xf0ULL) + payload |= 0xffULL << SPE_ADDR_PKT_ADDR_BYTE7_SHIFT; /* Data access physical address */ } else if (index == SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS) { - /* Cleanup byte 7 */ - addr[7] = 0x0; + /* Clean highest byte */ + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); } else { pr_err("unsupported address packet index: 0x%x\n", index); } @@ -182,16 +192,13 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) if (payload & BIT(EV_TLB_ACCESS)) decoder->record.type |= ARM_SPE_TLB_ACCESS; - if ((idx == 2 || idx == 4 || idx == 8) && - (payload & BIT(EV_LLC_MISS))) + if (payload & BIT(EV_LLC_MISS)) decoder->record.type |= ARM_SPE_LLC_MISS; - if ((idx == 2 || idx == 4 || idx == 8) && - (payload & BIT(EV_LLC_ACCESS))) + if (payload & BIT(EV_LLC_ACCESS)) decoder->record.type |= ARM_SPE_LLC_ACCESS; - if ((idx == 2 || idx == 4 || idx == 8) && - (payload & BIT(EV_REMOTE_ACCESS))) + if (payload & BIT(EV_REMOTE_ACCESS)) decoder->record.type |= ARM_SPE_REMOTE_ACCESS; if (payload & BIT(EV_MISPRED)) 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 a5111a8d43600..24727b8ca7ffa 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -13,23 +13,6 @@ #include "arm-spe-pkt-decoder.h" -enum arm_spe_events { - EV_EXCEPTION_GEN = 0, - EV_RETIRED = 1, - EV_L1D_ACCESS = 2, - EV_L1D_REFILL = 3, - EV_TLB_ACCESS = 4, - EV_TLB_WALK = 5, - EV_NOT_TAKEN = 6, - EV_MISPRED = 7, - EV_LLC_ACCESS = 8, - EV_LLC_MISS = 9, - EV_REMOTE_ACCESS = 10, - EV_ALIGNMENT = 11, - EV_PARTIAL_PREDICATE = 17, - EV_EMPTY_PREDICATE = 18, -}; - enum arm_spe_sample_type { ARM_SPE_L1D_ACCESS = 1 << 0, ARM_SPE_L1D_MISS = 1 << 1, diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index b94001b756c79..f3ac9d40cebf4 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -8,36 +8,11 @@ #include <string.h> #include <endian.h> #include <byteswap.h> +#include <linux/bitops.h> +#include <stdarg.h> #include "arm-spe-pkt-decoder.h" -#define BIT(n) (1ULL << (n)) - -#define NS_FLAG BIT(63) -#define EL_FLAG (BIT(62) | BIT(61)) - -#define SPE_HEADER0_PAD 0x0 -#define SPE_HEADER0_END 0x1 -#define SPE_HEADER0_ADDRESS 0x30 /* address packet (short) */ -#define SPE_HEADER0_ADDRESS_MASK 0x38 -#define SPE_HEADER0_COUNTER 0x18 /* counter packet (short) */ -#define SPE_HEADER0_COUNTER_MASK 0x38 -#define SPE_HEADER0_TIMESTAMP 0x71 -#define SPE_HEADER0_TIMESTAMP 0x71 -#define SPE_HEADER0_EVENTS 0x2 -#define SPE_HEADER0_EVENTS_MASK 0xf -#define SPE_HEADER0_SOURCE 0x3 -#define SPE_HEADER0_SOURCE_MASK 0xf -#define SPE_HEADER0_CONTEXT 0x24 -#define SPE_HEADER0_CONTEXT_MASK 0x3c -#define SPE_HEADER0_OP_TYPE 0x8 -#define SPE_HEADER0_OP_TYPE_MASK 0x3c -#define SPE_HEADER1_ALIGNMENT 0x0 -#define SPE_HEADER1_ADDRESS 0xb0 /* address packet (extended) */ -#define SPE_HEADER1_ADDRESS_MASK 0xf8 -#define SPE_HEADER1_COUNTER 0x98 /* counter packet (extended) */ -#define SPE_HEADER1_COUNTER_MASK 0xf8 - #if __BYTE_ORDER == __BIG_ENDIAN #define le16_to_cpu bswap_16 #define le32_to_cpu bswap_32 @@ -70,27 +45,28 @@ const char *arm_spe_pkt_name(enum arm_spe_pkt_type type) return arm_spe_packet_name[type]; } -/* return ARM SPE payload size from its encoding, - * which is in bits 5:4 of the byte. - * 00 : byte - * 01 : halfword (2) - * 10 : word (4) - * 11 : doubleword (8) +/* + * Extracts the field "sz" from header bits and converts to bytes: + * 00 : byte (1) + * 01 : halfword (2) + * 10 : word (4) + * 11 : doubleword (8) */ -static int payloadlen(unsigned char byte) +static unsigned int arm_spe_payload_len(unsigned char hdr) { - return 1 << ((byte & 0x30) >> 4); + return 1U << ((hdr & GENMASK_ULL(5, 4)) >> 4); } static int arm_spe_get_payload(const unsigned char *buf, size_t len, + unsigned char ext_hdr, struct arm_spe_pkt *packet) { - size_t payload_len = payloadlen(buf[0]); + size_t payload_len = arm_spe_payload_len(buf[ext_hdr]); - if (len < 1 + payload_len) + if (len < 1 + ext_hdr + payload_len) return ARM_SPE_NEED_MORE_BYTES; - buf++; + buf += 1 + ext_hdr; switch (payload_len) { case 1: packet->payload = *(uint8_t *)buf; break; @@ -100,7 +76,7 @@ static int arm_spe_get_payload(const unsigned char *buf, size_t len, default: return ARM_SPE_BAD_PACKET; } - return 1 + payload_len; + return 1 + ext_hdr + payload_len; } static int arm_spe_get_pad(struct arm_spe_pkt *packet) @@ -131,127 +107,128 @@ static int arm_spe_get_timestamp(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { packet->type = ARM_SPE_TIMESTAMP; - return arm_spe_get_payload(buf, len, packet); + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_events(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { - int ret = arm_spe_get_payload(buf, len, packet); - packet->type = ARM_SPE_EVENTS; /* we use index to identify Events with a less number of * comparisons in arm_spe_pkt_desc(): E.g., the LLC-ACCESS, - * LLC-REFILL, and REMOTE-ACCESS events are identified iff + * LLC-REFILL, and REMOTE-ACCESS events are identified if * index > 1. */ - packet->index = ret - 1; + packet->index = arm_spe_payload_len(buf[0]); - return ret; + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_data_source(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { packet->type = ARM_SPE_DATA_SOURCE; - return arm_spe_get_payload(buf, len, packet); + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_context(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { packet->type = ARM_SPE_CONTEXT; - packet->index = buf[0] & 0x3; - - return arm_spe_get_payload(buf, len, packet); + packet->index = SPE_CTX_PKT_HDR_INDEX(buf[0]); + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_op_type(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { packet->type = ARM_SPE_OP_TYPE; - packet->index = buf[0] & 0x3; - return arm_spe_get_payload(buf, len, packet); + packet->index = SPE_OP_PKT_HDR_CLASS(buf[0]); + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_counter(const unsigned char *buf, size_t len, const unsigned char ext_hdr, struct arm_spe_pkt *packet) { - if (len < 2) - return ARM_SPE_NEED_MORE_BYTES; - packet->type = ARM_SPE_COUNTER; + if (ext_hdr) - packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7); + packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]); else - packet->index = buf[0] & 0x7; - - packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1)); + packet->index = SPE_HDR_SHORT_INDEX(buf[0]); - return 1 + ext_hdr + 2; + return arm_spe_get_payload(buf, len, ext_hdr, packet); } static int arm_spe_get_addr(const unsigned char *buf, size_t len, const unsigned char ext_hdr, struct arm_spe_pkt *packet) { - if (len < 8) - return ARM_SPE_NEED_MORE_BYTES; - packet->type = ARM_SPE_ADDRESS; + if (ext_hdr) - packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7); + packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]); else - packet->index = buf[0] & 0x7; - - memcpy_le64(&packet->payload, buf + 1, 8); + packet->index = SPE_HDR_SHORT_INDEX(buf[0]); - return 1 + ext_hdr + 8; + return arm_spe_get_payload(buf, len, ext_hdr, packet); } static int arm_spe_do_get_packet(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { - unsigned int byte; + unsigned int hdr; + unsigned char ext_hdr = 0; memset(packet, 0, sizeof(struct arm_spe_pkt)); if (!len) return ARM_SPE_NEED_MORE_BYTES; - byte = buf[0]; - if (byte == SPE_HEADER0_PAD) + hdr = buf[0]; + + if (hdr == SPE_HEADER0_PAD) return arm_spe_get_pad(packet); - else if (byte == SPE_HEADER0_END) /* no timestamp at end of record */ + + if (hdr == SPE_HEADER0_END) /* no timestamp at end of record */ return arm_spe_get_end(packet); - else if (byte & 0xc0 /* 0y11xxxxxx */) { - if (byte & 0x80) { - if ((byte & SPE_HEADER0_ADDRESS_MASK) == SPE_HEADER0_ADDRESS) - return arm_spe_get_addr(buf, len, 0, packet); - if ((byte & SPE_HEADER0_COUNTER_MASK) == SPE_HEADER0_COUNTER) - return arm_spe_get_counter(buf, len, 0, packet); - } else - if (byte == SPE_HEADER0_TIMESTAMP) - return arm_spe_get_timestamp(buf, len, packet); - else if ((byte & SPE_HEADER0_EVENTS_MASK) == SPE_HEADER0_EVENTS) - return arm_spe_get_events(buf, len, packet); - else if ((byte & SPE_HEADER0_SOURCE_MASK) == SPE_HEADER0_SOURCE) - return arm_spe_get_data_source(buf, len, packet); - else if ((byte & SPE_HEADER0_CONTEXT_MASK) == SPE_HEADER0_CONTEXT) - return arm_spe_get_context(buf, len, packet); - else if ((byte & SPE_HEADER0_OP_TYPE_MASK) == SPE_HEADER0_OP_TYPE) - return arm_spe_get_op_type(buf, len, packet); - } else if ((byte & 0xe0) == 0x20 /* 0y001xxxxx */) { - /* 16-bit header */ - byte = buf[1]; - if (byte == SPE_HEADER1_ALIGNMENT) + + if (hdr == SPE_HEADER0_TIMESTAMP) + return arm_spe_get_timestamp(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK1) == SPE_HEADER0_EVENTS) + return arm_spe_get_events(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK1) == SPE_HEADER0_SOURCE) + return arm_spe_get_data_source(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_CONTEXT) + return arm_spe_get_context(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_OP_TYPE) + return arm_spe_get_op_type(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_EXTENDED) { + /* 16-bit extended format header */ + ext_hdr = 1; + + hdr = buf[1]; + if (hdr == SPE_HEADER1_ALIGNMENT) return arm_spe_get_alignment(buf, len, packet); - else if ((byte & SPE_HEADER1_ADDRESS_MASK) == SPE_HEADER1_ADDRESS) - return arm_spe_get_addr(buf, len, 1, packet); - else if ((byte & SPE_HEADER1_COUNTER_MASK) == SPE_HEADER1_COUNTER) - return arm_spe_get_counter(buf, len, 1, packet); } + /* + * The short format header's byte 0 or the extended format header's + * byte 1 has been assigned to 'hdr', which uses the same encoding for + * address packet and counter packet, so don't need to distinguish if + * it's short format or extended format and handle in once. + */ + if ((hdr & SPE_HEADER0_MASK3) == SPE_HEADER0_ADDRESS) + return arm_spe_get_addr(buf, len, ext_hdr, packet); + + if ((hdr & SPE_HEADER0_MASK3) == SPE_HEADER0_COUNTER) + return arm_spe_get_counter(buf, len, ext_hdr, packet); + return ARM_SPE_BAD_PACKET; } @@ -271,192 +248,286 @@ int arm_spe_get_packet(const unsigned char *buf, size_t len, return ret; } +static int arm_spe_pkt_out_string(int *err, char **buf_p, size_t *blen, + const char *fmt, ...) +{ + va_list ap; + int ret; + + /* Bail out if any error occurred */ + if (err && *err) + return *err; + + va_start(ap, fmt); + ret = vsnprintf(*buf_p, *blen, fmt, ap); + va_end(ap); + + if (ret < 0) { + if (err && !*err) + *err = ret; + + /* + * A return value of *blen or more means that the output was + * truncated and the buffer is overrun. + */ + } else if ((size_t)ret >= *blen) { + (*buf_p)[*blen - 1] = '\0'; + + /* + * Set *err to 'ret' to avoid overflow if tries to + * fill this buffer sequentially. + */ + if (err && !*err) + *err = ret; + } else { + *buf_p += ret; + *blen -= ret; + } + + return ret; +} + +static int arm_spe_pkt_desc_event(const struct arm_spe_pkt *packet, + char *buf, size_t buf_len) +{ + u64 payload = packet->payload; + int err = 0; + + arm_spe_pkt_out_string(&err, &buf, &buf_len, "EV"); + + if (payload & BIT(EV_EXCEPTION_GEN)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " EXCEPTION-GEN"); + if (payload & BIT(EV_RETIRED)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " RETIRED"); + if (payload & BIT(EV_L1D_ACCESS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " L1D-ACCESS"); + if (payload & BIT(EV_L1D_REFILL)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " L1D-REFILL"); + if (payload & BIT(EV_TLB_ACCESS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " TLB-ACCESS"); + if (payload & BIT(EV_TLB_WALK)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " TLB-REFILL"); + if (payload & BIT(EV_NOT_TAKEN)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " NOT-TAKEN"); + if (payload & BIT(EV_MISPRED)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " MISPRED"); + if (payload & BIT(EV_LLC_ACCESS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " LLC-ACCESS"); + if (payload & BIT(EV_LLC_MISS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " LLC-REFILL"); + if (payload & BIT(EV_REMOTE_ACCESS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " REMOTE-ACCESS"); + if (payload & BIT(EV_ALIGNMENT)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " ALIGNMENT"); + if (payload & BIT(EV_PARTIAL_PREDICATE)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-PARTIAL-PRED"); + if (payload & BIT(EV_EMPTY_PREDICATE)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-EMPTY-PRED"); + + return err; +} + +static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, + char *buf, size_t buf_len) +{ + u64 payload = packet->payload; + int err = 0; + + switch (packet->index) { + case SPE_OP_PKT_HDR_CLASS_OTHER: + if (SPE_OP_PKT_IS_OTHER_SVE_OP(payload)) { + arm_spe_pkt_out_string(&err, &buf, &buf_len, "SVE-OTHER"); + + /* SVE effective vector length */ + arm_spe_pkt_out_string(&err, &buf, &buf_len, " EVLEN %d", + SPE_OP_PKG_SVE_EVL(payload)); + + if (payload & SPE_OP_PKT_SVE_FP) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " FP"); + if (payload & SPE_OP_PKT_SVE_PRED) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED"); + } else { + arm_spe_pkt_out_string(&err, &buf, &buf_len, "OTHER"); + arm_spe_pkt_out_string(&err, &buf, &buf_len, " %s", + payload & SPE_OP_PKT_COND ? + "COND-SELECT" : "INSN-OTHER"); + } + break; + case SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC: + arm_spe_pkt_out_string(&err, &buf, &buf_len, + payload & 0x1 ? "ST" : "LD"); + + if (SPE_OP_PKT_IS_LDST_ATOMIC(payload)) { + if (payload & SPE_OP_PKT_AT) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " AT"); + if (payload & SPE_OP_PKT_EXCL) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " EXCL"); + if (payload & SPE_OP_PKT_AR) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " AR"); + } + + switch (SPE_OP_PKT_LDST_SUBCLASS_GET(payload)) { + case SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SIMD-FP"); + break; + case SPE_OP_PKT_LDST_SUBCLASS_GP_REG: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " GP-REG"); + break; + case SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " UNSPEC-REG"); + break; + case SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " NV-SYSREG"); + break; + default: + break; + } + + if (SPE_OP_PKT_IS_LDST_SVE(payload)) { + /* SVE effective vector length */ + arm_spe_pkt_out_string(&err, &buf, &buf_len, " EVLEN %d", + SPE_OP_PKG_SVE_EVL(payload)); + + if (payload & SPE_OP_PKT_SVE_PRED) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED"); + if (payload & SPE_OP_PKT_SVE_SG) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SG"); + } + break; + case SPE_OP_PKT_HDR_CLASS_BR_ERET: + arm_spe_pkt_out_string(&err, &buf, &buf_len, "B"); + + if (payload & SPE_OP_PKT_COND) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " COND"); + + if (SPE_OP_PKT_IS_INDIRECT_BRANCH(payload)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " IND"); + + break; + default: + /* Unknown index */ + err = -1; + break; + } + + return err; +} + +static int arm_spe_pkt_desc_addr(const struct arm_spe_pkt *packet, + char *buf, size_t buf_len) +{ + int ns, el, idx = packet->index; + int ch, pat; + u64 payload = packet->payload; + int err = 0; + + switch (idx) { + case SPE_ADDR_PKT_HDR_INDEX_INS: + case SPE_ADDR_PKT_HDR_INDEX_BRANCH: + ns = !!SPE_ADDR_PKT_GET_NS(payload); + el = SPE_ADDR_PKT_GET_EL(payload); + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); + arm_spe_pkt_out_string(&err, &buf, &buf_len, + "%s 0x%llx el%d ns=%d", + (idx == 1) ? "TGT" : "PC", payload, el, ns); + break; + case SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT: + arm_spe_pkt_out_string(&err, &buf, &buf_len, + "VA 0x%llx", payload); + break; + case SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS: + ns = !!SPE_ADDR_PKT_GET_NS(payload); + ch = !!SPE_ADDR_PKT_GET_CH(payload); + pat = SPE_ADDR_PKT_GET_PAT(payload); + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); + arm_spe_pkt_out_string(&err, &buf, &buf_len, + "PA 0x%llx ns=%d ch=%d pat=%x", + payload, ns, ch, pat); + break; + default: + /* Unknown index */ + err = -1; + break; + } + + return err; +} + +static int arm_spe_pkt_desc_counter(const struct arm_spe_pkt *packet, + char *buf, size_t buf_len) +{ + u64 payload = packet->payload; + const char *name = arm_spe_pkt_name(packet->type); + int err = 0; + + arm_spe_pkt_out_string(&err, &buf, &buf_len, "%s %d ", name, + (unsigned short)payload); + + switch (packet->index) { + case SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT: + arm_spe_pkt_out_string(&err, &buf, &buf_len, "TOT"); + break; + case SPE_CNT_PKT_HDR_INDEX_ISSUE_LAT: + arm_spe_pkt_out_string(&err, &buf, &buf_len, "ISSUE"); + break; + case SPE_CNT_PKT_HDR_INDEX_TRANS_LAT: + arm_spe_pkt_out_string(&err, &buf, &buf_len, "XLAT"); + break; + default: + break; + } + + return err; +} + int arm_spe_pkt_desc(const struct arm_spe_pkt *packet, char *buf, size_t buf_len) { - int ret, ns, el, idx = packet->index; + int idx = packet->index; unsigned long long payload = packet->payload; const char *name = arm_spe_pkt_name(packet->type); + char *buf_orig = buf; + size_t blen = buf_len; + int err = 0; switch (packet->type) { case ARM_SPE_BAD: case ARM_SPE_PAD: case ARM_SPE_END: - return snprintf(buf, buf_len, "%s", name); - case ARM_SPE_EVENTS: { - size_t blen = buf_len; - - ret = 0; - ret = snprintf(buf, buf_len, "EV"); - buf += ret; - blen -= ret; - if (payload & 0x1) { - ret = snprintf(buf, buf_len, " EXCEPTION-GEN"); - buf += ret; - blen -= ret; - } - if (payload & 0x2) { - ret = snprintf(buf, buf_len, " RETIRED"); - buf += ret; - blen -= ret; - } - if (payload & 0x4) { - ret = snprintf(buf, buf_len, " L1D-ACCESS"); - buf += ret; - blen -= ret; - } - if (payload & 0x8) { - ret = snprintf(buf, buf_len, " L1D-REFILL"); - buf += ret; - blen -= ret; - } - if (payload & 0x10) { - ret = snprintf(buf, buf_len, " TLB-ACCESS"); - buf += ret; - blen -= ret; - } - if (payload & 0x20) { - ret = snprintf(buf, buf_len, " TLB-REFILL"); - buf += ret; - blen -= ret; - } - if (payload & 0x40) { - ret = snprintf(buf, buf_len, " NOT-TAKEN"); - buf += ret; - blen -= ret; - } - if (payload & 0x80) { - ret = snprintf(buf, buf_len, " MISPRED"); - buf += ret; - blen -= ret; - } - if (idx > 1) { - if (payload & 0x100) { - ret = snprintf(buf, buf_len, " LLC-ACCESS"); - buf += ret; - blen -= ret; - } - if (payload & 0x200) { - ret = snprintf(buf, buf_len, " LLC-REFILL"); - buf += ret; - blen -= ret; - } - if (payload & 0x400) { - ret = snprintf(buf, buf_len, " REMOTE-ACCESS"); - buf += ret; - blen -= ret; - } - } - if (ret < 0) - return ret; - blen -= ret; - return buf_len - blen; - } + arm_spe_pkt_out_string(&err, &buf, &blen, "%s", name); + break; + case ARM_SPE_EVENTS: + err = arm_spe_pkt_desc_event(packet, buf, buf_len); + break; case ARM_SPE_OP_TYPE: - switch (idx) { - case 0: return snprintf(buf, buf_len, "%s", payload & 0x1 ? - "COND-SELECT" : "INSN-OTHER"); - case 1: { - size_t blen = buf_len; - - if (payload & 0x1) - ret = snprintf(buf, buf_len, "ST"); - else - ret = snprintf(buf, buf_len, "LD"); - buf += ret; - blen -= ret; - if (payload & 0x2) { - if (payload & 0x4) { - ret = snprintf(buf, buf_len, " AT"); - buf += ret; - blen -= ret; - } - if (payload & 0x8) { - ret = snprintf(buf, buf_len, " EXCL"); - buf += ret; - blen -= ret; - } - if (payload & 0x10) { - ret = snprintf(buf, buf_len, " AR"); - buf += ret; - blen -= ret; - } - } else if (payload & 0x4) { - ret = snprintf(buf, buf_len, " SIMD-FP"); - buf += ret; - blen -= ret; - } - if (ret < 0) - return ret; - blen -= ret; - return buf_len - blen; - } - case 2: { - size_t blen = buf_len; - - ret = snprintf(buf, buf_len, "B"); - buf += ret; - blen -= ret; - if (payload & 0x1) { - ret = snprintf(buf, buf_len, " COND"); - buf += ret; - blen -= ret; - } - if (payload & 0x2) { - ret = snprintf(buf, buf_len, " IND"); - buf += ret; - blen -= ret; - } - if (ret < 0) - return ret; - blen -= ret; - return buf_len - blen; - } - default: return 0; - } + err = arm_spe_pkt_desc_op_type(packet, buf, buf_len); + break; case ARM_SPE_DATA_SOURCE: case ARM_SPE_TIMESTAMP: - return snprintf(buf, buf_len, "%s %lld", name, payload); + arm_spe_pkt_out_string(&err, &buf, &blen, "%s %lld", name, payload); + break; case ARM_SPE_ADDRESS: - switch (idx) { - case 0: - case 1: ns = !!(packet->payload & NS_FLAG); - el = (packet->payload & EL_FLAG) >> 61; - payload &= ~(0xffULL << 56); - return snprintf(buf, buf_len, "%s 0x%llx el%d ns=%d", - (idx == 1) ? "TGT" : "PC", payload, el, ns); - case 2: return snprintf(buf, buf_len, "VA 0x%llx", payload); - case 3: ns = !!(packet->payload & NS_FLAG); - payload &= ~(0xffULL << 56); - return snprintf(buf, buf_len, "PA 0x%llx ns=%d", - payload, ns); - default: return 0; - } + err = arm_spe_pkt_desc_addr(packet, buf, buf_len); + break; case ARM_SPE_CONTEXT: - return snprintf(buf, buf_len, "%s 0x%lx el%d", name, - (unsigned long)payload, idx + 1); - case ARM_SPE_COUNTER: { - size_t blen = buf_len; - - ret = snprintf(buf, buf_len, "%s %d ", name, - (unsigned short)payload); - buf += ret; - blen -= ret; - switch (idx) { - case 0: ret = snprintf(buf, buf_len, "TOT"); break; - case 1: ret = snprintf(buf, buf_len, "ISSUE"); break; - case 2: ret = snprintf(buf, buf_len, "XLAT"); break; - default: ret = 0; - } - if (ret < 0) - return ret; - blen -= ret; - return buf_len - blen; - } + arm_spe_pkt_out_string(&err, &buf, &blen, "%s 0x%lx el%d", + name, (unsigned long)payload, idx + 1); + break; + case ARM_SPE_COUNTER: + err = arm_spe_pkt_desc_counter(packet, buf, buf_len); + break; default: + /* Unknown packet type */ + err = -1; break; } - return snprintf(buf, buf_len, "%s 0x%llx (%d)", - name, payload, packet->index); + /* Output raw data if detect any error */ + if (err) { + err = 0; + arm_spe_pkt_out_string(&err, &buf_orig, &buf_len, "%s 0x%llx (%d)", + name, payload, packet->index); + } + + return err; } diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h index 4c870521b8eb0..9b970e7bf1e21 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h @@ -36,19 +36,115 @@ struct arm_spe_pkt { uint64_t payload; }; -#define SPE_ADDR_PKT_HDR_INDEX_INS (0x0) -#define SPE_ADDR_PKT_HDR_INDEX_BRANCH (0x1) -#define SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT (0x2) -#define SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS (0x3) - -#define SPE_ADDR_PKT_NS BIT(7) -#define SPE_ADDR_PKT_CH BIT(6) -#define SPE_ADDR_PKT_EL_OFFSET (5) -#define SPE_ADDR_PKT_EL_MASK (0x3 << SPE_ADDR_PKT_EL_OFFSET) -#define SPE_ADDR_PKT_EL0 (0) -#define SPE_ADDR_PKT_EL1 (1) -#define SPE_ADDR_PKT_EL2 (2) -#define SPE_ADDR_PKT_EL3 (3) +/* Short header (HEADER0) and extended header (HEADER1) */ +#define SPE_HEADER0_PAD 0x0 +#define SPE_HEADER0_END 0x1 +#define SPE_HEADER0_TIMESTAMP 0x71 +/* Mask for event & data source */ +#define SPE_HEADER0_MASK1 (GENMASK_ULL(7, 6) | GENMASK_ULL(3, 0)) +#define SPE_HEADER0_EVENTS 0x42 +#define SPE_HEADER0_SOURCE 0x43 +/* Mask for context & operation */ +#define SPE_HEADER0_MASK2 GENMASK_ULL(7, 2) +#define SPE_HEADER0_CONTEXT 0x64 +#define SPE_HEADER0_OP_TYPE 0x48 +/* Mask for extended format */ +#define SPE_HEADER0_EXTENDED 0x20 +/* Mask for address & counter */ +#define SPE_HEADER0_MASK3 GENMASK_ULL(7, 3) +#define SPE_HEADER0_ADDRESS 0xb0 +#define SPE_HEADER0_COUNTER 0x98 +#define SPE_HEADER1_ALIGNMENT 0x0 + +#define SPE_HDR_SHORT_INDEX(h) ((h) & GENMASK_ULL(2, 0)) +#define SPE_HDR_EXTENDED_INDEX(h0, h1) (((h0) & GENMASK_ULL(1, 0)) << 3 | \ + SPE_HDR_SHORT_INDEX(h1)) + +/* Address packet header */ +#define SPE_ADDR_PKT_HDR_INDEX_INS 0x0 +#define SPE_ADDR_PKT_HDR_INDEX_BRANCH 0x1 +#define SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT 0x2 +#define SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS 0x3 + +/* Address packet payload */ +#define SPE_ADDR_PKT_ADDR_BYTE7_SHIFT 56 +#define SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(v) ((v) & GENMASK_ULL(55, 0)) +#define SPE_ADDR_PKT_ADDR_GET_BYTE_6(v) (((v) & GENMASK_ULL(55, 48)) >> 48) + +#define SPE_ADDR_PKT_GET_NS(v) (((v) & BIT_ULL(63)) >> 63) +#define SPE_ADDR_PKT_GET_EL(v) (((v) & GENMASK_ULL(62, 61)) >> 61) +#define SPE_ADDR_PKT_GET_CH(v) (((v) & BIT_ULL(62)) >> 62) +#define SPE_ADDR_PKT_GET_PAT(v) (((v) & GENMASK_ULL(59, 56)) >> 56) + +#define SPE_ADDR_PKT_EL0 0 +#define SPE_ADDR_PKT_EL1 1 +#define SPE_ADDR_PKT_EL2 2 +#define SPE_ADDR_PKT_EL3 3 + +/* Context packet header */ +#define SPE_CTX_PKT_HDR_INDEX(h) ((h) & GENMASK_ULL(1, 0)) + +/* Counter packet header */ +#define SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT 0x0 +#define SPE_CNT_PKT_HDR_INDEX_ISSUE_LAT 0x1 +#define SPE_CNT_PKT_HDR_INDEX_TRANS_LAT 0x2 + +/* Event packet payload */ +enum arm_spe_events { + EV_EXCEPTION_GEN = 0, + EV_RETIRED = 1, + EV_L1D_ACCESS = 2, + EV_L1D_REFILL = 3, + EV_TLB_ACCESS = 4, + EV_TLB_WALK = 5, + EV_NOT_TAKEN = 6, + EV_MISPRED = 7, + EV_LLC_ACCESS = 8, + EV_LLC_MISS = 9, + EV_REMOTE_ACCESS = 10, + EV_ALIGNMENT = 11, + EV_PARTIAL_PREDICATE = 17, + EV_EMPTY_PREDICATE = 18, +}; + +/* Operation packet header */ +#define SPE_OP_PKT_HDR_CLASS(h) ((h) & GENMASK_ULL(1, 0)) +#define SPE_OP_PKT_HDR_CLASS_OTHER 0x0 +#define SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC 0x1 +#define SPE_OP_PKT_HDR_CLASS_BR_ERET 0x2 + +#define SPE_OP_PKT_IS_OTHER_SVE_OP(v) (((v) & (BIT(7) | BIT(3) | BIT(0))) == 0x8) + +#define SPE_OP_PKT_COND BIT(0) + +#define SPE_OP_PKT_LDST_SUBCLASS_GET(v) ((v) & GENMASK_ULL(7, 1)) +#define SPE_OP_PKT_LDST_SUBCLASS_GP_REG 0x0 +#define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP 0x4 +#define SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG 0x10 +#define SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG 0x30 + +#define SPE_OP_PKT_IS_LDST_ATOMIC(v) (((v) & (GENMASK_ULL(7, 5) | BIT(1))) == 0x2) + +#define SPE_OP_PKT_AR BIT(4) +#define SPE_OP_PKT_EXCL BIT(3) +#define SPE_OP_PKT_AT BIT(2) +#define SPE_OP_PKT_ST BIT(0) + +#define SPE_OP_PKT_IS_LDST_SVE(v) (((v) & (BIT(3) | BIT(1))) == 0x8) + +#define SPE_OP_PKT_SVE_SG BIT(7) +/* + * SVE effective vector length (EVL) is stored in byte 0 bits [6:4]; + * the length is rounded up to a power of two and use 32 as one step, + * so EVL calculation is: + * + * 32 * (2 ^ bits [6:4]) = 32 << (bits [6:4]) + */ +#define SPE_OP_PKG_SVE_EVL(v) (32 << (((v) & GENMASK_ULL(6, 4)) >> 4)) +#define SPE_OP_PKT_SVE_PRED BIT(2) +#define SPE_OP_PKT_SVE_FP BIT(1) + +#define SPE_OP_PKT_IS_INDIRECT_BRANCH(v) (((v) & GENMASK_ULL(7, 1)) == 0x2) const char *arm_spe_pkt_name(enum arm_spe_pkt_type); diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 3882a5360ada4..8901a1656a41d 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -113,7 +113,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused, if (ret > 0) { ret = arm_spe_pkt_desc(&packet, desc, ARM_SPE_PKT_DESC_MAX); - if (ret > 0) + if (!ret) color_fprintf(stdout, color, " %s\n", desc); } else { color_fprintf(stdout, color, " Bad packet!\n"); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 42a85c86421d7..a608784981399 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -62,9 +62,7 @@ * Make a group from 'leader' to 'last', requiring that the events were not * already grouped to a different leader. */ -static int perf_evlist__regroup(struct evlist *evlist, - struct evsel *leader, - struct evsel *last) +static int evlist__regroup(struct evlist *evlist, struct evsel *leader, struct evsel *last) { struct evsel *evsel; bool grp; @@ -658,8 +656,7 @@ int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx) if (evsel->core.attr.type == itr->pmu->type) { if (evsel->disabled) return 0; - return perf_evlist__enable_event_idx(itr->evlist, evsel, - idx); + return evlist__enable_event_idx(itr->evlist, evsel, idx); } } return -EINVAL; @@ -776,7 +773,7 @@ no_opt: evsel->core.attr.aux_sample_size = term->val.aux_sample_size; /* If possible, group with the AUX event */ if (aux_evsel && evsel->core.attr.aux_sample_size) - perf_evlist__regroup(evlist, aux_evsel, evsel); + evlist__regroup(evlist, aux_evsel, evsel); } } @@ -1017,7 +1014,7 @@ struct auxtrace_queue *auxtrace_queues__sample_queue(struct auxtrace_queues *que if (!id) return NULL; - sid = perf_evlist__id2sid(session->evlist, id); + sid = evlist__id2sid(session->evlist, id); if (!sid) return NULL; @@ -1047,7 +1044,7 @@ int auxtrace_queues__add_sample(struct auxtrace_queues *queues, if (!id) return -EINVAL; - sid = perf_evlist__id2sid(session->evlist, id); + sid = evlist__id2sid(session->evlist, id); if (!sid) return -ENOENT; @@ -1082,7 +1079,7 @@ static int auxtrace_queue_data_cb(struct perf_session *session, if (!qd->samples || event->header.type != PERF_RECORD_SAMPLE) return 0; - err = perf_evlist__parse_sample(session->evlist, event, &sample); + err = evlist__parse_sample(session->evlist, event, &sample); if (err) return err; @@ -1333,6 +1330,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts, synth_opts->flc = true; synth_opts->llc = true; synth_opts->tlb = true; + synth_opts->mem = true; synth_opts->remote_access = true; if (no_sample) { @@ -1554,6 +1552,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'a': synth_opts->remote_access = true; break; + case 'M': + synth_opts->mem = true; + break; case 'q': synth_opts->quick += 1; break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 951d2d14cf249..7e5c9e1552bd4 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -88,6 +88,7 @@ enum itrace_period_type { * @llc: whether to synthesize last level cache events * @tlb: whether to synthesize TLB events * @remote_access: whether to synthesize remote access events + * @mem: whether to synthesize memory events * @callchain_sz: maximum callchain size * @last_branch_sz: branch context size * @period: 'instructions' events period @@ -126,6 +127,7 @@ struct itrace_synth_opts { bool llc; bool tlb; bool remote_access; + bool mem; unsigned int callchain_sz; unsigned int last_branch_sz; unsigned long long period; diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 3742511a08d15..57d58c81a5f8e 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -526,7 +526,7 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env) */ attr.wakeup_watermark = 1; - return perf_evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env); + return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env); } void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 2feb751516ab8..9087f1bffd3d6 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -328,12 +328,6 @@ config_bpf_program(struct bpf_program *prog) probe_conf.no_inlines = false; probe_conf.force_add = false; - config_str = bpf_program__title(prog, false); - if (IS_ERR(config_str)) { - pr_debug("bpf: unable to get title for program\n"); - return PTR_ERR(config_str); - } - priv = calloc(sizeof(*priv), 1); if (!priv) { pr_debug("bpf: failed to alloc priv\n"); @@ -341,6 +335,7 @@ config_bpf_program(struct bpf_program *prog) } pev = &priv->pev; + config_str = bpf_program__section_name(prog); pr_debug("bpf: config program '%s'\n", config_str); err = parse_prog_config(config_str, &main_str, &is_tp, pev); if (err) @@ -454,10 +449,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n, if (err) { const char *title; - title = bpf_program__title(prog, false); - if (!title) - title = "[unknown]"; - + title = bpf_program__section_name(prog); pr_debug("Failed to generate prologue for program %s\n", title); return err; @@ -1066,12 +1058,11 @@ __bpf_map__config_event(struct bpf_map *map, struct parse_events_term *term, struct evlist *evlist) { - struct evsel *evsel; const struct bpf_map_def *def; struct bpf_map_op *op; const char *map_name = bpf_map__name(map); + struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str); - evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str); if (!evsel) { pr_debug("Event (for '%s') '%s' doesn't exist\n", map_name, term->val.str); diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index 25251d63164ce..5d1c725cea295 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -8,6 +8,8 @@ #include <linux/compiler.h> #include <linux/err.h> + +#ifdef HAVE_LIBBPF_SUPPORT #include <bpf/libbpf.h> enum bpf_loader_errno { @@ -38,6 +40,7 @@ enum bpf_loader_errno { BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG, /* Index too large */ __BPF_LOADER_ERRNO__END, }; +#endif // HAVE_LIBBPF_SUPPORT struct evsel; struct evlist; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 31207b6e20667..02df36b30ac54 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -37,6 +37,8 @@ #include <linux/ctype.h> #include <linux/zalloc.h> +#include <linux/string.h> +#include <asm/bug.h> static bool no_buildid_cache; @@ -95,13 +97,15 @@ struct perf_tool build_id__mark_dso_hit_ops = { .ordered_events = true, }; -int build_id__sprintf(const u8 *build_id, int len, char *bf) +int build_id__sprintf(const struct build_id *build_id, char *bf) { char *bid = bf; - const u8 *raw = build_id; - int i; + const u8 *raw = build_id->data; + size_t i; + + bf[0] = 0x0; - for (i = 0; i < len; ++i) { + for (i = 0; i < build_id->size; ++i) { sprintf(bid, "%02x", *raw); ++raw; bid += 2; @@ -113,7 +117,7 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf) int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id) { char notes[PATH_MAX]; - u8 build_id[BUILD_ID_SIZE]; + struct build_id bid; int ret; if (!root_dir) @@ -121,25 +125,23 @@ int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id) scnprintf(notes, sizeof(notes), "%s/sys/kernel/notes", root_dir); - ret = sysfs__read_build_id(notes, build_id, sizeof(build_id)); + ret = sysfs__read_build_id(notes, &bid); if (ret < 0) return ret; - return build_id__sprintf(build_id, sizeof(build_id), sbuild_id); + return build_id__sprintf(&bid, sbuild_id); } int filename__sprintf_build_id(const char *pathname, char *sbuild_id) { - u8 build_id[BUILD_ID_SIZE]; + struct build_id bid; int ret; - ret = filename__read_build_id(pathname, build_id, sizeof(build_id)); + ret = filename__read_build_id(pathname, &bid); if (ret < 0) return ret; - else if (ret != sizeof(build_id)) - return -EINVAL; - return build_id__sprintf(build_id, sizeof(build_id), sbuild_id); + return build_id__sprintf(&bid, sbuild_id); } /* asnprintf consolidates asprintf and snprintf */ @@ -259,10 +261,9 @@ static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso, "debug" : "elf")); } -char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, - bool is_debug) +char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug, bool is_kallsyms) { - bool is_kallsyms = dso__is_kallsyms((struct dso *)dso); bool is_vdso = dso__is_vdso((struct dso *)dso); char sbuild_id[SBUILD_ID_SIZE]; char *linkname; @@ -272,7 +273,7 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, if (!dso->has_build_id) return NULL; - build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + build_id__sprintf(&dso->bid, sbuild_id); linkname = build_id_cache__linkname(sbuild_id, NULL, 0); if (!linkname) return NULL; @@ -291,13 +292,21 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, return bf; } +char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug) +{ + bool is_kallsyms = dso__is_kallsyms((struct dso *)dso); + + return __dso__build_id_filename(dso, bf, size, is_debug, is_kallsyms); +} + #define dsos__for_each_with_build_id(pos, head) \ list_for_each_entry(pos, head, node) \ if (!pos->has_build_id) \ continue; \ else -static int write_buildid(const char *name, size_t name_len, u8 *build_id, +static int write_buildid(const char *name, size_t name_len, struct build_id *bid, pid_t pid, u16 misc, struct feat_fd *fd) { int err; @@ -308,7 +317,9 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id, len = PERF_ALIGN(len, NAME_ALIGN); memset(&b, 0, sizeof(b)); - memcpy(&b.build_id, build_id, BUILD_ID_SIZE); + memcpy(&b.data, bid->data, bid->size); + b.size = (u8) bid->size; + misc |= PERF_RECORD_MISC_BUILD_ID_SIZE; b.pid = pid; b.header.misc = misc; b.header.size = sizeof(b) + len; @@ -355,7 +366,7 @@ static int machine__write_buildid_table(struct machine *machine, in_kernel = pos->kernel || is_kernel_module(name, PERF_RECORD_MISC_CPUMODE_UNKNOWN); - err = write_buildid(name, name_len, pos->build_id, machine->pid, + err = write_buildid(name, name_len, &pos->bid, machine->pid, in_kernel ? kmisc : umisc, fd); if (err) break; @@ -660,24 +671,15 @@ out: return realname; } -int build_id_cache__add_s(const char *sbuild_id, const char *name, - struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) +int +build_id_cache__add(const char *sbuild_id, const char *name, const char *realname, + struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) { const size_t size = PATH_MAX; - char *realname = NULL, *filename = NULL, *dir_name = NULL, - *linkname = zalloc(size), *tmp; + char *filename = NULL, *dir_name = NULL, *linkname = zalloc(size), *tmp; char *debugfile = NULL; int err = -1; - if (!is_kallsyms) { - if (!is_vdso) - realname = nsinfo__realpath(name, nsi); - else - realname = realpath(name, NULL); - if (!realname) - goto out_free; - } - dir_name = build_id_cache__cachedir(sbuild_id, name, nsi, is_kallsyms, is_vdso); if (!dir_name) @@ -751,8 +753,25 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, tmp = dir_name + strlen(buildid_dir) - 5; memcpy(tmp, "../..", 5); - if (symlink(tmp, linkname) == 0) + if (symlink(tmp, linkname) == 0) { err = 0; + } else if (errno == EEXIST) { + char path[PATH_MAX]; + ssize_t len; + + len = readlink(linkname, path, sizeof(path) - 1); + if (len <= 0) { + pr_err("Cant read link: %s\n", linkname); + goto out_free; + } + path[len] = '\0'; + + if (strcmp(tmp, path)) { + pr_debug("build <%s> already linked to %s\n", + sbuild_id, linkname); + } + err = 0; + } /* Update SDT cache : error is just warned */ if (realname && @@ -760,8 +779,6 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, pr_debug4("Failed to update/scan SDT cache for %s\n", realname); out_free: - if (!is_kallsyms) - free(realname); free(filename); free(debugfile); free(dir_name); @@ -769,13 +786,36 @@ out_free: return err; } -static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, +int build_id_cache__add_s(const char *sbuild_id, const char *name, + struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) +{ + char *realname = NULL; + int err = -1; + + if (!is_kallsyms) { + if (!is_vdso) + realname = nsinfo__realpath(name, nsi); + else + realname = realpath(name, NULL); + if (!realname) + goto out_free; + } + + err = build_id_cache__add(sbuild_id, name, realname, nsi, is_kallsyms, is_vdso); + +out_free: + if (!is_kallsyms) + free(realname); + return err; +} + +static int build_id_cache__add_b(const struct build_id *bid, const char *name, struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) { char sbuild_id[SBUILD_ID_SIZE]; - build_id__sprintf(build_id, build_id_size, sbuild_id); + build_id__sprintf(bid, sbuild_id); return build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms, is_vdso); @@ -831,57 +871,54 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *dso, struct machine *machine) +static int dso__cache_build_id(struct dso *dso, struct machine *machine, + void *priv __maybe_unused) { bool is_kallsyms = dso__is_kallsyms(dso); bool is_vdso = dso__is_vdso(dso); const char *name = dso->long_name; + if (!dso->has_build_id) + return 0; + if (dso__is_kcore(dso)) { is_kallsyms = true; name = machine->mmap_name; } - return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, - dso->nsinfo, is_kallsyms, is_vdso); + return build_id_cache__add_b(&dso->bid, name, dso->nsinfo, + is_kallsyms, is_vdso); } -static int __dsos__cache_build_ids(struct list_head *head, - struct machine *machine) +static int +machines__for_each_dso(struct machines *machines, machine__dso_t fn, void *priv) { - struct dso *pos; - int err = 0; - - dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, machine)) - err = -1; + int ret = machine__for_each_dso(&machines->host, fn, priv); + struct rb_node *nd; - return err; -} + for (nd = rb_first_cached(&machines->guests); nd; + nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); -static int machine__cache_build_ids(struct machine *machine) -{ - return __dsos__cache_build_ids(&machine->dsos.head, machine); + ret |= machine__for_each_dso(pos, fn, priv); + } + return ret ? -1 : 0; } -int perf_session__cache_build_ids(struct perf_session *session) +int __perf_session__cache_build_ids(struct perf_session *session, + machine__dso_t fn, void *priv) { - struct rb_node *nd; - int ret; - if (no_buildid_cache) return 0; if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST) return -1; - ret = machine__cache_build_ids(&session->machines.host); + return machines__for_each_dso(&session->machines, fn, priv) ? -1 : 0; +} - for (nd = rb_first_cached(&session->machines.guests); nd; - nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret |= machine__cache_build_ids(pos); - } - return ret ? -1 : 0; +int perf_session__cache_build_ids(struct perf_session *session) +{ + return __perf_session__cache_build_ids(session, dso__cache_build_id, NULL); } static bool machine__read_build_ids(struct machine *machine, bool with_hits) @@ -902,3 +939,15 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) return ret; } + +void build_id__init(struct build_id *bid, const u8 *data, size_t size) +{ + WARN_ON(size > BUILD_ID_SIZE); + memcpy(bid->data, data, size); + bid->size = size; +} + +bool build_id__is_defined(const struct build_id *bid) +{ + return bid && bid->size ? !!memchr_inv(bid->data, 0, bid->size) : false; +} diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index aad419bb165cd..02613f4b2c291 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -5,16 +5,24 @@ #define BUILD_ID_SIZE 20 #define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1) +#include "machine.h" #include "tool.h" #include <linux/types.h> +struct build_id { + u8 data[BUILD_ID_SIZE]; + size_t size; +}; + struct nsinfo; extern struct perf_tool build_id__mark_dso_hit_ops; struct dso; struct feat_fd; -int build_id__sprintf(const u8 *build_id, int len, char *bf); +void build_id__init(struct build_id *bid, const u8 *data, size_t size); +int build_id__sprintf(const struct build_id *build_id, char *bf); +bool build_id__is_defined(const struct build_id *bid); int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id); int filename__sprintf_build_id(const char *pathname, char *sbuild_id); char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, @@ -22,6 +30,8 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, bool is_debug); +char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug, bool is_kallsyms); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct evsel *evsel, @@ -29,10 +39,16 @@ int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, int dsos__hit_all(struct perf_session *session); +int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, struct evsel *evsel, + struct machine *machine); + bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); int perf_session__write_buildid_table(struct perf_session *session, struct feat_fd *fd); int perf_session__cache_build_ids(struct perf_session *session); +int __perf_session__cache_build_ids(struct perf_session *session, + machine__dso_t fn, void *priv); char *build_id_cache__origname(const char *sbuild_id); char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size); @@ -47,6 +63,8 @@ char *build_id_cache__complement(const char *incomplete_sbuild_id); int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi, struct strlist **result); bool build_id_cache__cached(const char *sbuild_id); +int build_id_cache__add(const char *sbuild_id, const char *name, const char *realname, + struct nsinfo *nsi, bool is_kallsyms, bool is_vdso); int build_id_cache__add_s(const char *sbuild_id, const char *name, struct nsinfo *nsi, bool is_kallsyms, bool is_vdso); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 2775b752f2fa6..1b60985690bba 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1613,3 +1613,102 @@ void callchain_param_setup(u64 sample_type) callchain_param.record_mode = CALLCHAIN_FP; } } + +static bool chain_match(struct callchain_list *base_chain, + struct callchain_list *pair_chain) +{ + enum match_result match; + + match = match_chain_strings(base_chain->srcline, + pair_chain->srcline); + if (match != MATCH_ERROR) + return match == MATCH_EQ; + + match = match_chain_dso_addresses(base_chain->ms.map, + base_chain->ip, + pair_chain->ms.map, + pair_chain->ip); + + return match == MATCH_EQ; +} + +bool callchain_cnode_matched(struct callchain_node *base_cnode, + struct callchain_node *pair_cnode) +{ + struct callchain_list *base_chain, *pair_chain; + bool match = false; + + pair_chain = list_first_entry(&pair_cnode->val, + struct callchain_list, + list); + + list_for_each_entry(base_chain, &base_cnode->val, list) { + if (&pair_chain->list == &pair_cnode->val) + return false; + + if (!base_chain->srcline || !pair_chain->srcline) { + pair_chain = list_next_entry(pair_chain, list); + continue; + } + + match = chain_match(base_chain, pair_chain); + if (!match) + return false; + + pair_chain = list_next_entry(pair_chain, list); + } + + /* + * Say chain1 is ABC, chain2 is ABCD, we consider they are + * not fully matched. + */ + if (pair_chain && (&pair_chain->list != &pair_cnode->val)) + return false; + + return match; +} + +static u64 count_callchain_hits(struct hist_entry *he) +{ + struct rb_root *root = &he->sorted_chain; + struct rb_node *rb_node = rb_first(root); + struct callchain_node *node; + u64 chain_hits = 0; + + while (rb_node) { + node = rb_entry(rb_node, struct callchain_node, rb_node); + chain_hits += node->hit; + rb_node = rb_next(rb_node); + } + + return chain_hits; +} + +u64 callchain_total_hits(struct hists *hists) +{ + struct rb_node *next = rb_first_cached(&hists->entries); + u64 chain_hits = 0; + + while (next) { + struct hist_entry *he = rb_entry(next, struct hist_entry, + rb_node); + + chain_hits += count_callchain_hits(he); + next = rb_next(&he->rb_node); + } + + return chain_hits; +} + +s64 callchain_avg_cycles(struct callchain_node *cnode) +{ + struct callchain_list *chain; + s64 cycles = 0; + + list_for_each_entry(chain, &cnode->val, list) { + if (chain->srcline && chain->branch_count) + cycles += chain->cycles_count / chain->branch_count; + } + + return cycles; +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index fe36a9e5ccd14..5824134f983b0 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -13,6 +13,7 @@ struct ip_callchain; struct map; struct perf_sample; struct thread; +struct hists; #define HELP_PAD "\t\t\t\t" @@ -298,4 +299,12 @@ int callchain_branch_counts(struct callchain_root *root, u64 *abort_count, u64 *cycles_count); void callchain_param_setup(u64 sample_type); + +bool callchain_cnode_matched(struct callchain_node *base_cnode, + struct callchain_node *pair_cnode); + +u64 callchain_total_hits(struct hists *hists); + +s64 callchain_avg_cycles(struct callchain_node *cnode); + #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 050dea9f1e884..5dff7e489921b 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -3,6 +3,9 @@ #include "evsel.h" #include "cgroup.h" #include "evlist.h" +#include "rblist.h" +#include "metricgroup.h" +#include "stat.h" #include <linux/zalloc.h> #include <sys/types.h> #include <sys/stat.h> @@ -10,9 +13,19 @@ #include <stdlib.h> #include <string.h> #include <api/fs/fs.h> +#include <ftw.h> +#include <regex.h> int nr_cgroups; +/* used to match cgroup name with patterns */ +struct cgroup_name { + struct list_head list; + bool used; + char name[]; +}; +static LIST_HEAD(cgroup_list); + static int open_cgroup(const char *name) { char path[PATH_MAX + 1]; @@ -48,7 +61,7 @@ static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str return NULL; } -static struct cgroup *cgroup__new(const char *name) +static struct cgroup *cgroup__new(const char *name, bool do_open) { struct cgroup *cgroup = zalloc(sizeof(*cgroup)); @@ -58,9 +71,14 @@ static struct cgroup *cgroup__new(const char *name) cgroup->name = strdup(name); if (!cgroup->name) goto out_err; - cgroup->fd = open_cgroup(name); - if (cgroup->fd == -1) - goto out_free_name; + + if (do_open) { + cgroup->fd = open_cgroup(name); + if (cgroup->fd == -1) + goto out_free_name; + } else { + cgroup->fd = -1; + } } return cgroup; @@ -76,7 +94,7 @@ struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name) { struct cgroup *cgroup = evlist__find_cgroup(evlist, name); - return cgroup ?: cgroup__new(name); + return cgroup ?: cgroup__new(name, true); } static int add_cgroup(struct evlist *evlist, const char *str) @@ -141,6 +159,137 @@ void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup) evsel__set_default_cgroup(evsel, cgroup); } +/* helper function for ftw() in match_cgroups and list_cgroups */ +static int add_cgroup_name(const char *fpath, const struct stat *sb __maybe_unused, + int typeflag) +{ + struct cgroup_name *cn; + + if (typeflag != FTW_D) + return 0; + + cn = malloc(sizeof(*cn) + strlen(fpath) + 1); + if (cn == NULL) + return -1; + + cn->used = false; + strcpy(cn->name, fpath); + + list_add_tail(&cn->list, &cgroup_list); + return 0; +} + +static void release_cgroup_list(void) +{ + struct cgroup_name *cn; + + while (!list_empty(&cgroup_list)) { + cn = list_first_entry(&cgroup_list, struct cgroup_name, list); + list_del(&cn->list); + free(cn); + } +} + +/* collect given cgroups only */ +static int list_cgroups(const char *str) +{ + const char *p, *e, *eos = str + strlen(str); + struct cgroup_name *cn; + char *s; + + /* use given name as is - for testing purpose */ + for (;;) { + p = strchr(str, ','); + e = p ? p : eos; + + if (e - str) { + int ret; + + s = strndup(str, e - str); + if (!s) + return -1; + /* pretend if it's added by ftw() */ + ret = add_cgroup_name(s, NULL, FTW_D); + free(s); + if (ret) + return -1; + } else { + if (add_cgroup_name("", NULL, FTW_D) < 0) + return -1; + } + + if (!p) + break; + str = p+1; + } + + /* these groups will be used */ + list_for_each_entry(cn, &cgroup_list, list) + cn->used = true; + + return 0; +} + +/* collect all cgroups first and then match with the pattern */ +static int match_cgroups(const char *str) +{ + char mnt[PATH_MAX]; + const char *p, *e, *eos = str + strlen(str); + struct cgroup_name *cn; + regex_t reg; + int prefix_len; + char *s; + + if (cgroupfs_find_mountpoint(mnt, sizeof(mnt), "perf_event")) + return -1; + + /* cgroup_name will have a full path, skip the root directory */ + prefix_len = strlen(mnt); + + /* collect all cgroups in the cgroup_list */ + if (ftw(mnt, add_cgroup_name, 20) < 0) + return -1; + + for (;;) { + p = strchr(str, ','); + e = p ? p : eos; + + /* allow empty cgroups, i.e., skip */ + if (e - str) { + /* termination added */ + s = strndup(str, e - str); + if (!s) + return -1; + if (regcomp(®, s, REG_NOSUB)) { + free(s); + return -1; + } + + /* check cgroup name with the pattern */ + list_for_each_entry(cn, &cgroup_list, list) { + char *name = cn->name + prefix_len; + + if (name[0] == '/' && name[1]) + name++; + if (!regexec(®, name, 0, NULL, 0)) + cn->used = true; + } + regfree(®); + free(s); + } else { + /* first entry to root cgroup */ + cn = list_first_entry(&cgroup_list, struct cgroup_name, + list); + cn->used = true; + } + + if (!p) + break; + str = p+1; + } + return prefix_len; +} + int parse_cgroups(const struct option *opt, const char *str, int unset __maybe_unused) { @@ -193,6 +342,114 @@ int parse_cgroups(const struct option *opt, const char *str, return 0; } +static bool has_pattern_string(const char *str) +{ + return !!strpbrk(str, "{}[]()|*+?^$"); +} + +int evlist__expand_cgroup(struct evlist *evlist, const char *str, + struct rblist *metric_events, bool open_cgroup) +{ + struct evlist *orig_list, *tmp_list; + struct evsel *pos, *evsel, *leader; + struct rblist orig_metric_events; + struct cgroup *cgrp = NULL; + struct cgroup_name *cn; + int ret = -1; + int prefix_len; + + if (evlist->core.nr_entries == 0) { + fprintf(stderr, "must define events before cgroups\n"); + return -EINVAL; + } + + orig_list = evlist__new(); + tmp_list = evlist__new(); + if (orig_list == NULL || tmp_list == NULL) { + fprintf(stderr, "memory allocation failed\n"); + return -ENOMEM; + } + + /* save original events and init evlist */ + evlist__splice_list_tail(orig_list, &evlist->core.entries); + evlist->core.nr_entries = 0; + + if (metric_events) { + orig_metric_events = *metric_events; + rblist__init(metric_events); + } else { + rblist__init(&orig_metric_events); + } + + if (has_pattern_string(str)) + prefix_len = match_cgroups(str); + else + prefix_len = list_cgroups(str); + + if (prefix_len < 0) + goto out_err; + + list_for_each_entry(cn, &cgroup_list, list) { + char *name; + + if (!cn->used) + continue; + + /* cgroup_name might have a full path, skip the prefix */ + name = cn->name + prefix_len; + if (name[0] == '/' && name[1]) + name++; + cgrp = cgroup__new(name, open_cgroup); + if (cgrp == NULL) + goto out_err; + + leader = NULL; + evlist__for_each_entry(orig_list, pos) { + evsel = evsel__clone(pos); + if (evsel == NULL) + goto out_err; + + cgroup__put(evsel->cgrp); + evsel->cgrp = cgroup__get(cgrp); + + if (evsel__is_group_leader(pos)) + leader = evsel; + evsel->leader = leader; + + evlist__add(tmp_list, evsel); + } + /* cgroup__new() has a refcount, release it here */ + cgroup__put(cgrp); + nr_cgroups++; + + if (metric_events) { + perf_stat__collect_metric_expr(tmp_list); + if (metricgroup__copy_metric_events(tmp_list, cgrp, + metric_events, + &orig_metric_events) < 0) + goto out_err; + } + + evlist__splice_list_tail(evlist, &tmp_list->core.entries); + tmp_list->core.nr_entries = 0; + } + + if (list_empty(&evlist->core.entries)) { + fprintf(stderr, "no cgroup matched: %s\n", str); + goto out_err; + } + + ret = 0; + +out_err: + evlist__delete(orig_list); + evlist__delete(tmp_list); + rblist__exit(&orig_metric_events); + release_cgroup_list(); + + return ret; +} + static struct cgroup *__cgroup__findnew(struct rb_root *root, uint64_t id, bool create, const char *path) { diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index e98d5975fe550..162906f3412ae 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -22,8 +22,11 @@ struct cgroup *cgroup__get(struct cgroup *cgroup); void cgroup__put(struct cgroup *cgroup); struct evlist; +struct rblist; struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name); +int evlist__expand_cgroup(struct evlist *evlist, const char *cgroups, + struct rblist *metric_events, bool open_cgroup); void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup); diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 20be0504fb951..6969f82843eef 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -489,7 +489,7 @@ int perf_default_config(const char *var, const char *value, return 0; } -static int perf_config_from_file(config_fn_t fn, const char *filename, void *data) +int perf_config_from_file(config_fn_t fn, const char *filename, void *data) { int ret; FILE *f = fopen(filename, "r"); diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index c10b66dde2f35..8c881e3a3ec31 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -26,6 +26,8 @@ struct perf_config_set { extern const char *config_exclusive_filename; typedef int (*config_fn_t)(const char *, const char *, void *); + +int perf_config_from_file(config_fn_t fn, const char *filename, void *data); int perf_default_config(const char *, const char *, void *); int perf_config(config_fn_t fn, void *); int perf_config_int(int *dest, const char *, const char *); diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index dc5c5e6fc502d..87d3eca9b872d 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -95,6 +95,23 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr) return cpus; } +struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr) +{ + struct cpu_aggr_map *cpus = malloc(sizeof(*cpus) + sizeof(struct aggr_cpu_id) * nr); + + if (cpus != NULL) { + int i; + + cpus->nr = nr; + for (i = 0; i < nr; i++) + cpus->map[i] = cpu_map__empty_aggr_cpu_id(); + + refcount_set(&cpus->refcnt, 1); + } + + return cpus; +} + static int cpu__get_topology_int(int cpu, const char *name, int *value) { char path[PATH_MAX]; @@ -111,40 +128,57 @@ int cpu_map__get_socket_id(int cpu) return ret ?: value; } -int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data __maybe_unused) +struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, + void *data __maybe_unused) { int cpu; + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); if (idx > map->nr) - return -1; + return id; cpu = map->map[idx]; - return cpu_map__get_socket_id(cpu); + id.socket = cpu_map__get_socket_id(cpu); + return id; } -static int cmp_ids(const void *a, const void *b) +static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) { - return *(int *)a - *(int *)b; + struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer; + struct aggr_cpu_id *b = (struct aggr_cpu_id *)b_pointer; + + if (a->node != b->node) + return a->node - b->node; + else if (a->socket != b->socket) + return a->socket - b->socket; + else if (a->die != b->die) + return a->die - b->die; + else if (a->core != b->core) + return a->core - b->core; + else + return a->thread - b->thread; } -int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, - int (*f)(struct perf_cpu_map *map, int cpu, void *data), +int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, + struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), void *data) { - struct perf_cpu_map *c; int nr = cpus->nr; - int cpu, s1, s2; + struct cpu_aggr_map *c = cpu_aggr_map__empty_new(nr); + int cpu, s2; + struct aggr_cpu_id s1; - /* allocate as much as possible */ - c = calloc(1, sizeof(*c) + nr * sizeof(int)); if (!c) return -1; + /* Reset size as it may only be partially filled */ + c->nr = 0; + for (cpu = 0; cpu < nr; cpu++) { s1 = f(cpus, cpu, data); for (s2 = 0; s2 < c->nr; s2++) { - if (s1 == c->map[s2]) + if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2])) break; } if (s2 == c->nr) { @@ -153,9 +187,8 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, } } /* ensure we process id in increasing order */ - qsort(c->map, c->nr, sizeof(int), cmp_ids); + qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), cmp_aggr_cpu_id); - refcount_set(&c->refcnt, 1); *res = c; return 0; } @@ -167,37 +200,32 @@ int cpu_map__get_die_id(int cpu) return ret ?: value; } -int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) +struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) { - int cpu, die_id, s; + int cpu, die; + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); if (idx > map->nr) - return -1; + return id; cpu = map->map[idx]; - die_id = cpu_map__get_die_id(cpu); + die = cpu_map__get_die_id(cpu); /* There is no die_id on legacy system. */ - if (die_id == -1) - die_id = 0; - - s = cpu_map__get_socket(map, idx, data); - if (s == -1) - return -1; + if (die == -1) + die = 0; /* - * Encode socket in bit range 15:8 - * die_id is relative to socket, and - * we need a global id. So we combine - * socket + die id + * die_id is relative to socket, so start + * with the socket ID and then add die to + * make a unique ID. */ - if (WARN_ONCE(die_id >> 8, "The die id number is too big.\n")) - return -1; - - if (WARN_ONCE(s >> 8, "The socket id number is too big.\n")) - return -1; + id = cpu_map__get_socket(map, idx, data); + if (cpu_map__aggr_cpu_id_is_empty(id)) + return id; - return (s << 8) | (die_id & 0xff); + id.die = die; + return id; } int cpu_map__get_core_id(int cpu) @@ -211,59 +239,58 @@ int cpu_map__get_node_id(int cpu) return cpu__get_node(cpu); } -int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) +struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) { - int cpu, s_die; + int cpu; + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); if (idx > map->nr) - return -1; + return id; cpu = map->map[idx]; cpu = cpu_map__get_core_id(cpu); - /* s_die is the combination of socket + die id */ - s_die = cpu_map__get_die(map, idx, data); - if (s_die == -1) - return -1; + /* cpu_map__get_die returns a struct with socket and die set*/ + id = cpu_map__get_die(map, idx, data); + if (cpu_map__aggr_cpu_id_is_empty(id)) + return id; /* - * encode socket in bit range 31:24 - * encode die id in bit range 23:16 - * core_id is relative to socket and die, - * we need a global id. So we combine - * socket + die id + core id + * core_id is relative to socket and die, we need a global id. + * So we combine the result from cpu_map__get_die with the core id */ - if (WARN_ONCE(cpu >> 16, "The core id number is too big.\n")) - return -1; - - return (s_die << 16) | (cpu & 0xffff); + id.core = cpu; + return id; } -int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) { + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + if (idx < 0 || idx >= map->nr) - return -1; + return id; - return cpu_map__get_node_id(map->map[idx]); + id.node = cpu_map__get_node_id(map->map[idx]); + return id; } -int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp) +int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp) { return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL); } -int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep) +int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep) { return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL); } -int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep) +int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep) { return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL); } -int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **numap) +int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap) { return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL); } @@ -586,3 +613,33 @@ const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ return online; } + +bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b) +{ + return a.thread == b.thread && + a.node == b.node && + a.socket == b.socket && + a.die == b.die && + a.core == b.core; +} + +bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a) +{ + return a.thread == -1 && + a.node == -1 && + a.socket == -1 && + a.die == -1 && + a.core == -1; +} + +struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void) +{ + struct aggr_cpu_id ret = { + .thread = -1, + .node = -1, + .socket = -1, + .die = -1, + .core = -1 + }; + return ret; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 3a442f0214684..a27eeaf086e8c 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -7,25 +7,41 @@ #include <internal/cpumap.h> #include <perf/cpumap.h> +struct aggr_cpu_id { + int thread; + int node; + int socket; + int die; + int core; +}; + +struct cpu_aggr_map { + refcount_t refcnt; + int nr; + struct aggr_cpu_id map[]; +}; + struct perf_record_cpu_map_data; struct perf_cpu_map *perf_cpu_map__empty_new(int nr); +struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr); + struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data); size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); int cpu_map__get_socket_id(int cpu); -int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); +struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_die_id(int cpu); -int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); +struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_core_id(int cpu); -int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); +struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_node_id(int cpu); -int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp); -int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep); -int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep); -int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **nodep); +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); +int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp); +int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep); +int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep); +int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **nodep); const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */ static inline int cpu_map__socket(struct perf_cpu_map *sock, int s) @@ -35,21 +51,6 @@ static inline int cpu_map__socket(struct perf_cpu_map *sock, int s) return sock->map[s]; } -static inline int cpu_map__id_to_socket(int id) -{ - return id >> 24; -} - -static inline int cpu_map__id_to_die(int id) -{ - return (id >> 16) & 0xff; -} - -static inline int cpu_map__id_to_cpu(int id) -{ - return id & 0xffff; -} - int cpu__setup_cpunode_map(void); int cpu__max_node(void); @@ -57,11 +58,15 @@ int cpu__max_cpu(void); int cpu__max_present_cpu(void); int cpu__get_node(int cpu); -int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, - int (*f)(struct perf_cpu_map *map, int cpu, void *data), +int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, + struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), void *data); int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); +bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b); +bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a); +struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void); + #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index c47aa34fdc0a7..f29af4fc3d093 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -174,8 +174,21 @@ static bool check_pipe(struct perf_data *data) is_pipe = true; } - if (is_pipe) - data->file.fd = fd; + if (is_pipe) { + if (data->use_stdio) { + const char *mode; + + mode = perf_data__is_read(data) ? "r" : "w"; + data->file.fptr = fdopen(fd, mode); + + if (data->file.fptr == NULL) { + data->file.fd = fd; + data->use_stdio = false; + } + } else { + data->file.fd = fd; + } + } return data->is_pipe = is_pipe; } @@ -334,6 +347,9 @@ int perf_data__open(struct perf_data *data) if (check_pipe(data)) return 0; + /* currently it allows stdio for pipe only */ + data->use_stdio = false; + if (!data->path) data->path = "perf.data"; @@ -353,7 +369,21 @@ void perf_data__close(struct perf_data *data) perf_data__close_dir(data); zfree(&data->file.path); - close(data->file.fd); + + if (data->use_stdio) + fclose(data->file.fptr); + else + close(data->file.fd); +} + +ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size) +{ + if (data->use_stdio) { + if (fread(buf, size, 1, data->file.fptr) == 1) + return size; + return feof(data->file.fptr) ? 0 : -1; + } + return readn(data->file.fd, buf, size); } ssize_t perf_data_file__write(struct perf_data_file *file, @@ -365,6 +395,11 @@ ssize_t perf_data_file__write(struct perf_data_file *file, ssize_t perf_data__write(struct perf_data *data, void *buf, size_t size) { + if (data->use_stdio) { + if (fwrite(buf, size, 1, data->file.fptr) == 1) + return size; + return -1; + } return perf_data_file__write(&data->file, buf, size); } @@ -457,3 +492,22 @@ char *perf_data__kallsyms_name(struct perf_data *data) return kallsyms_name; } + +bool is_perf_data(const char *path) +{ + bool ret = false; + FILE *file; + u64 magic; + + file = fopen(path, "r"); + if (!file) + return false; + + if (fread(&magic, 1, 8, file) < 8) + goto out; + + ret = is_perf_magic(magic); +out: + fclose(file); + return ret; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 75947ef6bc170..62a3e66fbee8a 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -2,6 +2,7 @@ #ifndef __PERF_DATA_H #define __PERF_DATA_H +#include <stdio.h> #include <stdbool.h> enum perf_data_mode { @@ -16,7 +17,10 @@ enum perf_dir_version { struct perf_data_file { char *path; - int fd; + union { + int fd; + FILE *fptr; + }; unsigned long size; }; @@ -26,6 +30,7 @@ struct perf_data { bool is_pipe; bool is_dir; bool force; + bool use_stdio; enum perf_data_mode mode; struct { @@ -62,11 +67,15 @@ static inline bool perf_data__is_single_file(struct perf_data *data) static inline int perf_data__fd(struct perf_data *data) { + if (data->use_stdio) + return fileno(data->file.fptr); + return data->file.fd; } int perf_data__open(struct perf_data *data); void perf_data__close(struct perf_data *data); +ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size); ssize_t perf_data__write(struct perf_data *data, void *buf, size_t size); ssize_t perf_data_file__write(struct perf_data_file *file, @@ -89,4 +98,5 @@ int perf_data__update_dir(struct perf_data *data); unsigned long perf_data__size(struct perf_data *data); int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz); char *perf_data__kallsyms_name(struct perf_data *data); +bool is_perf_data(const char *path); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 5cda5565777a0..50fd6a4be4e01 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -30,6 +30,12 @@ bool dump_trace = false, quiet = false; int debug_ordered_events; static int redirect_to_stderr; int debug_data_convert; +static FILE *debug_file; + +void debug_set_file(FILE *file) +{ + debug_file = file; +} int veprintf(int level, int var, const char *fmt, va_list args) { @@ -39,7 +45,7 @@ int veprintf(int level, int var, const char *fmt, va_list args) if (use_browser >= 1 && !redirect_to_stderr) ui_helpline__vshow(fmt, args); else - ret = vfprintf(stderr, fmt, args); + ret = vfprintf(debug_file, fmt, args); } return ret; @@ -227,6 +233,7 @@ DEBUG_WRAPPER(debug, 1); void perf_debug_setup(void) { + debug_set_file(stderr); libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper); } diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index f1734abd98dd0..43f7122956455 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -5,6 +5,7 @@ #include <stdarg.h> #include <stdbool.h> +#include <stdio.h> #include <linux/compiler.h> extern int verbose; @@ -62,6 +63,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5) int veprintf(int level, int var, const char *fmt, va_list args); int perf_debug_option(const char *str); +void debug_set_file(FILE *file); void perf_debug_setup(void); int perf_quiet_option(void); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 5a3b4755f0b3a..d786cf6b0cfa6 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -11,8 +11,10 @@ #include <errno.h> #include <fcntl.h> #include <stdlib.h> +#ifdef HAVE_LIBBPF_SUPPORT #include <bpf/libbpf.h> #include "bpf-event.h" +#endif #include "compress.h" #include "env.h" #include "namespaces.h" @@ -172,9 +174,7 @@ int dso__read_binary_type_filename(const struct dso *dso, break; } - build_id__sprintf(dso->build_id, - sizeof(dso->build_id), - build_id_hex); + build_id__sprintf(&dso->bid, build_id_hex); len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/"); snprintf(filename + len, size - len, "%.2s/%s.debug", build_id_hex, build_id_hex + 2); @@ -279,18 +279,12 @@ bool dso__needs_decompress(struct dso *dso) dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; } -static int decompress_kmodule(struct dso *dso, const char *name, - char *pathname, size_t len) +int filename__decompress(const char *name, char *pathname, + size_t len, int comp, int *err) { char tmpbuf[] = KMOD_DECOMP_NAME; int fd = -1; - if (!dso__needs_decompress(dso)) - return -1; - - if (dso->comp == COMP_ID__NONE) - return -1; - /* * We have proper compression id for DSO and yet the file * behind the 'name' can still be plain uncompressed object. @@ -304,17 +298,17 @@ static int decompress_kmodule(struct dso *dso, const char *name, * To keep this transparent, we detect this and return the file * descriptor to the uncompressed file. */ - if (!compressions[dso->comp].is_compressed(name)) + if (!compressions[comp].is_compressed(name)) return open(name, O_RDONLY); fd = mkstemp(tmpbuf); if (fd < 0) { - dso->load_errno = errno; + *err = errno; return -1; } - if (compressions[dso->comp].decompress(name, fd)) { - dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; + if (compressions[comp].decompress(name, fd)) { + *err = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; close(fd); fd = -1; } @@ -328,6 +322,19 @@ static int decompress_kmodule(struct dso *dso, const char *name, return fd; } +static int decompress_kmodule(struct dso *dso, const char *name, + char *pathname, size_t len) +{ + if (!dso__needs_decompress(dso)) + return -1; + + if (dso->comp == COMP_ID__NONE) + return -1; + + return filename__decompress(name, pathname, len, dso->comp, + &dso->load_errno); +} + int dso__decompress_kmodule_fd(struct dso *dso, const char *name) { return decompress_kmodule(dso, name, NULL, 0); @@ -730,6 +737,7 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by) return false; } +#ifdef HAVE_LIBBPF_SUPPORT static ssize_t bpf_read(struct dso *dso, u64 offset, char *data) { struct bpf_prog_info_node *node; @@ -767,6 +775,7 @@ static int bpf_size(struct dso *dso) dso->data.file_size = node->info_linear->info.jited_prog_len; return 0; } +#endif // HAVE_LIBBPF_SUPPORT static void dso_cache__free(struct dso *dso) @@ -896,10 +905,12 @@ static struct dso_cache *dso_cache__populate(struct dso *dso, *ret = -ENOMEM; return NULL; } - +#ifdef HAVE_LIBBPF_SUPPORT if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) *ret = bpf_read(dso, cache_offset, cache->data); - else if (dso->binary_type == DSO_BINARY_TYPE__OOL) + else +#endif + if (dso->binary_type == DSO_BINARY_TYPE__OOL) *ret = DSO__DATA_CACHE_SIZE; else *ret = file_read(dso, machine, cache_offset, cache->data); @@ -1020,10 +1031,10 @@ int dso__data_file_size(struct dso *dso, struct machine *machine) if (dso->data.status == DSO_DATA_STATUS_ERROR) return -1; - +#ifdef HAVE_LIBBPF_SUPPORT if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) return bpf_size(dso); - +#endif return file_size(dso, machine); } @@ -1328,15 +1339,16 @@ void dso__put(struct dso *dso) dso__delete(dso); } -void dso__set_build_id(struct dso *dso, void *build_id) +void dso__set_build_id(struct dso *dso, struct build_id *bid) { - memcpy(dso->build_id, build_id, sizeof(dso->build_id)); + dso->bid = *bid; dso->has_build_id = 1; } -bool dso__build_id_equal(const struct dso *dso, u8 *build_id) +bool dso__build_id_equal(const struct dso *dso, struct build_id *bid) { - return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0; + return dso->bid.size == bid->size && + memcmp(dso->bid.data, bid->data, dso->bid.size) == 0; } void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine) @@ -1346,8 +1358,7 @@ void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine) if (machine__is_default_guest(machine)) return; sprintf(path, "%s/sys/kernel/notes", machine->root_dir); - if (sysfs__read_build_id(path, dso->build_id, - sizeof(dso->build_id)) == 0) + if (sysfs__read_build_id(path, &dso->bid) == 0) dso->has_build_id = true; } @@ -1365,18 +1376,17 @@ int dso__kernel_module_get_build_id(struct dso *dso, "%s/sys/module/%.*s/notes/.note.gnu.build-id", root_dir, (int)strlen(name) - 1, name); - if (sysfs__read_build_id(filename, dso->build_id, - sizeof(dso->build_id)) == 0) + if (sysfs__read_build_id(filename, &dso->bid) == 0) dso->has_build_id = true; return 0; } -size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) +static size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) { char sbuild_id[SBUILD_ID_SIZE]; - build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + build_id__sprintf(&dso->bid, sbuild_id); return fprintf(fp, "%s", sbuild_id); } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 8ad17f395a197..cd2fe64a3c5de 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -176,7 +176,7 @@ struct dso { bool sorted_by_name; bool loaded; u8 rel; - u8 build_id[BUILD_ID_SIZE]; + struct build_id bid; u64 text_offset; const char *short_name; const char *long_name; @@ -260,8 +260,8 @@ bool dso__sorted_by_name(const struct dso *dso); void dso__set_sorted_by_name(struct dso *dso); void dso__sort_by_name(struct dso *dso); -void dso__set_build_id(struct dso *dso, void *build_id); -bool dso__build_id_equal(const struct dso *dso, u8 *build_id); +void dso__set_build_id(struct dso *dso, struct build_id *bid); +bool dso__build_id_equal(const struct dso *dso, struct build_id *bid); void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine); int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir); @@ -274,6 +274,8 @@ bool dso__needs_decompress(struct dso *dso); int dso__decompress_kmodule_fd(struct dso *dso, const char *name); int dso__decompress_kmodule_path(struct dso *dso, const char *name, char *pathname, size_t len); +int filename__decompress(const char *name, char *pathname, + size_t len, int comp, int *err); #define KMOD_DECOMP_NAME "/tmp/perf-kmod-XXXXXX" #define KMOD_DECOMP_LEN sizeof(KMOD_DECOMP_NAME) @@ -362,7 +364,6 @@ struct dso *machine__findnew_kernel(struct machine *machine, const char *name, void dso__reset_find_symbol_cache(struct dso *dso); -size_t dso__fprintf_buildid(struct dso *dso, FILE *fp); size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp); size_t dso__fprintf(struct dso *dso, FILE *fp); diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c index 939471731ea64..183a81d5b2f92 100644 --- a/tools/perf/util/dsos.c +++ b/tools/perf/util/dsos.c @@ -73,8 +73,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) continue; } nsinfo__mountns_enter(pos->nsinfo, &nsc); - if (filename__read_build_id(pos->long_name, pos->build_id, - sizeof(pos->build_id)) > 0) { + if (filename__read_build_id(pos->long_name, &pos->bid) > 0) { have_build_id = true; pos->has_build_id = true; } @@ -288,10 +287,12 @@ size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, size_t ret = 0; list_for_each_entry(pos, head, node) { + char sbuild_id[SBUILD_ID_SIZE]; + if (skip && skip(pos, parm)) continue; - ret += dso__fprintf_buildid(pos, fp); - ret += fprintf(fp, " %s\n", pos->long_name); + build_id__sprintf(&pos->bid, sbuild_id); + ret += fprintf(fp, "%-40s %s\n", sbuild_id, pos->long_name); } return ret; } diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index aa898014ad12f..7b2d471a6419d 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -356,9 +356,25 @@ bool die_is_signed_type(Dwarf_Die *tp_die) bool die_is_func_def(Dwarf_Die *dw_die) { Dwarf_Attribute attr; + Dwarf_Addr addr = 0; + + if (dwarf_tag(dw_die) != DW_TAG_subprogram) + return false; + + if (dwarf_attr(dw_die, DW_AT_declaration, &attr)) + return false; - return (dwarf_tag(dw_die) == DW_TAG_subprogram && - dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); + /* + * DW_AT_declaration can be lost from function declaration + * by gcc's bug #97060. + * So we need to check this subprogram DIE has DW_AT_inline + * or an entry address. + */ + if (!dwarf_attr(dw_die, DW_AT_inline, &attr) && + die_entrypc(dw_die, &addr) < 0) + return false; + + return true; } /** @@ -373,6 +389,7 @@ bool die_is_func_def(Dwarf_Die *dw_die) int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) { Dwarf_Addr base, end; + Dwarf_Attribute attr; if (!addr) return -EINVAL; @@ -380,6 +397,13 @@ int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr) if (dwarf_entrypc(dw_die, addr) == 0) return 0; + /* + * Since the dwarf_ranges() will return 0 if there is no + * DW_AT_ranges attribute, we should check it first. + */ + if (!dwarf_attr(dw_die, DW_AT_ranges, &attr)) + return -ENOENT; + return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0; } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index fadc59708ece0..9130f6fad8d54 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -5,16 +5,18 @@ #include "util/header.h" #include <linux/ctype.h> #include <linux/zalloc.h> -#include "bpf-event.h" #include "cgroup.h" #include <errno.h> #include <sys/utsname.h> -#include <bpf/libbpf.h> #include <stdlib.h> #include <string.h> struct perf_env perf_env; +#ifdef HAVE_LIBBPF_SUPPORT +#include "bpf-event.h" +#include <bpf/libbpf.h> + void perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) { @@ -163,6 +165,11 @@ static void perf_env__purge_bpf(struct perf_env *env) up_write(&env->bpf_progs.lock); } +#else // HAVE_LIBBPF_SUPPORT +static void perf_env__purge_bpf(struct perf_env *env __maybe_unused) +{ +} +#endif // HAVE_LIBBPF_SUPPORT void perf_env__exit(struct perf_env *env) { @@ -197,11 +204,13 @@ void perf_env__exit(struct perf_env *env) zfree(&env->memory_nodes); } -void perf_env__init(struct perf_env *env) +void perf_env__init(struct perf_env *env __maybe_unused) { +#ifdef HAVE_LIBBPF_SUPPORT env->bpf_progs.infos = RB_ROOT; env->bpf_progs.btfs = RB_ROOT; init_rwsem(&env->bpf_progs.lock); +#endif } int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]) diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index a129726520064..ca249bf5e9844 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -77,7 +77,7 @@ struct perf_env { struct numa_node *numa_nodes; struct memory_node *memory_nodes; unsigned long long memory_bsize; - +#ifdef HAVE_LIBBPF_SUPPORT /* * bpf_info_lock protects bpf rbtrees. This is needed because the * trees are accessed by different threads in perf-top @@ -89,7 +89,7 @@ struct perf_env { struct rb_root btfs; u32 btfs_cnt; } bpf_progs; - +#endif // HAVE_LIBBPF_SUPPORT /* same reason as above (for perf-top) */ struct { struct rw_semaphore lock; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 317a265718458..05616d4138a96 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -398,7 +398,7 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp) if (event->header.type == PERF_RECORD_SWITCH) return fprintf(fp, " %s\n", in_out); - return fprintf(fp, " %s %s pid/tid: %5u/%-5u\n", + return fprintf(fp, " %s %s pid/tid: %5d/%-5d\n", in_out, out ? "next" : "prev", event->context_switch.next_prev_pid, event->context_switch.next_prev_tid); diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index b828b99176f40..ff403ea578e11 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -135,6 +135,7 @@ struct perf_sample { u32 raw_size; u64 data_src; u64 phys_addr; + u64 data_page_size; u64 cgroup; u32 flags; u16 insn_len; @@ -408,4 +409,7 @@ extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; extern unsigned int proc_map_timeout; +#define PAGE_SIZE_NAME_LEN 32 +char *get_page_size_name(u64 size, char *str); + #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index c0768c61eb430..05363a7247c41 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -78,7 +78,7 @@ struct evlist *evlist__new(void) return evlist; } -struct evlist *perf_evlist__new_default(void) +struct evlist *evlist__new_default(void) { struct evlist *evlist = evlist__new(); @@ -90,7 +90,7 @@ struct evlist *perf_evlist__new_default(void) return evlist; } -struct evlist *perf_evlist__new_dummy(void) +struct evlist *evlist__new_dummy(void) { struct evlist *evlist = evlist__new(); @@ -103,13 +103,13 @@ struct evlist *perf_evlist__new_dummy(void) } /** - * perf_evlist__set_id_pos - set the positions of event ids. + * evlist__set_id_pos - set the positions of event ids. * @evlist: selected event list * * Events with compatible sample types all have the same id_pos * and is_pos. For convenience, put a copy on evlist. */ -void perf_evlist__set_id_pos(struct evlist *evlist) +void evlist__set_id_pos(struct evlist *evlist) { struct evsel *first = evlist__first(evlist); @@ -117,14 +117,14 @@ void perf_evlist__set_id_pos(struct evlist *evlist) evlist->is_pos = first->is_pos; } -static void perf_evlist__update_id_pos(struct evlist *evlist) +static void evlist__update_id_pos(struct evlist *evlist) { struct evsel *evsel; evlist__for_each_entry(evlist, evsel) evsel__calc_id_pos(evsel); - perf_evlist__set_id_pos(evlist); + evlist__set_id_pos(evlist); } static void evlist__purge(struct evlist *evlist) @@ -168,7 +168,7 @@ void evlist__add(struct evlist *evlist, struct evsel *entry) perf_evlist__add(&evlist->core, &entry->core); if (evlist->core.nr_entries == 1) - perf_evlist__set_id_pos(evlist); + evlist__set_id_pos(evlist); } void evlist__remove(struct evlist *evlist, struct evsel *evsel) @@ -177,27 +177,36 @@ void evlist__remove(struct evlist *evlist, struct evsel *evsel) perf_evlist__remove(&evlist->core, &evsel->core); } -void perf_evlist__splice_list_tail(struct evlist *evlist, - struct list_head *list) +void evlist__splice_list_tail(struct evlist *evlist, struct list_head *list) { - struct evsel *evsel, *temp; + while (!list_empty(list)) { + struct evsel *evsel, *temp, *leader = NULL; - __evlist__for_each_entry_safe(list, temp, evsel) { - list_del_init(&evsel->core.node); - evlist__add(evlist, evsel); + __evlist__for_each_entry_safe(list, temp, evsel) { + list_del_init(&evsel->core.node); + evlist__add(evlist, evsel); + leader = evsel; + break; + } + + __evlist__for_each_entry_safe(list, temp, evsel) { + if (evsel->leader == leader) { + list_del_init(&evsel->core.node); + evlist__add(evlist, evsel); + } + } } } int __evlist__set_tracepoints_handlers(struct evlist *evlist, const struct evsel_str_handler *assocs, size_t nr_assocs) { - struct evsel *evsel; size_t i; int err; for (i = 0; i < nr_assocs; i++) { // Adding a handler for an event not in this evlist, just ignore it. - evsel = perf_evlist__find_tracepoint_by_name(evlist, assocs[i].name); + struct evsel *evsel = evlist__find_tracepoint_by_name(evlist, assocs[i].name); if (evsel == NULL) continue; @@ -212,7 +221,7 @@ out: return err; } -void __perf_evlist__set_leader(struct list_head *list) +void __evlist__set_leader(struct list_head *list) { struct evsel *evsel, *leader; @@ -226,11 +235,11 @@ void __perf_evlist__set_leader(struct list_head *list) } } -void perf_evlist__set_leader(struct evlist *evlist) +void evlist__set_leader(struct evlist *evlist) { if (evlist->core.nr_entries) { evlist->nr_groups = evlist->core.nr_entries > 1 ? 1 : 0; - __perf_evlist__set_leader(&evlist->core.entries); + __evlist__set_leader(&evlist->core.entries); } } @@ -274,7 +283,7 @@ static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attr list_add_tail(&evsel->core.node, &head); } - perf_evlist__splice_list_tail(evlist, &head); + evlist__splice_list_tail(evlist, &head); return 0; @@ -294,8 +303,7 @@ int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *a return evlist__add_attrs(evlist, attrs, nr_attrs); } -struct evsel * -perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id) +struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id) { struct evsel *evsel; @@ -308,9 +316,7 @@ perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id) return NULL; } -struct evsel * -perf_evlist__find_tracepoint_by_name(struct evlist *evlist, - const char *name) +struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name) { struct evsel *evsel; @@ -335,8 +341,7 @@ int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, return 0; } -static int perf_evlist__nr_threads(struct evlist *evlist, - struct evsel *evsel) +static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel) { if (evsel->core.system_wide) return 1; @@ -376,7 +381,30 @@ bool evsel__cpu_iter_skip(struct evsel *ev, int cpu) return true; } -void evlist__disable(struct evlist *evlist) +static int evsel__strcmp(struct evsel *pos, char *evsel_name) +{ + if (!evsel_name) + return 0; + if (evsel__is_dummy_event(pos)) + return 1; + return strcmp(pos->name, evsel_name); +} + +static int evlist__is_enabled(struct evlist *evlist) +{ + struct evsel *pos; + + evlist__for_each_entry(evlist, pos) { + if (!evsel__is_group_leader(pos) || !pos->core.fd) + continue; + /* If at least one event is enabled, evlist is enabled. */ + if (!pos->disabled) + return true; + } + return false; +} + +static void __evlist__disable(struct evlist *evlist, char *evsel_name) { struct evsel *pos; struct affinity affinity; @@ -392,6 +420,8 @@ void evlist__disable(struct evlist *evlist) affinity__set(&affinity, cpu); evlist__for_each_entry(evlist, pos) { + if (evsel__strcmp(pos, evsel_name)) + continue; if (evsel__cpu_iter_skip(pos, cpu)) continue; if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd) @@ -409,15 +439,34 @@ void evlist__disable(struct evlist *evlist) affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { + if (evsel__strcmp(pos, evsel_name)) + continue; if (!evsel__is_group_leader(pos) || !pos->core.fd) continue; pos->disabled = true; } - evlist->enabled = false; + /* + * If we disabled only single event, we need to check + * the enabled state of the evlist manually. + */ + if (evsel_name) + evlist->enabled = evlist__is_enabled(evlist); + else + evlist->enabled = false; } -void evlist__enable(struct evlist *evlist) +void evlist__disable(struct evlist *evlist) +{ + __evlist__disable(evlist, NULL); +} + +void evlist__disable_evsel(struct evlist *evlist, char *evsel_name) +{ + __evlist__disable(evlist, evsel_name); +} + +static void __evlist__enable(struct evlist *evlist, char *evsel_name) { struct evsel *pos; struct affinity affinity; @@ -430,6 +479,8 @@ void evlist__enable(struct evlist *evlist) affinity__set(&affinity, cpu); evlist__for_each_entry(evlist, pos) { + if (evsel__strcmp(pos, evsel_name)) + continue; if (evsel__cpu_iter_skip(pos, cpu)) continue; if (!evsel__is_group_leader(pos) || !pos->core.fd) @@ -439,24 +490,40 @@ void evlist__enable(struct evlist *evlist) } affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { + if (evsel__strcmp(pos, evsel_name)) + continue; if (!evsel__is_group_leader(pos) || !pos->core.fd) continue; pos->disabled = false; } + /* + * Even single event sets the 'enabled' for evlist, + * so the toggle can work properly and toggle to + * 'disabled' state. + */ evlist->enabled = true; } -void perf_evlist__toggle_enable(struct evlist *evlist) +void evlist__enable(struct evlist *evlist) +{ + __evlist__enable(evlist, NULL); +} + +void evlist__enable_evsel(struct evlist *evlist, char *evsel_name) +{ + __evlist__enable(evlist, evsel_name); +} + +void evlist__toggle_enable(struct evlist *evlist) { (evlist->enabled ? evlist__disable : evlist__enable)(evlist); } -static int perf_evlist__enable_event_cpu(struct evlist *evlist, - struct evsel *evsel, int cpu) +static int evlist__enable_event_cpu(struct evlist *evlist, struct evsel *evsel, int cpu) { int thread; - int nr_threads = perf_evlist__nr_threads(evlist, evsel); + int nr_threads = evlist__nr_threads(evlist, evsel); if (!evsel->core.fd) return -EINVAL; @@ -469,9 +536,7 @@ static int perf_evlist__enable_event_cpu(struct evlist *evlist, return 0; } -static int perf_evlist__enable_event_thread(struct evlist *evlist, - struct evsel *evsel, - int thread) +static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evsel, int thread) { int cpu; int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); @@ -487,15 +552,14 @@ static int perf_evlist__enable_event_thread(struct evlist *evlist, return 0; } -int perf_evlist__enable_event_idx(struct evlist *evlist, - struct evsel *evsel, int idx) +int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx) { bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus); if (per_cpu_mmaps) - return perf_evlist__enable_event_cpu(evlist, evsel, idx); - else - return perf_evlist__enable_event_thread(evlist, evsel, idx); + return evlist__enable_event_cpu(evlist, evsel, idx); + + return evlist__enable_event_thread(evlist, evsel, idx); } int evlist__add_pollfd(struct evlist *evlist, int fd) @@ -513,7 +577,7 @@ int evlist__poll(struct evlist *evlist, int timeout) return perf_evlist__poll(&evlist->core, timeout); } -struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id) +struct perf_sample_id *evlist__id2sid(struct evlist *evlist, u64 id) { struct hlist_head *head; struct perf_sample_id *sid; @@ -529,14 +593,14 @@ struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id) return NULL; } -struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id) +struct evsel *evlist__id2evsel(struct evlist *evlist, u64 id) { struct perf_sample_id *sid; if (evlist->core.nr_entries == 1 || !id) return evlist__first(evlist); - sid = perf_evlist__id2sid(evlist, id); + sid = evlist__id2sid(evlist, id); if (sid) return container_of(sid->evsel, struct evsel, core); @@ -546,23 +610,21 @@ struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id) return NULL; } -struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, - u64 id) +struct evsel *evlist__id2evsel_strict(struct evlist *evlist, u64 id) { struct perf_sample_id *sid; if (!id) return NULL; - sid = perf_evlist__id2sid(evlist, id); + sid = evlist__id2sid(evlist, id); if (sid) return container_of(sid->evsel, struct evsel, core); return NULL; } -static int perf_evlist__event2id(struct evlist *evlist, - union perf_event *event, u64 *id) +static int evlist__event2id(struct evlist *evlist, union perf_event *event, u64 *id) { const __u64 *array = event->sample.array; ssize_t n; @@ -582,8 +644,7 @@ static int perf_evlist__event2id(struct evlist *evlist, return 0; } -struct evsel *perf_evlist__event2evsel(struct evlist *evlist, - union perf_event *event) +struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event) { struct evsel *first = evlist__first(evlist); struct hlist_head *head; @@ -598,7 +659,7 @@ struct evsel *perf_evlist__event2evsel(struct evlist *evlist, event->header.type != PERF_RECORD_SAMPLE) return first; - if (perf_evlist__event2id(evlist, event, &id)) + if (evlist__event2id(evlist, event, &id)) return NULL; /* Synthesized events have an id of zero */ @@ -615,7 +676,7 @@ struct evsel *perf_evlist__event2evsel(struct evlist *evlist, return NULL; } -static int perf_evlist__set_paused(struct evlist *evlist, bool value) +static int evlist__set_paused(struct evlist *evlist, bool value) { int i; @@ -635,14 +696,14 @@ static int perf_evlist__set_paused(struct evlist *evlist, bool value) return 0; } -static int perf_evlist__pause(struct evlist *evlist) +static int evlist__pause(struct evlist *evlist) { - return perf_evlist__set_paused(evlist, true); + return evlist__set_paused(evlist, true); } -static int perf_evlist__resume(struct evlist *evlist) +static int evlist__resume(struct evlist *evlist) { - return perf_evlist__set_paused(evlist, false); + return evlist__set_paused(evlist, false); } static void evlist__munmap_nofree(struct evlist *evlist) @@ -727,7 +788,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx) if (overwrite) { evlist->overwrite_mmap = maps; if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY) - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); } else { evlist->mmap = maps; } @@ -827,7 +888,7 @@ static long parse_pages_arg(const char *str, unsigned long min, return pages; } -int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str) +int __evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str) { unsigned long max = UINT_MAX; long pages; @@ -845,10 +906,9 @@ int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str) return 0; } -int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, - int unset __maybe_unused) +int evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset __maybe_unused) { - return __perf_evlist__parse_mmap_pages(opt->value, str); + return __evlist__parse_mmap_pages(opt->value, str); } /** @@ -904,7 +964,7 @@ int evlist__mmap(struct evlist *evlist, unsigned int pages) return evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0); } -int perf_evlist__create_maps(struct evlist *evlist, struct target *target) +int evlist__create_maps(struct evlist *evlist, struct target *target) { bool all_threads = (target->per_thread && target->system_wide); struct perf_cpu_map *cpus; @@ -957,25 +1017,7 @@ out_delete_threads: return -1; } -void __perf_evlist__set_sample_bit(struct evlist *evlist, - enum perf_event_sample_format bit) -{ - struct evsel *evsel; - - evlist__for_each_entry(evlist, evsel) - __evsel__set_sample_bit(evsel, bit); -} - -void __perf_evlist__reset_sample_bit(struct evlist *evlist, - enum perf_event_sample_format bit) -{ - struct evsel *evsel; - - evlist__for_each_entry(evlist, evsel) - __evsel__reset_sample_bit(evsel, bit); -} - -int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) +int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) { struct evsel *evsel; int err = 0; @@ -998,7 +1040,7 @@ int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) return err; } -int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter) +int evlist__set_tp_filter(struct evlist *evlist, const char *filter) { struct evsel *evsel; int err = 0; @@ -1018,7 +1060,7 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter) return err; } -int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter) +int evlist__append_tp_filter(struct evlist *evlist, const char *filter) { struct evsel *evsel; int err = 0; @@ -1064,32 +1106,32 @@ out_free: return NULL; } -int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) +int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) { char *filter = asprintf__tp_filter_pids(npids, pids); - int ret = perf_evlist__set_tp_filter(evlist, filter); + int ret = evlist__set_tp_filter(evlist, filter); free(filter); return ret; } -int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid) +int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid) { - return perf_evlist__set_tp_filter_pids(evlist, 1, &pid); + return evlist__set_tp_filter_pids(evlist, 1, &pid); } -int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) +int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) { char *filter = asprintf__tp_filter_pids(npids, pids); - int ret = perf_evlist__append_tp_filter(evlist, filter); + int ret = evlist__append_tp_filter(evlist, filter); free(filter); return ret; } -int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid) +int evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid) { - return perf_evlist__append_tp_filter_pids(evlist, 1, &pid); + return evlist__append_tp_filter_pids(evlist, 1, &pid); } bool evlist__valid_sample_type(struct evlist *evlist) @@ -1140,7 +1182,7 @@ u64 evlist__combined_branch_type(struct evlist *evlist) return branch_type; } -bool perf_evlist__valid_read_format(struct evlist *evlist) +bool evlist__valid_read_format(struct evlist *evlist) { struct evsel *first = evlist__first(evlist), *pos = first; u64 read_format = first->core.attr.read_format; @@ -1162,7 +1204,7 @@ bool perf_evlist__valid_read_format(struct evlist *evlist) return true; } -u16 perf_evlist__id_hdr_size(struct evlist *evlist) +u16 evlist__id_hdr_size(struct evlist *evlist) { struct evsel *first = evlist__first(evlist); struct perf_sample *data; @@ -1213,8 +1255,7 @@ bool evlist__sample_id_all(struct evlist *evlist) return first->core.attr.sample_id_all; } -void perf_evlist__set_selected(struct evlist *evlist, - struct evsel *evsel) +void evlist__set_selected(struct evlist *evlist, struct evsel *evsel) { evlist->selected = evsel; } @@ -1253,7 +1294,7 @@ void evlist__close(struct evlist *evlist) } } -static int perf_evlist__create_syswide_maps(struct evlist *evlist) +static int evlist__create_syswide_maps(struct evlist *evlist) { struct perf_cpu_map *cpus; struct perf_thread_map *threads; @@ -1295,12 +1336,12 @@ int evlist__open(struct evlist *evlist) * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL */ if (evlist->core.threads == NULL && evlist->core.cpus == NULL) { - err = perf_evlist__create_syswide_maps(evlist); + err = evlist__create_syswide_maps(evlist); if (err < 0) goto out_err; } - perf_evlist__update_id_pos(evlist); + evlist__update_id_pos(evlist); evlist__for_each_entry(evlist, evsel) { err = evsel__open(evsel, evsel->core.cpus, evsel->core.threads); @@ -1315,9 +1356,8 @@ out_err: return err; } -int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target, - const char *argv[], bool pipe_output, - void (*exec_error)(int signo, siginfo_t *info, void *ucontext)) +int evlist__prepare_workload(struct evlist *evlist, struct target *target, const char *argv[], + bool pipe_output, void (*exec_error)(int signo, siginfo_t *info, void *ucontext)) { int child_ready_pipe[2], go_pipe[2]; char bf; @@ -1362,7 +1402,7 @@ int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target, /* * The parent will ask for the execvp() to be performed by * writing exactly one byte, in workload.cork_fd, usually via - * perf_evlist__start_workload(). + * evlist__start_workload(). * * For cancelling the workload without actually running it, * the parent will just close workload.cork_fd, without writing @@ -1429,7 +1469,7 @@ out_close_ready_pipe: return -1; } -int perf_evlist__start_workload(struct evlist *evlist) +int evlist__start_workload(struct evlist *evlist) { if (evlist->workload.cork_fd > 0) { char bf = 0; @@ -1448,21 +1488,18 @@ int perf_evlist__start_workload(struct evlist *evlist) return 0; } -int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event, - struct perf_sample *sample) +int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = evlist__event2evsel(evlist, event); if (!evsel) return -EFAULT; return evsel__parse_sample(evsel, event, sample); } -int perf_evlist__parse_sample_timestamp(struct evlist *evlist, - union perf_event *event, - u64 *timestamp) +int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp) { - struct evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = evlist__event2evsel(evlist, event); if (!evsel) return -EFAULT; @@ -1553,8 +1590,7 @@ int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size return 0; } -void perf_evlist__to_front(struct evlist *evlist, - struct evsel *move_evsel) +void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel) { struct evsel *evsel, *n; LIST_HEAD(move); @@ -1570,7 +1606,7 @@ void perf_evlist__to_front(struct evlist *evlist, list_splice(&move, &evlist->core.entries); } -struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist) +struct evsel *evlist__get_tracking_event(struct evlist *evlist) { struct evsel *evsel; @@ -1582,8 +1618,7 @@ struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist) return evlist__first(evlist); } -void perf_evlist__set_tracking_event(struct evlist *evlist, - struct evsel *tracking_evsel) +void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel) { struct evsel *evsel; @@ -1598,9 +1633,7 @@ void perf_evlist__set_tracking_event(struct evlist *evlist, tracking_evsel->tracking = true; } -struct evsel * -perf_evlist__find_evsel_by_str(struct evlist *evlist, - const char *str) +struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str) { struct evsel *evsel; @@ -1614,8 +1647,7 @@ perf_evlist__find_evsel_by_str(struct evlist *evlist, return NULL; } -void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, - enum bkw_mmap_state state) +void evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state) { enum bkw_mmap_state old_state = evlist->bkw_mmap_state; enum action { @@ -1658,10 +1690,10 @@ void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, switch (action) { case PAUSE: - perf_evlist__pause(evlist); + evlist__pause(evlist); break; case RESUME: - perf_evlist__resume(evlist); + evlist__resume(evlist); break; case NONE: default: @@ -1672,7 +1704,7 @@ state_err: return; } -bool perf_evlist__exclude_kernel(struct evlist *evlist) +bool evlist__exclude_kernel(struct evlist *evlist) { struct evsel *evsel; @@ -1689,19 +1721,17 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist) * the group display. Set the artificial group and set the leader's * forced_leader flag to notify the display code. */ -void perf_evlist__force_leader(struct evlist *evlist) +void evlist__force_leader(struct evlist *evlist) { if (!evlist->nr_groups) { struct evsel *leader = evlist__first(evlist); - perf_evlist__set_leader(evlist); + evlist__set_leader(evlist); leader->forced_leader = true; } } -struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, - struct evsel *evsel, - bool close) +struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel *evsel, bool close) { struct evsel *c2, *leader; bool is_open = true; @@ -1732,6 +1762,91 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, return leader; } +static int evlist__parse_control_fifo(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close) +{ + char *s, *p; + int ret = 0, fd; + + if (strncmp(str, "fifo:", 5)) + return -EINVAL; + + str += 5; + if (!*str || *str == ',') + return -EINVAL; + + s = strdup(str); + if (!s) + return -ENOMEM; + + p = strchr(s, ','); + if (p) + *p = '\0'; + + /* + * O_RDWR avoids POLLHUPs which is necessary to allow the other + * end of a FIFO to be repeatedly opened and closed. + */ + fd = open(s, O_RDWR | O_NONBLOCK | O_CLOEXEC); + if (fd < 0) { + pr_err("Failed to open '%s'\n", s); + ret = -errno; + goto out_free; + } + *ctl_fd = fd; + *ctl_fd_close = true; + + if (p && *++p) { + /* O_RDWR | O_NONBLOCK means the other end need not be open */ + fd = open(p, O_RDWR | O_NONBLOCK | O_CLOEXEC); + if (fd < 0) { + pr_err("Failed to open '%s'\n", p); + ret = -errno; + goto out_free; + } + *ctl_fd_ack = fd; + } + +out_free: + free(s); + return ret; +} + +int evlist__parse_control(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close) +{ + char *comma = NULL, *endptr = NULL; + + *ctl_fd_close = false; + + if (strncmp(str, "fd:", 3)) + return evlist__parse_control_fifo(str, ctl_fd, ctl_fd_ack, ctl_fd_close); + + *ctl_fd = strtoul(&str[3], &endptr, 0); + if (endptr == &str[3]) + return -EINVAL; + + comma = strchr(str, ','); + if (comma) { + if (endptr != comma) + return -EINVAL; + + *ctl_fd_ack = strtoul(comma + 1, &endptr, 0); + if (endptr == comma + 1 || *endptr != '\0') + return -EINVAL; + } + + return 0; +} + +void evlist__close_control(int ctl_fd, int ctl_fd_ack, bool *ctl_fd_close) +{ + if (*ctl_fd_close) { + *ctl_fd_close = false; + close(ctl_fd); + if (ctl_fd_ack >= 0) + close(ctl_fd_ack); + } +} + int evlist__initialize_ctlfd(struct evlist *evlist, int fd, int ack) { if (fd == -1) { @@ -1783,6 +1898,7 @@ static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd, char c; size_t bytes_read = 0; + *cmd = EVLIST_CTL_CMD_UNSUPPORTED; memset(cmd_data, 0, data_size); data_size--; @@ -1794,30 +1910,39 @@ static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd, cmd_data[bytes_read++] = c; if (bytes_read == data_size) break; - } else { - if (err == -1) + continue; + } else if (err == -1) { + if (errno == EINTR) + continue; + if (errno == EAGAIN || errno == EWOULDBLOCK) + err = 0; + else pr_err("Failed to read from ctlfd %d: %m\n", evlist->ctl_fd.fd); - break; } + break; } while (1); pr_debug("Message from ctl_fd: \"%s%s\"\n", cmd_data, bytes_read == data_size ? "" : c == '\n' ? "\\n" : "\\0"); - if (err > 0) { + if (bytes_read > 0) { if (!strncmp(cmd_data, EVLIST_CTL_CMD_ENABLE_TAG, (sizeof(EVLIST_CTL_CMD_ENABLE_TAG)-1))) { *cmd = EVLIST_CTL_CMD_ENABLE; } else if (!strncmp(cmd_data, EVLIST_CTL_CMD_DISABLE_TAG, (sizeof(EVLIST_CTL_CMD_DISABLE_TAG)-1))) { *cmd = EVLIST_CTL_CMD_DISABLE; + } else if (!strncmp(cmd_data, EVLIST_CTL_CMD_SNAPSHOT_TAG, + (sizeof(EVLIST_CTL_CMD_SNAPSHOT_TAG)-1))) { + *cmd = EVLIST_CTL_CMD_SNAPSHOT; + pr_debug("is snapshot\n"); } } - return err; + return bytes_read ? (int)bytes_read : err; } -static int evlist__ctlfd_ack(struct evlist *evlist) +int evlist__ctlfd_ack(struct evlist *evlist) { int err; @@ -1853,13 +1978,16 @@ int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd) case EVLIST_CTL_CMD_DISABLE: evlist__disable(evlist); break; + case EVLIST_CTL_CMD_SNAPSHOT: + break; case EVLIST_CTL_CMD_ACK: case EVLIST_CTL_CMD_UNSUPPORTED: default: pr_debug("ctlfd: unsupported %d\n", *cmd); break; } - if (!(*cmd == EVLIST_CTL_CMD_ACK || *cmd == EVLIST_CTL_CMD_UNSUPPORTED)) + if (!(*cmd == EVLIST_CTL_CMD_ACK || *cmd == EVLIST_CTL_CMD_UNSUPPORTED || + *cmd == EVLIST_CTL_CMD_SNAPSHOT)) evlist__ctlfd_ack(evlist); } } @@ -1871,3 +1999,14 @@ int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd) return err; } + +struct evsel *evlist__find_evsel(struct evlist *evlist, int idx) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->idx == idx) + return evsel; + } + return NULL; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index c73f7f7f120b6..1aae75895dea0 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -87,8 +87,8 @@ struct evsel_str_handler { }; struct evlist *evlist__new(void); -struct evlist *perf_evlist__new_default(void); -struct evlist *perf_evlist__new_dummy(void); +struct evlist *evlist__new_default(void); +struct evlist *evlist__new_dummy(void); void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, struct perf_thread_map *threads); void evlist__exit(struct evlist *evlist); @@ -112,14 +112,11 @@ int __evlist__add_default_attrs(struct evlist *evlist, int evlist__add_dummy(struct evlist *evlist); -int perf_evlist__add_sb_event(struct evlist *evlist, - struct perf_event_attr *attr, - evsel__sb_cb_t cb, - void *data); +int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, + evsel__sb_cb_t cb, void *data); void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data); -int perf_evlist__start_sb_thread(struct evlist *evlist, - struct target *target); -void perf_evlist__stop_sb_thread(struct evlist *evlist); +int evlist__start_sb_thread(struct evlist *evlist, struct target *target); +void evlist__stop_sb_thread(struct evlist *evlist); int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler); @@ -130,45 +127,29 @@ int __evlist__set_tracepoints_handlers(struct evlist *evlist, #define evlist__set_tracepoints_handlers(evlist, array) \ __evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) -void __perf_evlist__set_sample_bit(struct evlist *evlist, - enum perf_event_sample_format bit); -void __perf_evlist__reset_sample_bit(struct evlist *evlist, - enum perf_event_sample_format bit); +int evlist__set_tp_filter(struct evlist *evlist, const char *filter); +int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid); +int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); -#define perf_evlist__set_sample_bit(evlist, bit) \ - __perf_evlist__set_sample_bit(evlist, PERF_SAMPLE_##bit) +int evlist__append_tp_filter(struct evlist *evlist, const char *filter); -#define perf_evlist__reset_sample_bit(evlist, bit) \ - __perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit) +int evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid); +int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); -int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter); -int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid); -int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); - -int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter); - -int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid); -int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); - -struct evsel * -perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id); - -struct evsel * -perf_evlist__find_tracepoint_by_name(struct evlist *evlist, - const char *name); +struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id); +struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name); int evlist__add_pollfd(struct evlist *evlist, int fd); int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask); int evlist__poll(struct evlist *evlist, int timeout); -struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id); -struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, - u64 id); +struct evsel *evlist__id2evsel(struct evlist *evlist, u64 id); +struct evsel *evlist__id2evsel_strict(struct evlist *evlist, u64 id); -struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id); +struct perf_sample_id *evlist__id2sid(struct evlist *evlist, u64 id); -void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state); +void evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state); void evlist__mmap_consume(struct evlist *evlist, int idx); @@ -177,24 +158,19 @@ void evlist__close(struct evlist *evlist); struct callchain_param; -void perf_evlist__set_id_pos(struct evlist *evlist); -void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, - struct callchain_param *callchain); +void evlist__set_id_pos(struct evlist *evlist); +void evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain); int record_opts__config(struct record_opts *opts); -int perf_evlist__prepare_workload(struct evlist *evlist, - struct target *target, - const char *argv[], bool pipe_output, - void (*exec_error)(int signo, siginfo_t *info, - void *ucontext)); -int perf_evlist__start_workload(struct evlist *evlist); +int evlist__prepare_workload(struct evlist *evlist, struct target *target, + const char *argv[], bool pipe_output, + void (*exec_error)(int signo, siginfo_t *info, void *ucontext)); +int evlist__start_workload(struct evlist *evlist); struct option; -int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str); -int perf_evlist__parse_mmap_pages(const struct option *opt, - const char *str, - int unset); +int __evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str); +int evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset); unsigned long perf_event_mlock_kb_in_pages(void); @@ -209,41 +185,36 @@ size_t evlist__mmap_size(unsigned long pages); void evlist__disable(struct evlist *evlist); void evlist__enable(struct evlist *evlist); -void perf_evlist__toggle_enable(struct evlist *evlist); +void evlist__toggle_enable(struct evlist *evlist); +void evlist__disable_evsel(struct evlist *evlist, char *evsel_name); +void evlist__enable_evsel(struct evlist *evlist, char *evsel_name); -int perf_evlist__enable_event_idx(struct evlist *evlist, - struct evsel *evsel, int idx); +int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx); -void perf_evlist__set_selected(struct evlist *evlist, - struct evsel *evsel); +void evlist__set_selected(struct evlist *evlist, struct evsel *evsel); -int perf_evlist__create_maps(struct evlist *evlist, struct target *target); -int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); +int evlist__create_maps(struct evlist *evlist, struct target *target); +int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); -void __perf_evlist__set_leader(struct list_head *list); -void perf_evlist__set_leader(struct evlist *evlist); +void __evlist__set_leader(struct list_head *list); +void evlist__set_leader(struct evlist *evlist); u64 __evlist__combined_sample_type(struct evlist *evlist); u64 evlist__combined_sample_type(struct evlist *evlist); u64 evlist__combined_branch_type(struct evlist *evlist); bool evlist__sample_id_all(struct evlist *evlist); -u16 perf_evlist__id_hdr_size(struct evlist *evlist); - -int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event, - struct perf_sample *sample); +u16 evlist__id_hdr_size(struct evlist *evlist); -int perf_evlist__parse_sample_timestamp(struct evlist *evlist, - union perf_event *event, - u64 *timestamp); +int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); +int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp); bool evlist__valid_sample_type(struct evlist *evlist); bool evlist__valid_sample_id_all(struct evlist *evlist); -bool perf_evlist__valid_read_format(struct evlist *evlist); +bool evlist__valid_read_format(struct evlist *evlist); -void perf_evlist__splice_list_tail(struct evlist *evlist, - struct list_head *list); +void evlist__splice_list_tail(struct evlist *evlist, struct list_head *list); -static inline bool perf_evlist__empty(struct evlist *evlist) +static inline bool evlist__empty(struct evlist *evlist) { return list_empty(&evlist->core.entries); } @@ -265,9 +236,8 @@ static inline struct evsel *evlist__last(struct evlist *evlist) int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size); int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size); -bool perf_evlist__can_select_event(struct evlist *evlist, const char *str); -void perf_evlist__to_front(struct evlist *evlist, - struct evsel *move_evsel); +bool evlist__can_select_event(struct evlist *evlist, const char *str); +void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel); /** * __evlist__for_each_entry - iterate thru all the evsels @@ -339,30 +309,27 @@ void perf_evlist__to_front(struct evlist *evlist, evlist__cpu_iter_start(evlist); \ perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) -struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist); -void perf_evlist__set_tracking_event(struct evlist *evlist, - struct evsel *tracking_evsel); +struct evsel *evlist__get_tracking_event(struct evlist *evlist); +void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); void evlist__cpu_iter_start(struct evlist *evlist); bool evsel__cpu_iter_skip(struct evsel *ev, int cpu); bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu); -struct evsel * -perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str); +struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str); + +struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event); -struct evsel *perf_evlist__event2evsel(struct evlist *evlist, - union perf_event *event); +bool evlist__exclude_kernel(struct evlist *evlist); -bool perf_evlist__exclude_kernel(struct evlist *evlist); +void evlist__force_leader(struct evlist *evlist); -void perf_evlist__force_leader(struct evlist *evlist); +struct evsel *evlist__reset_weak_group(struct evlist *evlist, struct evsel *evsel, bool close); -struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist, - struct evsel *evsel, - bool close); #define EVLIST_CTL_CMD_ENABLE_TAG "enable" #define EVLIST_CTL_CMD_DISABLE_TAG "disable" #define EVLIST_CTL_CMD_ACK_TAG "ack\n" +#define EVLIST_CTL_CMD_SNAPSHOT_TAG "snapshot" #define EVLIST_CTL_CMD_MAX_LEN 64 @@ -370,15 +337,20 @@ enum evlist_ctl_cmd { EVLIST_CTL_CMD_UNSUPPORTED = 0, EVLIST_CTL_CMD_ENABLE, EVLIST_CTL_CMD_DISABLE, - EVLIST_CTL_CMD_ACK + EVLIST_CTL_CMD_ACK, + EVLIST_CTL_CMD_SNAPSHOT, }; +int evlist__parse_control(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close); +void evlist__close_control(int ctl_fd, int ctl_fd_ack, bool *ctl_fd_close); int evlist__initialize_ctlfd(struct evlist *evlist, int ctl_fd, int ctl_fd_ack); int evlist__finalize_ctlfd(struct evlist *evlist); bool evlist__ctlfd_initialized(struct evlist *evlist); int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd); +int evlist__ctlfd_ack(struct evlist *evlist); #define EVLIST_ENABLED_MSG "Events enabled\n" #define EVLIST_DISABLED_MSG "Events disabled\n" +struct evsel *evlist__find_evsel(struct evlist *evlist, int idx); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 459b51e900636..c26ea82220bd8 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -331,6 +331,110 @@ error_free: goto out; } +static int evsel__copy_config_terms(struct evsel *dst, struct evsel *src) +{ + struct evsel_config_term *pos, *tmp; + + list_for_each_entry(pos, &src->config_terms, list) { + tmp = malloc(sizeof(*tmp)); + if (tmp == NULL) + return -ENOMEM; + + *tmp = *pos; + if (tmp->free_str) { + tmp->val.str = strdup(pos->val.str); + if (tmp->val.str == NULL) { + free(tmp); + return -ENOMEM; + } + } + list_add_tail(&tmp->list, &dst->config_terms); + } + return 0; +} + +/** + * evsel__clone - create a new evsel copied from @orig + * @orig: original evsel + * + * 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; + + BUG_ON(orig->core.fd); + BUG_ON(orig->counts); + BUG_ON(orig->priv); + BUG_ON(orig->per_pkg_mask); + + /* cannot handle BPF objects for now */ + if (orig->bpf_obj) + return NULL; + + evsel = evsel__new(&orig->core.attr); + if (evsel == NULL) + return NULL; + + evsel->core.cpus = perf_cpu_map__get(orig->core.cpus); + evsel->core.own_cpus = perf_cpu_map__get(orig->core.own_cpus); + evsel->core.threads = perf_thread_map__get(orig->core.threads); + evsel->core.nr_members = orig->core.nr_members; + evsel->core.system_wide = orig->core.system_wide; + + if (orig->name) { + evsel->name = strdup(orig->name); + if (evsel->name == NULL) + goto out_err; + } + if (orig->group_name) { + evsel->group_name = strdup(orig->group_name); + if (evsel->group_name == NULL) + goto out_err; + } + if (orig->pmu_name) { + evsel->pmu_name = strdup(orig->pmu_name); + if (evsel->pmu_name == NULL) + goto out_err; + } + if (orig->filter) { + evsel->filter = strdup(orig->filter); + if (evsel->filter == NULL) + goto out_err; + } + evsel->cgrp = cgroup__get(orig->cgrp); + evsel->tp_format = orig->tp_format; + evsel->handler = orig->handler; + evsel->leader = orig->leader; + + evsel->max_events = orig->max_events; + evsel->tool_event = orig->tool_event; + evsel->unit = orig->unit; + evsel->scale = orig->scale; + evsel->snapshot = orig->snapshot; + evsel->per_pkg = orig->per_pkg; + evsel->percore = orig->percore; + evsel->precise_max = orig->precise_max; + evsel->use_uncore_alias = orig->use_uncore_alias; + evsel->is_libpfm_event = orig->is_libpfm_event; + + evsel->exclude_GH = orig->exclude_GH; + evsel->sample_read = orig->sample_read; + evsel->auto_merge_stats = orig->auto_merge_stats; + evsel->collect_stat = orig->collect_stat; + evsel->weak_group = orig->weak_group; + + if (evsel__copy_config_terms(evsel, orig) < 0) + goto out_err; + + return evsel; + +out_err: + evsel__delete(evsel); + return NULL; +} + /* * Returns pointer with encoded error via <linux/err.h> interface. */ @@ -393,7 +497,7 @@ static const char *__evsel__hw_name(u64 config) return "unknown-hardware"; } -static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) +static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) { int colon = 0, r = 0; struct perf_event_attr *attr = &evsel->core.attr; @@ -432,7 +536,7 @@ static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) static int evsel__hw_name(struct evsel *evsel, char *bf, size_t size) { int r = scnprintf(bf, size, "%s", __evsel__hw_name(evsel->core.attr.config)); - return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); + return r + evsel__add_modifiers(evsel, bf + r, size - r); } const char *evsel__sw_names[PERF_COUNT_SW_MAX] = { @@ -458,7 +562,7 @@ static const char *__evsel__sw_name(u64 config) static int evsel__sw_name(struct evsel *evsel, char *bf, size_t size) { int r = scnprintf(bf, size, "%s", __evsel__sw_name(evsel->core.attr.config)); - return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); + return r + evsel__add_modifiers(evsel, bf + r, size - r); } static int __evsel__bp_name(char *bf, size_t size, u64 addr, u64 type) @@ -483,7 +587,7 @@ static int evsel__bp_name(struct evsel *evsel, char *bf, size_t size) { struct perf_event_attr *attr = &evsel->core.attr; int r = __evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type); - return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); + return r + evsel__add_modifiers(evsel, bf + r, size - r); } const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES] = { @@ -578,13 +682,13 @@ out_err: static int evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size) { int ret = __evsel__hw_cache_name(evsel->core.attr.config, bf, size); - return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); + return ret + evsel__add_modifiers(evsel, bf + ret, size - ret); } static int evsel__raw_name(struct evsel *evsel, char *bf, size_t size) { int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config); - return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); + return ret + evsel__add_modifiers(evsel, bf + ret, size - ret); } static int evsel__tool_name(char *bf, size_t size) @@ -746,9 +850,7 @@ void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, return __evsel__config_callchain(evsel, opts, param); } -static void -perf_evsel__reset_callgraph(struct evsel *evsel, - struct callchain_param *param) +static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param *param) { struct perf_event_attr *attr = &evsel->core.attr; @@ -884,7 +986,7 @@ static void evsel__apply_config_terms(struct evsel *evsel, /* If global callgraph set, clear it */ if (callchain_param.enabled) - perf_evsel__reset_callgraph(evsel, &callchain_param); + evsel__reset_callgraph(evsel, &callchain_param); /* set perf-event callgraph */ if (param.enabled) { @@ -1086,6 +1188,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, evsel__set_sample_bit(evsel, CGROUP); } + if (opts->sample_data_page_size) + evsel__set_sample_bit(evsel, DATA_PAGE_SIZE); + if (opts->record_switch_events) attr->context_switch = track; @@ -1330,9 +1435,7 @@ static int evsel__read_one(struct evsel *evsel, int cpu, int thread) return perf_evsel__read(&evsel->core, cpu, thread, count); } -static void -perf_evsel__set_count(struct evsel *counter, int cpu, int thread, - u64 val, u64 ena, u64 run) +static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run) { struct perf_counts_values *count; @@ -1345,9 +1448,7 @@ perf_evsel__set_count(struct evsel *counter, int cpu, int thread, perf_counts__set_loaded(counter->counts, cpu, thread, true); } -static int -perf_evsel__process_group_data(struct evsel *leader, - int cpu, int thread, u64 *data) +static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data) { u64 read_format = leader->core.attr.read_format; struct sample_read_value *v; @@ -1366,18 +1467,16 @@ perf_evsel__process_group_data(struct evsel *leader, v = (struct sample_read_value *) data; - perf_evsel__set_count(leader, cpu, thread, - v[0].value, ena, run); + evsel__set_count(leader, cpu, thread, v[0].value, ena, run); for (i = 1; i < nr; i++) { struct evsel *counter; - counter = perf_evlist__id2evsel(leader->evlist, v[i].id); + counter = evlist__id2evsel(leader->evlist, v[i].id); if (!counter) return -EINVAL; - perf_evsel__set_count(counter, cpu, thread, - v[i].value, ena, run); + evsel__set_count(counter, cpu, thread, v[i].value, ena, run); } return 0; @@ -1410,7 +1509,7 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread) if (readn(FD(leader, cpu, thread), data, size) <= 0) return -errno; - return perf_evsel__process_group_data(leader, cpu, thread, data); + return evsel__process_group_data(leader, cpu, thread, data); } int evsel__read_counter(struct evsel *evsel, int cpu, int thread) @@ -1463,9 +1562,7 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread) return fd; } -static void perf_evsel__remove_fd(struct evsel *pos, - int nr_cpus, int nr_threads, - int thread_idx) +static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) { for (int cpu = 0; cpu < nr_cpus; cpu++) for (int thread = thread_idx; thread < nr_threads - 1; thread++) @@ -1484,7 +1581,7 @@ static int update_fds(struct evsel *evsel, evlist__for_each_entry(evsel->evlist, pos) { nr_cpus = pos != evsel ? nr_cpus : cpu_idx; - perf_evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx); + evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx); /* * Since fds for next evsel has not been created, @@ -1684,6 +1781,11 @@ retry_open: FD(evsel, cpu, thread) = fd; + if (unlikely(test_attr__enabled)) { + test_attr__open(&evsel->core.attr, pid, cpus->map[cpu], + fd, group_fd, flags); + } + if (fd < 0) { err = -errno; @@ -1771,7 +1873,12 @@ try_fallback: * Must probe features in the order they were added to the * perf_event_attr interface. */ - if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { + if (!perf_missing_features.data_page_size && + (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)) { + perf_missing_features.data_page_size = true; + pr_debug2_peo("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n"); + goto out_close; + } else if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { perf_missing_features.cgroup = true; pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n"); goto out_close; @@ -2256,6 +2363,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } + data->data_page_size = 0; + if (type & PERF_SAMPLE_DATA_PAGE_SIZE) { + data->data_page_size = *array; + array++; + } + if (type & PERF_SAMPLE_AUX) { OVERFLOW_CHECK_u64(array); sz = *array++; @@ -2565,6 +2678,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, "We found oprofile daemon running, please stop it and try again."); break; case EINVAL: + if (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE && perf_missing_features.data_page_size) + return scnprintf(msg, size, "Asking for the data page size isn't supported by this kernel."); if (evsel->core.attr.write_backward && perf_missing_features.write_backward) return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel."); if (perf_missing_features.clockid) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 35e3f6d66085b..cd1d8dd431997 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -42,65 +42,79 @@ enum perf_tool_event { */ struct evsel { struct perf_evsel core; - struct evlist *evlist; - char *filter; + struct evlist *evlist; + off_t id_offset; + int idx; + int id_pos; + int is_pos; + unsigned int sample_size; + + /* + * These fields can be set in the parse-events code or similar. + * Please check evsel__clone() to copy them properly so that + * they can be released properly. + */ + struct { + char *name; + char *group_name; + const char *pmu_name; + struct tep_event *tp_format; + char *filter; + unsigned long max_events; + double scale; + const char *unit; + struct cgroup *cgrp; + enum perf_tool_event tool_event; + /* parse modifier helper */ + int exclude_GH; + int sample_read; + bool snapshot; + bool per_pkg; + bool percore; + bool precise_max; + bool use_uncore_alias; + bool is_libpfm_event; + bool auto_merge_stats; + bool collect_stat; + bool weak_group; + int bpf_fd; + struct bpf_object *bpf_obj; + }; + + /* + * metric fields are similar, but needs more care as they can have + * references to other metric (evsel). + */ + const char * metric_expr; + const char * metric_name; + struct evsel **metric_events; + struct evsel *metric_leader; + + void *handler; struct perf_counts *counts; struct perf_counts *prev_raw_counts; - int idx; - unsigned long max_events; unsigned long nr_events_printed; - char *name; - double scale; - const char *unit; - struct tep_event *tp_format; - off_t id_offset; struct perf_stat_evsel *stats; void *priv; u64 db_id; - struct cgroup *cgrp; - void *handler; - unsigned int sample_size; - int id_pos; - int is_pos; - enum perf_tool_event tool_event; bool uniquified_name; - bool snapshot; bool supported; bool needs_swap; bool disabled; bool no_aux_samples; bool immediate; bool tracking; - bool per_pkg; - bool precise_max; bool ignore_missing_thread; bool forced_leader; - bool use_uncore_alias; - bool is_libpfm_event; - /* parse modifier helper */ - int exclude_GH; - int sample_read; - unsigned long *per_pkg_mask; - struct evsel *leader; - char *group_name; bool cmdline_group_boundary; - struct list_head config_terms; - struct bpf_object *bpf_obj; - int bpf_fd; - int err; - bool auto_merge_stats; bool merged_stat; - const char * metric_expr; - const char * metric_name; - struct evsel **metric_events; - struct evsel *metric_leader; - bool collect_stat; - bool weak_group; bool reset_group; bool errored; - bool percore; + unsigned long *per_pkg_mask; + struct evsel *leader; + struct list_head config_terms; + int err; int cpu_iter; - const char *pmu_name; struct { evsel__sb_cb_t *cb; void *data; @@ -130,6 +144,7 @@ struct perf_missing_features { bool aux_output; bool branch_hw_idx; bool cgroup; + bool data_page_size; }; extern struct perf_missing_features perf_missing_features; @@ -169,6 +184,7 @@ 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__newtp_idx(const char *sys, const char *name, int idx); /* diff --git a/tools/perf/util/evswitch.c b/tools/perf/util/evswitch.c index 3ba72f743d3c9..40cb56a9347da 100644 --- a/tools/perf/util/evswitch.c +++ b/tools/perf/util/evswitch.c @@ -41,7 +41,7 @@ static int evswitch__fprintf_enoent(FILE *fp, const char *evtype, const char *ev int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp) { if (evswitch->on_name) { - evswitch->on = perf_evlist__find_evsel_by_str(evlist, evswitch->on_name); + evswitch->on = evlist__find_evsel_by_str(evlist, evswitch->on_name); if (evswitch->on == NULL) { evswitch__fprintf_enoent(fp, "on", evswitch->on_name); return -ENOENT; @@ -50,7 +50,7 @@ int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp) } if (evswitch->off_name) { - evswitch->off = perf_evlist__find_evsel_by_str(evlist, evswitch->off_name); + evswitch->off = evlist__find_evsel_by_str(evlist, evswitch->off_name); if (evswitch->off == NULL) { evswitch__fprintf_enoent(fp, "off", evswitch->off_name); return -ENOENT; diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 53482ef53c411..a850fd0be3ee2 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -17,6 +17,29 @@ extern int expr_debug; #endif +struct expr_id_data { + union { + double val; + struct { + double val; + const char *metric_name; + const char *metric_expr; + } ref; + struct expr_id *parent; + }; + + enum { + /* Holding a double value. */ + EXPR_ID_DATA__VALUE, + /* Reference to another metric. */ + EXPR_ID_DATA__REF, + /* A reference but the value has been computed. */ + EXPR_ID_DATA__REF_VALUE, + /* A parent is remembered for the recursion check. */ + EXPR_ID_DATA__PARENT, + } kind; +}; + static size_t key_hash(const void *key, void *ctx __maybe_unused) { const char *str = (const char *)key; @@ -48,6 +71,7 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id) return -ENOMEM; data_ptr->parent = ctx->parent; + data_ptr->kind = EXPR_ID_DATA__PARENT; ret = hashmap__set(&ctx->ids, id, data_ptr, (const void **)&old_key, (void **)&old_data); @@ -69,7 +93,7 @@ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val) if (!data_ptr) return -ENOMEM; data_ptr->val = val; - data_ptr->is_ref = false; + data_ptr->kind = EXPR_ID_DATA__VALUE; ret = hashmap__set(&ctx->ids, id, data_ptr, (const void **)&old_key, (void **)&old_data); @@ -114,8 +138,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) */ data_ptr->ref.metric_name = ref->metric_name; data_ptr->ref.metric_expr = ref->metric_expr; - data_ptr->ref.counted = false; - data_ptr->is_ref = true; + data_ptr->kind = EXPR_ID_DATA__REF; ret = hashmap__set(&ctx->ids, name, data_ptr, (const void **)&old_key, (void **)&old_data); @@ -148,17 +171,30 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, data = *datap; - pr_debug2("lookup: is_ref %d, counted %d, val %f: %s\n", - data->is_ref, data->ref.counted, data->val, id); - - if (data->is_ref && !data->ref.counted) { - data->ref.counted = true; + switch (data->kind) { + case EXPR_ID_DATA__VALUE: + pr_debug2("lookup(%s): val %f\n", id, data->val); + break; + case EXPR_ID_DATA__PARENT: + pr_debug2("lookup(%s): parent %s\n", id, data->parent->id); + break; + case EXPR_ID_DATA__REF: + pr_debug2("lookup(%s): ref metric name %s\n", id, + data->ref.metric_name); pr_debug("processing metric: %s ENTRY\n", id); - if (expr__parse(&data->val, ctx, data->ref.metric_expr, 1)) { + data->kind = EXPR_ID_DATA__REF_VALUE; + if (expr__parse(&data->ref.val, ctx, data->ref.metric_expr, 1)) { pr_debug("%s failed to count\n", id); return -1; } pr_debug("processing metric: %s EXIT: %f\n", id, data->val); + break; + case EXPR_ID_DATA__REF_VALUE: + pr_debug2("lookup(%s): ref val %f metric name %s\n", id, + data->ref.val, data->ref.metric_name); + break; + default: + assert(0); /* Unreachable. */ } return 0; @@ -241,3 +277,17 @@ int expr__find_other(const char *expr, const char *one, return ret; } + +double expr_id_data__value(const struct expr_id_data *data) +{ + if (data->kind == EXPR_ID_DATA__VALUE) + return data->val; + assert(data->kind == EXPR_ID_DATA__REF_VALUE); + return data->ref.val; +} + +struct expr_id *expr_id_data__parent(struct expr_id_data *data) +{ + assert(data->kind == EXPR_ID_DATA__PARENT); + return data->parent; +} diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index fc2b5e824a663..dcf8d19b83c85 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -23,19 +23,7 @@ struct expr_parse_ctx { struct expr_id *parent; }; -struct expr_id_data { - union { - double val; - struct { - const char *metric_name; - const char *metric_expr; - bool counted; - } ref; - struct expr_id *parent; - }; - - bool is_ref; -}; +struct expr_id_data; struct expr_scanner_ctx { int start_token; @@ -57,4 +45,7 @@ int expr__parse(double *final_val, struct expr_parse_ctx *ctx, int expr__find_other(const char *expr, const char *one, struct expr_parse_ctx *ids, int runtime); +double expr_id_data__value(const struct expr_id_data *data); +struct expr_id *expr_id_data__parent(struct expr_id_data *data); + #endif diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index d34b370391c67..b2ada8f8309a9 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -93,7 +93,7 @@ expr: NUMBER YYABORT; } - $$ = data->val; + $$ = expr_id_data__value(data); free($1); } | expr '|' expr { $$ = (long)$1 | (long)$3; } diff --git a/tools/perf/util/group.h b/tools/perf/util/group.h deleted file mode 100644 index f36c7e31780a9..0000000000000 --- a/tools/perf/util/group.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef GROUP_H -#define GROUP_H 1 - -bool arch_topdown_check_group(bool *warn); -void arch_topdown_group_warn(void); - -#endif diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c index a405dad068f59..3c20b126d60d8 100644 --- a/tools/perf/util/hashmap.c +++ b/tools/perf/util/hashmap.c @@ -15,6 +15,9 @@ /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 +/* prevent accidental re-addition of reallocarray() */ +#pragma GCC poison reallocarray + /* start with 4 buckets */ #define HASHMAP_MIN_CAP_BITS 2 diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index e0af36b0e5d83..10a4c4cd13cf7 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -15,6 +15,9 @@ static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) /* LP64 case */ return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); @@ -25,6 +28,18 @@ static inline size_t hash_bits(size_t h, int bits) #endif } +/* generic C-string hashing function */ +static inline size_t str_hash(const char *s) +{ + size_t h = 0; + + while (*s) { + h = h * 31 + *s; + s++; + } + return h; +} + typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx); typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx); @@ -162,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur; \ cur = cur->next) \ if (map->equal_fn(cur->key, (_key), map->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ if (map->equal_fn(cur->key, (_key), map->ctx)) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 9cf4efdcbbbdb..c4ed3dc2c8f40 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -19,7 +19,9 @@ #include <sys/utsname.h> #include <linux/time64.h> #include <dirent.h> +#ifdef HAVE_LIBBPF_SUPPORT #include <bpf/libbpf.h> +#endif #include <perf/cpumap.h> #include "dso.h" @@ -987,13 +989,6 @@ out: up_read(&env->bpf_progs.lock); return ret; } -#else // HAVE_LIBBPF_SUPPORT -static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused, - struct evlist *evlist __maybe_unused) -{ - return 0; -} -#endif // HAVE_LIBBPF_SUPPORT static int write_bpf_btf(struct feat_fd *ff, struct evlist *evlist __maybe_unused) @@ -1027,6 +1022,7 @@ out: up_read(&env->bpf_progs.lock); return ret; } +#endif // HAVE_LIBBPF_SUPPORT static int cpu_cache_level__sort(const void *a, const void *b) { @@ -1638,6 +1634,7 @@ static void print_dir_format(struct feat_fd *ff, FILE *fp) fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version); } +#ifdef HAVE_LIBBPF_SUPPORT static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) { struct perf_env *env = &ff->ph->env; @@ -1683,6 +1680,7 @@ static void print_bpf_btf(struct feat_fd *ff, FILE *fp) up_read(&env->bpf_progs.lock); } +#endif // HAVE_LIBBPF_SUPPORT static void free_event_desc(struct evsel *events) { @@ -2082,8 +2080,14 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev, dso = machine__findnew_dso(machine, filename); if (dso != NULL) { char sbuild_id[SBUILD_ID_SIZE]; + struct build_id bid; + size_t size = BUILD_ID_SIZE; - dso__set_build_id(dso, &bev->build_id); + if (bev->header.misc & PERF_RECORD_MISC_BUILD_ID_SIZE) + size = bev->size; + + build_id__init(&bid, bev->data, size); + dso__set_build_id(dso, &bid); if (dso_space != DSO_SPACE__USER) { struct kmod_path m = { .name = NULL, }; @@ -2095,10 +2099,9 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev, free(m.name); } - build_id__sprintf(dso->build_id, sizeof(dso->build_id), - sbuild_id); - pr_debug("build id event received for %s: %s\n", - dso->long_name, sbuild_id); + build_id__sprintf(&dso->bid, sbuild_id); + pr_debug("build id event received for %s: %s [%zu]\n", + dso->long_name, sbuild_id, size); dso__put(dso); } @@ -2260,8 +2263,7 @@ static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused) return 0; } -static struct evsel * -perf_evlist__find_by_index(struct evlist *evlist, int idx) +static struct evsel *evlist__find_by_index(struct evlist *evlist, int idx) { struct evsel *evsel; @@ -2273,16 +2275,14 @@ perf_evlist__find_by_index(struct evlist *evlist, int idx) return NULL; } -static void -perf_evlist__set_event_name(struct evlist *evlist, - struct evsel *event) +static void evlist__set_event_name(struct evlist *evlist, struct evsel *event) { struct evsel *evsel; if (!event->name) return; - evsel = perf_evlist__find_by_index(evlist, event->idx); + evsel = evlist__find_by_index(evlist, event->idx); if (!evsel) return; @@ -2310,7 +2310,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused) } for (evsel = events; evsel->core.attr.size; evsel++) - perf_evlist__set_event_name(session->evlist, evsel); + evlist__set_event_name(session->evlist, evsel); if (!session->data->is_pipe) free_event_desc(events); @@ -2933,12 +2933,6 @@ out: up_write(&env->bpf_progs.lock); return err; } -#else // HAVE_LIBBPF_SUPPORT -static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused) -{ - return 0; -} -#endif // HAVE_LIBBPF_SUPPORT static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) { @@ -2985,6 +2979,7 @@ out: free(node); return err; } +#endif // HAVE_LIBBPF_SUPPORT static int process_compressed(struct feat_fd *ff, void *data __maybe_unused) @@ -3115,8 +3110,10 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), FEAT_OPR(CLOCKID, clockid, false), FEAT_OPN(DIR_FORMAT, dir_format, false), +#ifdef HAVE_LIBBPF_SUPPORT FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false), FEAT_OPR(BPF_BTF, bpf_btf, false), +#endif FEAT_OPR(COMPRESSED, compressed, false), FEAT_OPR(CPU_PMU_CAPS, cpu_pmu_caps, false), FEAT_OPR(CLOCK_DATA, clock_data, false), @@ -3326,6 +3323,14 @@ int perf_session__write_header(struct perf_session *session, attr_offset = lseek(ff.fd, 0, SEEK_CUR); evlist__for_each_entry(evlist, evsel) { + if (evsel->core.attr.size < sizeof(evsel->core.attr)) { + /* + * We are likely in "perf inject" and have read + * from an older file. Update attr size so that + * reader gets the right offset to the ids. + */ + evsel->core.attr.size = sizeof(evsel->core.attr); + } f_attr = (struct perf_file_attr){ .attr = evsel->core.attr, .ids = { @@ -3647,7 +3652,8 @@ static int perf_file_section__process(struct perf_file_section *section, } static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, - struct perf_header *ph, int fd, + struct perf_header *ph, + struct perf_data* data, bool repipe) { struct feat_fd ff = { @@ -3656,7 +3662,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, }; ssize_t ret; - ret = readn(fd, header, sizeof(*header)); + ret = perf_data__read(data, header, sizeof(*header)); if (ret <= 0) return -1; @@ -3679,8 +3685,7 @@ static int perf_header__read_pipe(struct perf_session *session) struct perf_header *header = &session->header; struct perf_pipe_file_header f_header; - if (perf_file_header__read_pipe(&f_header, header, - perf_data__fd(session->data), + if (perf_file_header__read_pipe(&f_header, header, session->data, session->repipe) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; @@ -3735,8 +3740,7 @@ static int read_attr(int fd, struct perf_header *ph, return ret <= 0 ? -1 : 0; } -static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel, - struct tep_handle *pevent) +static int evsel__prepare_tracepoint_event(struct evsel *evsel, struct tep_handle *pevent) { struct tep_event *event; char bf[128]; @@ -3767,14 +3771,13 @@ static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel, return 0; } -static int perf_evlist__prepare_tracepoint_events(struct evlist *evlist, - struct tep_handle *pevent) +static int evlist__prepare_tracepoint_events(struct evlist *evlist, struct tep_handle *pevent) { struct evsel *pos; evlist__for_each_entry(evlist, pos) { if (pos->core.attr.type == PERF_TYPE_TRACEPOINT && - perf_evsel__prepare_tracepoint_event(pos, pevent)) + evsel__prepare_tracepoint_event(pos, pevent)) return -1; } @@ -3883,8 +3886,7 @@ int perf_session__read_header(struct perf_session *session) perf_header__process_sections(header, fd, &session->tevent, perf_file_section__process); - if (perf_evlist__prepare_tracepoint_events(session->evlist, - session->tevent.pevent)) + if (evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent)) goto out_delete_evlist; return 0; @@ -4032,7 +4034,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, evlist = *pevlist; - evsel = perf_evlist__id2evsel(evlist, ev->id); + evsel = evlist__id2evsel(evlist, ev->id); if (evsel == NULL) return -EINVAL; @@ -4105,8 +4107,7 @@ int perf_event__process_tracing_data(struct perf_session *session, return -1; } - perf_evlist__prepare_tracepoint_events(session->evlist, - session->tevent.pevent); + evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent); return size_read + padding; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 8a793e4c9400a..a08fb9ea411bd 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -188,6 +188,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR, unresolved_col_width + 4 + 2); + hists__new_col_len(hists, HISTC_MEM_DATA_PAGE_SIZE, + unresolved_col_width + 4 + 2); + } else { symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); @@ -2654,7 +2657,7 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, } } -size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp) +size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp) { struct evsel *pos; size_t ret = 0; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 96b1c13bbccc5..14f66330923d6 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -56,6 +56,7 @@ enum hist_column { HISTC_MEM_DADDR_SYMBOL, HISTC_MEM_DADDR_DSO, HISTC_MEM_PHYS_DADDR, + HISTC_MEM_DATA_PAGE_SIZE, HISTC_MEM_LOCKED, HISTC_MEM_TLB, HISTC_MEM_LVL, @@ -196,7 +197,7 @@ void hists__inc_nr_samples(struct hists *hists, bool filtered); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, bool ignore_callchains); -size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp); +size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); @@ -464,12 +465,9 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *annotation_opts); -int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, - struct hist_browser_timer *hbt, - float min_pcnt, - struct perf_env *env, - bool warn_lost_event, - struct annotation_options *annotation_options); +int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, + float min_pcnt, struct perf_env *env, bool warn_lost_event, + struct annotation_options *annotation_options); int script_browse(const char *script_opt, struct evsel *evsel); @@ -483,13 +481,13 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel, struct annotation_options *annotation_opts); #else static inline -int perf_evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, - const char *help __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused, - float min_pcnt __maybe_unused, - struct perf_env *env __maybe_unused, - bool warn_lost_event __maybe_unused, - struct annotation_options *annotation_options __maybe_unused) +int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, + const char *help __maybe_unused, + struct hist_browser_timer *hbt __maybe_unused, + float min_pcnt __maybe_unused, + struct perf_env *env __maybe_unused, + bool warn_lost_event __maybe_unused, + struct annotation_options *annotation_options __maybe_unused) { return 0; } diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index b8a5159361b41..5acf053fca7d4 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -25,6 +25,7 @@ /* SYM_L_* -- linkage of symbols */ #define SYM_L_GLOBAL(name) .globl name +#define SYM_L_WEAK(name) .weak name #define SYM_L_LOCAL(name) /* nothing */ #define ALIGN __ALIGN @@ -84,6 +85,12 @@ SYM_END(name, SYM_T_FUNC) #endif +/* SYM_FUNC_START_WEAK -- use for weak functions */ +#ifndef SYM_FUNC_START_WEAK +#define SYM_FUNC_START_WEAK(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN) +#endif + /* * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, * SYM_FUNC_START_WEAK, ... diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 0af4e81c46e2b..60214de42f31b 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1101,6 +1101,8 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt, if (queue->tid == -1 || pt->have_sched_switch) { ptq->tid = machine__get_current_tid(pt->machine, ptq->cpu); + if (ptq->tid == -1) + ptq->pid = -1; thread__zput(ptq->thread); } @@ -2518,11 +2520,10 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid, static int intel_pt_process_switch(struct intel_pt *pt, struct perf_sample *sample) { - struct evsel *evsel; pid_t tid; int cpu, ret; + struct evsel *evsel = evlist__id2evsel(pt->session->evlist, sample->id); - evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id); if (evsel != pt->switch_evsel) return 0; @@ -2603,10 +2604,8 @@ static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event, tid = sample->tid; } - if (tid == -1) { - pr_err("context_switch event has no tid\n"); - return -EINVAL; - } + if (tid == -1) + intel_pt_log("context_switch event has no tid\n"); ret = intel_pt_sync_switch(pt, cpu, tid, sample->time); if (ret <= 0) diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 0804308ef2857..055bab7a92b35 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -374,11 +374,15 @@ static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp) if (!jd->use_arch_timestamp) return timestamp; - tc.time_shift = jd->session->time_conv.time_shift; - tc.time_mult = jd->session->time_conv.time_mult; - tc.time_zero = jd->session->time_conv.time_zero; - - if (!tc.time_mult) + tc.time_shift = jd->session->time_conv.time_shift; + tc.time_mult = jd->session->time_conv.time_mult; + tc.time_zero = jd->session->time_conv.time_zero; + tc.time_cycles = jd->session->time_conv.time_cycles; + tc.time_mask = jd->session->time_conv.time_mask; + tc.cap_user_time_zero = jd->session->time_conv.cap_user_time_zero; + tc.cap_user_time_short = jd->session->time_conv.cap_user_time_short; + + if (!tc.cap_user_time_zero) return 0; return tsc_to_perf_time(timestamp, &tc); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 85587de027a51..1e9d3f982b477 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -786,11 +786,20 @@ static int machine__process_ksymbol_unregister(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) { + struct symbol *sym; struct map *map; map = maps__find(&machine->kmaps, event->ksymbol.addr); - if (map) + if (!map) + return 0; + + if (map != machine->vmlinux_map) maps__remove(&machine->kmaps, map); + else { + sym = dso__find_symbol(map->dso, map->map_ip(map, map->start)); + if (sym) + dso__delete_symbol(map->dso, sym); + } return 0; } @@ -1572,32 +1581,25 @@ static bool machine__uses_kcore(struct machine *machine) } static bool perf_event__is_extra_kernel_mmap(struct machine *machine, - union perf_event *event) + struct extra_kernel_map *xm) { return machine__is(machine, "x86_64") && - is_entry_trampoline(event->mmap.filename); + is_entry_trampoline(xm->name); } static int machine__process_extra_kernel_map(struct machine *machine, - union perf_event *event) + struct extra_kernel_map *xm) { struct dso *kernel = machine__kernel_dso(machine); - struct extra_kernel_map xm = { - .start = event->mmap.start, - .end = event->mmap.start + event->mmap.len, - .pgoff = event->mmap.pgoff, - }; if (kernel == NULL) return -1; - strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN); - - return machine__create_extra_kernel_map(machine, kernel, &xm); + return machine__create_extra_kernel_map(machine, kernel, xm); } static int machine__process_kernel_mmap_event(struct machine *machine, - union perf_event *event) + struct extra_kernel_map *xm) { struct map *map; enum dso_space_type dso_space; @@ -1612,20 +1614,18 @@ static int machine__process_kernel_mmap_event(struct machine *machine, else dso_space = DSO_SPACE__KERNEL_GUEST; - is_kernel_mmap = memcmp(event->mmap.filename, - machine->mmap_name, + is_kernel_mmap = memcmp(xm->name, machine->mmap_name, strlen(machine->mmap_name) - 1) == 0; - if (event->mmap.filename[0] == '/' || - (!is_kernel_mmap && event->mmap.filename[0] == '[')) { - map = machine__addnew_module_map(machine, event->mmap.start, - event->mmap.filename); + if (xm->name[0] == '/' || + (!is_kernel_mmap && xm->name[0] == '[')) { + map = machine__addnew_module_map(machine, xm->start, + xm->name); if (map == NULL) goto out_problem; - map->end = map->start + event->mmap.len; + map->end = map->start + xm->end - xm->start; } else if (is_kernel_mmap) { - const char *symbol_name = (event->mmap.filename + - strlen(machine->mmap_name)); + const char *symbol_name = (xm->name + strlen(machine->mmap_name)); /* * Should be there already, from the build-id table in * the header. @@ -1679,18 +1679,17 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (strstr(kernel->long_name, "vmlinux")) dso__set_short_name(kernel, "[kernel.vmlinux]", false); - machine__update_kernel_mmap(machine, event->mmap.start, - event->mmap.start + event->mmap.len); + machine__update_kernel_mmap(machine, xm->start, xm->end); /* * Avoid using a zero address (kptr_restrict) for the ref reloc * symbol. Effectively having zero here means that at record * time /proc/sys/kernel/kptr_restrict was non zero. */ - if (event->mmap.pgoff != 0) { + if (xm->pgoff != 0) { map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, symbol_name, - event->mmap.pgoff); + xm->pgoff); } if (machine__is_default_guest(machine)) { @@ -1699,8 +1698,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine, */ dso__load(kernel, machine__kernel_map(machine)); } - } else if (perf_event__is_extra_kernel_mmap(machine, event)) { - return machine__process_extra_kernel_map(machine, event); + } else if (perf_event__is_extra_kernel_mmap(machine, xm)) { + return machine__process_extra_kernel_map(machine, xm); } return 0; out_problem: @@ -1726,7 +1725,14 @@ int machine__process_mmap2_event(struct machine *machine, if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL || sample->cpumode == PERF_RECORD_MISC_KERNEL) { - ret = machine__process_kernel_mmap_event(machine, event); + struct extra_kernel_map xm = { + .start = event->mmap2.start, + .end = event->mmap2.start + event->mmap2.len, + .pgoff = event->mmap2.pgoff, + }; + + strlcpy(xm.name, event->mmap2.filename, KMAP_NAME_LEN); + ret = machine__process_kernel_mmap_event(machine, &xm); if (ret < 0) goto out_problem; return 0; @@ -1776,7 +1782,14 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL || sample->cpumode == PERF_RECORD_MISC_KERNEL) { - ret = machine__process_kernel_mmap_event(machine, event); + struct extra_kernel_map xm = { + .start = event->mmap.start, + .end = event->mmap.start + event->mmap.len, + .pgoff = event->mmap.pgoff, + }; + + strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN); + ret = machine__process_kernel_mmap_event(machine, &xm); if (ret < 0) goto out_problem; return 0; @@ -2010,11 +2023,12 @@ static void ip__resolve_ams(struct thread *thread, ams->ms.sym = al.sym; ams->ms.map = al.map; ams->phys_addr = 0; + ams->data_page_size = 0; } static void ip__resolve_data(struct thread *thread, u8 m, struct addr_map_symbol *ams, - u64 addr, u64 phys_addr) + u64 addr, u64 phys_addr, u64 daddr_page_size) { struct addr_location al; @@ -2028,6 +2042,7 @@ static void ip__resolve_data(struct thread *thread, ams->ms.sym = al.sym; ams->ms.map = al.map; ams->phys_addr = phys_addr; + ams->data_page_size = daddr_page_size; } struct mem_info *sample__resolve_mem(struct perf_sample *sample, @@ -2040,7 +2055,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, ip__resolve_ams(al->thread, &mi->iaddr, sample->ip); ip__resolve_data(al->thread, al->cpumode, &mi->daddr, - sample->addr, sample->phys_addr); + sample->addr, sample->phys_addr, + sample->data_page_size); mi->data_src.val = sample->data_src; return mi; @@ -2964,7 +2980,7 @@ int machines__for_each_thread(struct machines *machines, pid_t machine__get_current_tid(struct machine *machine, int cpu) { - int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS); + int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS); if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid) return -1; @@ -2976,7 +2992,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, pid_t tid) { struct thread *thread; - int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS); + int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS); if (cpu < 0) return -EINVAL; @@ -3100,3 +3116,15 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch *addrp = map->unmap_ip(map, sym->start); return sym->name; } + +int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv) +{ + struct dso *pos; + int err = 0; + + list_for_each_entry(pos, &machine->dsos.head, node) { + if (fn(pos, machine, priv)) + err = -1; + } + return err; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 062c36a8433ce..26368d3c17543 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -250,6 +250,10 @@ void machines__destroy_kernel_maps(struct machines *machines); size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); +typedef int (*machine__dso_t)(struct dso *dso, struct machine *machine, void *priv); + +int machine__for_each_dso(struct machine *machine, machine__dso_t fn, + void *priv); int machine__for_each_thread(struct machine *machine, int (*fn)(struct thread *thread, void *p), void *priv); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index cc0faf8f13219..f44ede437dc7f 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -27,21 +27,6 @@ static void __maps__insert(struct maps *maps, struct map *map); -static inline int is_anon_memory(const char *filename, u32 flags) -{ - return flags & MAP_HUGETLB || - !strcmp(filename, "//anon") || - !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) || - !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1); -} - -static inline int is_no_dso_memory(const char *filename) -{ - return !strncmp(filename, "[stack", 6) || - !strncmp(filename, "/SYSV",5) || - !strcmp(filename, "[heap]"); -} - static inline int is_android_lib(const char *filename) { return strstarts(filename, "/data/app-lib/") || @@ -158,7 +143,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, int anon, no_dso, vdso, android; android = is_android_lib(filename); - anon = is_anon_memory(filename, flags); + anon = is_anon_memory(filename) || flags & MAP_HUGETLB; vdso = is_vdso_map(filename); no_dso = is_no_dso_memory(filename); map->prot = prot; @@ -346,9 +331,7 @@ int map__load(struct map *map) if (map->dso->has_build_id) { char sbuild_id[SBUILD_ID_SIZE]; - build_id__sprintf(map->dso->build_id, - sizeof(map->dso->build_id), - sbuild_id); + build_id__sprintf(&map->dso->bid, sbuild_id); pr_debug("%s with build id %s not found", name, sbuild_id); } else pr_debug("Failed to open %s", name); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index c2f5d28fe73ac..b1c0686db1b7f 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -171,4 +171,18 @@ static inline bool is_bpf_image(const char *name) return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 || strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0; } + +static inline int is_anon_memory(const char *filename) +{ + return !strcmp(filename, "//anon") || + !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) || + !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1); +} + +static inline int is_no_dso_memory(const char *filename) +{ + return !strncmp(filename, "[stack", 6) || + !strncmp(filename, "/SYSV", 5) || + !strcmp(filename, "[heap]"); +} #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 5b8ca93798e9a..7d22ade082c8f 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -19,5 +19,6 @@ struct addr_map_symbol { u64 addr; u64 al_addr; u64 phys_addr; + u64 data_page_size; }; #endif // __PERF_MAP_SYMBOL diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index ea0af0bc4314a..19007e463b8ab 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -17,9 +17,10 @@ unsigned int perf_mem_events__loads_ldlat = 30; #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } -struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { - E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "mem-loads"), - E("ldlat-stores", "cpu/mem-stores/P", "mem-stores"), +static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { + E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "cpu/events/mem-loads"), + E("ldlat-stores", "cpu/mem-stores/P", "cpu/events/mem-stores"), + E(NULL, NULL, NULL), }; #undef E @@ -28,19 +29,31 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { static char mem_loads_name[100]; static bool mem_loads_name__init; +struct perf_mem_event * __weak perf_mem_events__ptr(int i) +{ + if (i >= PERF_MEM_EVENTS__MAX) + return NULL; + + return &perf_mem_events[i]; +} + char * __weak perf_mem_events__name(int i) { + struct perf_mem_event *e = perf_mem_events__ptr(i); + + if (!e) + return NULL; + if (i == PERF_MEM_EVENTS__LOAD) { if (!mem_loads_name__init) { mem_loads_name__init = true; scnprintf(mem_loads_name, sizeof(mem_loads_name), - perf_mem_events[i].name, - perf_mem_events__loads_ldlat); + e->name, perf_mem_events__loads_ldlat); } return mem_loads_name; } - return (char *)perf_mem_events[i].name; + return (char *)e->name; } int perf_mem_events__parse(const char *str) @@ -61,7 +74,10 @@ int perf_mem_events__parse(const char *str) while (tok) { for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - struct perf_mem_event *e = &perf_mem_events[j]; + struct perf_mem_event *e = perf_mem_events__ptr(j); + + if (!e->tag) + continue; if (strstr(e->tag, tok)) e->record = found = true; @@ -90,10 +106,17 @@ int perf_mem_events__init(void) for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { char path[PATH_MAX]; - struct perf_mem_event *e = &perf_mem_events[j]; + struct perf_mem_event *e = perf_mem_events__ptr(j); struct stat st; - scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s", + /* + * If the event entry isn't valid, skip initialization + * and "e->supported" will keep false. + */ + if (!e->tag) + continue; + + scnprintf(path, PATH_MAX, "%s/devices/%s", mnt, e->sysfs_name); if (!stat(path, &st)) @@ -108,10 +131,10 @@ void perf_mem_events__list(void) int j; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - struct perf_mem_event *e = &perf_mem_events[j]; + struct perf_mem_event *e = perf_mem_events__ptr(j); fprintf(stderr, "%-13s%-*s%s\n", - e->tag, + e->tag ?: "", verbose > 0 ? 25 : 0, verbose > 0 ? perf_mem_events__name(j) : "", e->supported ? ": available" : ""); diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 904dad34f7f7e..5ef178278909b 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -28,16 +28,17 @@ struct mem_info { enum { PERF_MEM_EVENTS__LOAD, PERF_MEM_EVENTS__STORE, + PERF_MEM_EVENTS__LOAD_STORE, PERF_MEM_EVENTS__MAX, }; -extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX]; extern unsigned int perf_mem_events__loads_ldlat; int perf_mem_events__parse(const char *str); int perf_mem_events__init(void); char *perf_mem_events__name(int i); +struct perf_mem_event *perf_mem_events__ptr(int i); void perf_mem_events__list(void); diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c index c84f5841c7abd..03a7d7b277377 100644 --- a/tools/perf/util/mem2node.c +++ b/tools/perf/util/mem2node.c @@ -96,7 +96,8 @@ int mem2node__init(struct mem2node *map, struct perf_env *env) /* Cut unused entries, due to merging. */ tmp_entries = realloc(entries, sizeof(*entries) * j); - if (tmp_entries || WARN_ON_ONCE(j == 0)) + if (tmp_entries || + WARN_ONCE(j == 0, "No memory nodes, is CONFIG_MEMORY_HOTPLUG enabled?\n")) entries = tmp_entries; for (i = 0; i < j; i++) { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index ab5030fcfed4e..e6d3452031e52 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -15,7 +15,6 @@ #include "rblist.h" #include <string.h> #include <errno.h> -#include "pmu-events/pmu-events.h" #include "strlist.h" #include <assert.h> #include <linux/ctype.h> @@ -25,6 +24,7 @@ #include <api/fs/fs.h> #include "util.h" #include <asm/bug.h> +#include "cgroup.h" struct metric_event *metricgroup__lookup(struct rblist *metric_events, struct evsel *evsel, @@ -150,8 +150,28 @@ static void expr_ids__exit(struct expr_ids *ids) free(ids->id[i].id); } +static bool contains_event(struct evsel **metric_events, int num_events, + const char *event_name) +{ + int i; + + for (i = 0; i < num_events; i++) { + if (!strcmp(metric_events[i]->name, event_name)) + return true; + } + return false; +} + +static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2) +{ + if (!ev1->pmu_name || !ev2->pmu_name) + return false; + + return !strcmp(ev1->pmu_name, ev2->pmu_name); +} + /** - * Find a group of events in perf_evlist that correpond to those from a parsed + * Find a group of events in perf_evlist that correspond to those from a parsed * metric expression. Note, as find_evsel_group is called in the same order as * perf_evlist was constructed, metric_no_merge doesn't need to test for * underfilling a group. @@ -180,7 +200,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, int i = 0, matched_events = 0, events_to_match; const int idnum = (int)hashmap__size(&pctx->ids); - /* duration_time is grouped separately. */ + /* + * duration_time is always grouped separately, when events are grouped + * (ie has_constraint is false) then ignore it in the matching loop and + * add it to metric_events at the end. + */ if (!has_constraint && hashmap__find(&pctx->ids, "duration_time", (void **)&val_ptr)) events_to_match = idnum - 1; @@ -207,23 +231,20 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, sizeof(struct evsel *) * idnum); current_leader = ev->leader; } - if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) { - if (has_constraint) { - /* - * Events aren't grouped, ensure the same event - * isn't matched from two groups. - */ - for (i = 0; i < matched_events; i++) { - if (!strcmp(ev->name, - metric_events[i]->name)) { - break; - } - } - if (i != matched_events) - continue; - } + /* + * Check for duplicate events with the same name. For example, + * uncore_imc/cas_count_read/ will turn into 6 events per socket + * on skylakex. Only the first such event is placed in + * metric_events. If events aren't grouped then this also + * ensures that the same event in different sibling groups + * aren't both added to metric_events. + */ + if (contains_event(metric_events, matched_events, ev->name)) + continue; + /* Does this event belong to the parse context? */ + if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) metric_events[matched_events++] = ev; - } + if (matched_events == events_to_match) break; } @@ -239,7 +260,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, } if (matched_events != idnum) { - /* Not whole match */ + /* Not a whole match */ return NULL; } @@ -247,8 +268,33 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, for (i = 0; i < idnum; i++) { ev = metric_events[i]; - ev->metric_leader = ev; + /* Don't free the used events. */ set_bit(ev->idx, evlist_used); + /* + * The metric leader points to the identically named event in + * metric_events. + */ + ev->metric_leader = ev; + /* + * Mark two events with identical names in the same group (or + * globally) as being in use as uncore events may be duplicated + * for each pmu. Set the metric leader of such events to be the + * event that appears in metric_events. + */ + evlist__for_each_entry_continue(perf_evlist, ev) { + /* + * If events are grouped then the search can terminate + * when then group is left. + */ + if (!has_constraint && + ev->leader != metric_events[i]->leader && + evsel_same_pmu(ev->leader, metric_events[i]->leader)) + break; + if (!strcmp(metric_events[i]->name, ev->name)) { + set_bit(ev->idx, evlist_used); + ev->metric_leader = metric_events[i]; + } + } } return metric_events[0]; @@ -376,6 +422,12 @@ static bool match_metric(const char *n, const char *list) return false; } +static bool match_pe_metric(struct pmu_event *pe, const char *metric) +{ + return match_metric(pe->metric_group, metric) || + match_metric(pe->metric_name, metric); +} + struct mep { struct rb_node nd; const char *name; @@ -454,6 +506,115 @@ static void metricgroup__print_strlist(struct strlist *metrics, bool raw) putchar('\n'); } +static int metricgroup__print_pmu_event(struct pmu_event *pe, + bool metricgroups, char *filter, + bool raw, bool details, + struct rblist *groups, + struct strlist *metriclist) +{ + const char *g; + char *omg, *mg; + + g = pe->metric_group; + if (!g && pe->metric_name) { + if (pe->name) + return 0; + g = "No_group"; + } + + if (!g) + return 0; + + mg = strdup(g); + + if (!mg) + return -ENOMEM; + omg = mg; + while ((g = strsep(&mg, ";")) != NULL) { + struct mep *me; + char *s; + + g = skip_spaces(g); + if (*g == 0) + g = "No_group"; + if (filter && !strstr(g, filter)) + continue; + if (raw) + s = (char *)pe->metric_name; + else { + if (asprintf(&s, "%s\n%*s%s]", + pe->metric_name, 8, "[", pe->desc) < 0) + return -1; + if (details) { + if (asprintf(&s, "%s\n%*s%s]", + s, 8, "[", pe->metric_expr) < 0) + return -1; + } + } + + if (!s) + continue; + + if (!metricgroups) { + strlist__add(metriclist, s); + } else { + me = mep_lookup(groups, g); + if (!me) + continue; + strlist__add(me->metrics, s); + } + + if (!raw) + free(s); + } + free(omg); + + return 0; +} + +struct metricgroup_print_sys_idata { + struct strlist *metriclist; + char *filter; + struct rblist *groups; + bool metricgroups; + bool raw; + bool details; +}; + +typedef int (*metricgroup_sys_event_iter_fn)(struct pmu_event *pe, void *); + +struct metricgroup_iter_data { + metricgroup_sys_event_iter_fn fn; + void *data; +}; + +static int metricgroup__sys_event_iter(struct pmu_event *pe, void *data) +{ + struct metricgroup_iter_data *d = data; + struct perf_pmu *pmu = NULL; + + if (!pe->metric_expr || !pe->compat) + return 0; + + while ((pmu = perf_pmu__scan(pmu))) { + + if (!pmu->id || strcmp(pmu->id, pe->compat)) + continue; + + return d->fn(pe, d->data); + } + + return 0; +} + +static int metricgroup__print_sys_event_iter(struct pmu_event *pe, void *data) +{ + struct metricgroup_print_sys_idata *d = data; + + return metricgroup__print_pmu_event(pe, d->metricgroups, d->filter, d->raw, + d->details, d->groups, d->metriclist); +} + void metricgroup__print(bool metrics, bool metricgroups, char *filter, bool raw, bool details) { @@ -464,9 +625,6 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, struct rb_node *node, *next; struct strlist *metriclist = NULL; - if (!map) - return; - if (!metricgroups) { metriclist = strlist__new(NULL, NULL); if (!metriclist) @@ -477,73 +635,41 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, groups.node_new = mep_new; groups.node_cmp = mep_cmp; groups.node_delete = mep_delete; - for (i = 0; ; i++) { - const char *g; + for (i = 0; map; i++) { pe = &map->table[i]; if (!pe->name && !pe->metric_group && !pe->metric_name) break; if (!pe->metric_expr) continue; - g = pe->metric_group; - if (!g && pe->metric_name) { - if (pe->name) - continue; - g = "No_group"; - } - if (g) { - char *omg; - char *mg = strdup(g); - - if (!mg) - return; - omg = mg; - while ((g = strsep(&mg, ";")) != NULL) { - struct mep *me; - char *s; - - g = skip_spaces(g); - if (*g == 0) - g = "No_group"; - if (filter && !strstr(g, filter)) - continue; - if (raw) - s = (char *)pe->metric_name; - else { - if (asprintf(&s, "%s\n%*s%s]", - pe->metric_name, 8, "[", pe->desc) < 0) - return; - - if (details) { - if (asprintf(&s, "%s\n%*s%s]", - s, 8, "[", pe->metric_expr) < 0) - return; - } - } - - if (!s) - continue; + if (metricgroup__print_pmu_event(pe, metricgroups, filter, + raw, details, &groups, + metriclist) < 0) + return; + } - if (!metricgroups) { - strlist__add(metriclist, s); - } else { - me = mep_lookup(&groups, g); - if (!me) - continue; - strlist__add(me->metrics, s); - } + { + struct metricgroup_iter_data data = { + .fn = metricgroup__print_sys_event_iter, + .data = (void *) &(struct metricgroup_print_sys_idata){ + .metriclist = metriclist, + .metricgroups = metricgroups, + .filter = filter, + .raw = raw, + .details = details, + .groups = &groups, + }, + }; - if (!raw) - free(s); - } - free(omg); - } + pmu_for_each_sys_event(metricgroup__sys_event_iter, &data); } - if (metricgroups && !raw) - printf("\nMetric Groups:\n\n"); - else if (metrics && !raw) - printf("\nMetrics:\n\n"); + if (!filter || !rblist__empty(&groups)) { + if (metricgroups && !raw) + printf("\nMetric Groups:\n\n"); + else if (metrics && !raw) + printf("\nMetrics:\n\n"); + } for (node = rb_first_cached(&groups.entries); node; node = next) { struct mep *me = container_of(node, struct mep, nd); @@ -639,11 +765,20 @@ static bool metricgroup__has_constraint(struct pmu_event *pe) return false; } -int __weak arch_get_runtimeparam(void) +int __weak arch_get_runtimeparam(struct pmu_event *pe __maybe_unused) { return 1; } +struct metricgroup_add_iter_data { + struct list_head *metric_list; + const char *metric; + struct expr_ids *ids; + int *ret; + bool *has_match; + bool metric_no_group; +}; + static int __add_metric(struct list_head *metric_list, struct pmu_event *pe, bool metric_no_group, @@ -753,10 +888,11 @@ static int __add_metric(struct list_head *metric_list, return 0; } -#define map_for_each_event(__pe, __idx, __map) \ - for (__idx = 0, __pe = &__map->table[__idx]; \ - __pe->name || __pe->metric_group || __pe->metric_name; \ - __pe = &__map->table[++__idx]) +#define map_for_each_event(__pe, __idx, __map) \ + if (__map) \ + for (__idx = 0, __pe = &__map->table[__idx]; \ + __pe->name || __pe->metric_group || __pe->metric_name; \ + __pe = &__map->table[++__idx]) #define map_for_each_metric(__pe, __idx, __map, __metric) \ map_for_each_event(__pe, __idx, __map) \ @@ -794,7 +930,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa if (ret) return ret; - p = data->parent; + p = expr_id_data__parent(data); while (p->parent) { if (!strcmp(p->id, id)) { @@ -815,7 +951,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa } p->id = strdup(id); - p->parent = data->parent; + p->parent = expr_id_data__parent(data); *parent = p; return p->id ? 0 : -ENOMEM; @@ -910,7 +1046,7 @@ static int add_metric(struct list_head *metric_list, } else { int j, count; - count = arch_get_runtimeparam(); + count = arch_get_runtimeparam(pe); /* This loop is added to create multiple * events depend on count value and add @@ -924,6 +1060,30 @@ static int add_metric(struct list_head *metric_list, return ret; } +static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe, + void *data) +{ + struct metricgroup_add_iter_data *d = data; + struct metric *m = NULL; + int ret; + + if (!match_pe_metric(pe, d->metric)) + return 0; + + ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids); + if (ret) + return ret; + + ret = resolve_metric(d->metric_no_group, + d->metric_list, NULL, d->ids); + if (ret) + return ret; + + *(d->has_match) = true; + + return *d->ret; +} + static int metricgroup__add_metric(const char *metric, bool metric_no_group, struct strbuf *events, struct list_head *metric_list, @@ -954,6 +1114,21 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group, goto out; } + { + struct metricgroup_iter_data data = { + .fn = metricgroup__add_metric_sys_event_iter, + .data = (void *) &(struct metricgroup_add_iter_data) { + .metric_list = &list, + .metric = metric, + .metric_no_group = metric_no_group, + .ids = &ids, + .has_match = &has_match, + .ret = &ret, + }, + }; + + pmu_for_each_sys_event(metricgroup__sys_event_iter, &data); + } /* End of pmu events. */ if (!has_match) { ret = -EINVAL; @@ -1080,8 +1255,6 @@ int metricgroup__parse_groups(const struct option *opt, struct evlist *perf_evlist = *(struct evlist **)opt->value; struct pmu_events_map *map = perf_pmu__find_map(NULL); - if (!map) - return 0; return parse_groups(perf_evlist, str, metric_no_group, metric_no_merge, NULL, metric_events, map); @@ -1119,3 +1292,87 @@ bool metricgroup__has_metric(const char *metric) } return false; } + +int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, + struct rblist *new_metric_events, + struct rblist *old_metric_events) +{ + unsigned i; + + for (i = 0; i < rblist__nr_entries(old_metric_events); i++) { + struct rb_node *nd; + struct metric_event *old_me, *new_me; + struct metric_expr *old_expr, *new_expr; + struct evsel *evsel; + size_t alloc_size; + int idx, nr; + + nd = rblist__entry(old_metric_events, i); + old_me = container_of(nd, struct metric_event, nd); + + evsel = evlist__find_evsel(evlist, old_me->evsel->idx); + if (!evsel) + return -EINVAL; + new_me = metricgroup__lookup(new_metric_events, evsel, true); + if (!new_me) + return -ENOMEM; + + pr_debug("copying metric event for cgroup '%s': %s (idx=%d)\n", + cgrp ? cgrp->name : "root", evsel->name, evsel->idx); + + list_for_each_entry(old_expr, &old_me->head, nd) { + new_expr = malloc(sizeof(*new_expr)); + if (!new_expr) + return -ENOMEM; + + new_expr->metric_expr = old_expr->metric_expr; + new_expr->metric_name = old_expr->metric_name; + new_expr->metric_unit = old_expr->metric_unit; + new_expr->runtime = old_expr->runtime; + + if (old_expr->metric_refs) { + /* calculate number of metric_events */ + for (nr = 0; old_expr->metric_refs[nr].metric_name; nr++) + continue; + alloc_size = sizeof(*new_expr->metric_refs); + new_expr->metric_refs = calloc(nr + 1, alloc_size); + if (!new_expr->metric_refs) { + free(new_expr); + return -ENOMEM; + } + + memcpy(new_expr->metric_refs, old_expr->metric_refs, + nr * alloc_size); + } else { + new_expr->metric_refs = NULL; + } + + /* calculate number of metric_events */ + for (nr = 0; old_expr->metric_events[nr]; nr++) + continue; + alloc_size = sizeof(*new_expr->metric_events); + new_expr->metric_events = calloc(nr + 1, alloc_size); + if (!new_expr->metric_events) { + free(new_expr->metric_refs); + free(new_expr); + return -ENOMEM; + } + + /* copy evsel in the same position */ + for (idx = 0; idx < nr; idx++) { + evsel = old_expr->metric_events[idx]; + evsel = evlist__find_evsel(evlist, evsel->idx); + if (evsel == NULL) { + free(new_expr->metric_events); + free(new_expr->metric_refs); + free(new_expr); + return -EINVAL; + } + new_expr->metric_events[idx] = evsel; + } + + list_add(&new_expr->nd, &new_me->head); + } + } + return 0; +} diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 62623a39cbecd..ed1b9392e624d 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -5,12 +5,15 @@ #include <linux/list.h> #include <linux/rbtree.h> #include <stdbool.h> +#include "pmu-events/pmu-events.h" +struct evlist; struct evsel; struct evlist; struct option; struct rblist; struct pmu_events_map; +struct cgroup; struct metric_event { struct rb_node nd; @@ -52,6 +55,10 @@ int metricgroup__parse_groups_test(struct evlist *evlist, void metricgroup__print(bool metrics, bool groups, char *filter, bool raw, bool details); bool metricgroup__has_metric(const char *metric); -int arch_get_runtimeparam(void); +int arch_get_runtimeparam(struct pmu_event *pe __maybe_unused); void metricgroup__rblist_exit(struct rblist *metric_events); + +int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, + struct rblist *new_metric_events, + struct rblist *old_metric_events); #endif diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 667cbca1547ac..42c84adeb2fbe 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -353,18 +353,20 @@ __add_event(struct list_head *list, int *idx, const char *cpu_list) { struct evsel *evsel; - struct perf_cpu_map *cpus = pmu ? pmu->cpus : + struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) : cpu_list ? perf_cpu_map__new(cpu_list) : NULL; if (init_attr) event_attr_init(attr); evsel = evsel__new_idx(attr, *idx); - if (!evsel) + if (!evsel) { + perf_cpu_map__put(cpus); return NULL; + } (*idx)++; - evsel->core.cpus = perf_cpu_map__get(cpus); + evsel->core.cpus = cpus; evsel->core.own_cpus = perf_cpu_map__get(cpus); evsel->core.system_wide = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats; @@ -666,6 +668,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, return ret; } +#ifdef HAVE_LIBBPF_SUPPORT struct __add_bpf_event_param { struct parse_events_state *parse_state; struct list_head *list; @@ -898,6 +901,30 @@ int parse_events_load_bpf(struct parse_events_state *parse_state, list_splice_tail(&obj_head_config, head_config); return err; } +#else // HAVE_LIBBPF_SUPPORT +int parse_events_load_bpf_obj(struct parse_events_state *parse_state, + struct list_head *list __maybe_unused, + struct bpf_object *obj __maybe_unused, + struct list_head *head_config __maybe_unused) +{ + parse_events__handle_error(parse_state->error, 0, + strdup("BPF support is not compiled"), + strdup("Make sure libbpf-devel is available at build time.")); + return -ENOTSUP; +} + +int parse_events_load_bpf(struct parse_events_state *parse_state, + struct list_head *list __maybe_unused, + char *bpf_file_name __maybe_unused, + bool source __maybe_unused, + struct list_head *head_config __maybe_unused) +{ + parse_events__handle_error(parse_state->error, 0, + strdup("BPF support is not compiled"), + strdup("Make sure libbpf-devel is available at build time.")); + return -ENOTSUP; +} +#endif // HAVE_LIBBPF_SUPPORT static int parse_breakpoint_type(const char *type, struct perf_event_attr *attr) @@ -940,12 +967,12 @@ do { \ } int parse_events_add_breakpoint(struct list_head *list, int *idx, - void *ptr, char *type, u64 len) + u64 addr, char *type, u64 len) { struct perf_event_attr attr; memset(&attr, 0, sizeof(attr)); - attr.bp_addr = (unsigned long) ptr; + attr.bp_addr = addr; if (parse_breakpoint_type(type, &attr)) return -EINVAL; @@ -1742,7 +1769,7 @@ void parse_events__set_leader(char *name, struct list_head *list, if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state)) return; - __perf_evlist__set_leader(list); + __evlist__set_leader(list); leader = list_entry(list->next, struct evsel, core.node); leader->group_name = name ? strdup(name) : NULL; } @@ -1773,6 +1800,7 @@ struct event_modifier { int sample_read; int pinned; int weak; + int exclusive; }; static int get_event_modifier(struct event_modifier *mod, char *str, @@ -1788,6 +1816,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, int precise_max = 0; int sample_read = 0; int pinned = evsel ? evsel->core.attr.pinned : 0; + int exclusive = evsel ? evsel->core.attr.exclusive : 0; int exclude = eu | ek | eh; int exclude_GH = evsel ? evsel->exclude_GH : 0; @@ -1831,6 +1860,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, sample_read = 1; } else if (*str == 'D') { pinned = 1; + } else if (*str == 'e') { + exclusive = 1; } else if (*str == 'W') { weak = 1; } else @@ -1864,6 +1895,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, mod->sample_read = sample_read; mod->pinned = pinned; mod->weak = weak; + mod->exclusive = exclusive; return 0; } @@ -1877,7 +1909,7 @@ static int check_modifier(char *str) char *p = str; /* The sizeof includes 0 byte as well. */ - if (strlen(str) > (sizeof("ukhGHpppPSDIW") - 1)) + if (strlen(str) > (sizeof("ukhGHpppPSDIWe") - 1)) return -1; while (*p) { @@ -1919,8 +1951,10 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) evsel->precise_max = mod.precise_max; evsel->weak_group = mod.weak; - if (evsel__is_group_leader(evsel)) + if (evsel__is_group_leader(evsel)) { evsel->core.attr.pinned = mod.pinned; + evsel->core.attr.exclusive = mod.exclusive; + } } return 0; @@ -2149,7 +2183,7 @@ int __parse_events(struct evlist *evlist, const char *str, /* * Add list to the evlist even with errors to allow callers to clean up. */ - perf_evlist__splice_list_tail(evlist, &parse_state.list); + evlist__splice_list_tail(evlist, &parse_state.list); if (!ret) { struct evsel *last; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 00cde7d2e30c7..e80c9b74f2f27 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -190,7 +190,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, struct parse_events_error *error, struct list_head *head_config); int parse_events_add_breakpoint(struct list_head *list, int *idx, - void *ptr, char *type, u64 len); + u64 addr, char *type, u64 len); int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 3ca5fd2829ca2..9db5097317f45 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -210,7 +210,7 @@ name_tag [\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\'] name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? /* If you add a modifier you need to update check_modifier() */ -modifier_event [ukhpPGHSDIW]+ +modifier_event [ukhpPGHSDIWe]+ modifier_bp [rwx]{1,3} %% diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 645bf4f1859fd..d5b6aff82f217 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -511,7 +511,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *)(uintptr_t) $2, $6, $4); + $2, $6, $4); free($6); if (err) { free(list); @@ -528,7 +528,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *)(uintptr_t) $2, NULL, $4)) { + $2, NULL, $4)) { free(list); YYABORT; } @@ -544,7 +544,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *)(uintptr_t) $2, $4, 0); + $2, $4, 0); free($4); if (err) { free(list); @@ -561,7 +561,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *)(uintptr_t) $2, NULL, 0)) { + $2, NULL, 0)) { free(list); YYABORT; } diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c index e687497b3aac0..a4a100425b3a2 100644 --- a/tools/perf/util/parse-regs-options.c +++ b/tools/perf/util/parse-regs-options.c @@ -54,7 +54,7 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr) #endif fputc('\n', stderr); /* just printing available regs */ - return -1; + goto error; } #ifdef HAVE_PERF_REGS_SUPPORT for (r = sample_reg_masks; r->name; r++) { diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index e67a227c0ce7e..fb0bb66844384 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -35,7 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value) bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX), - bit_name(CGROUP), + bit_name(CGROUP), bit_name(DATA_PAGE_SIZE), { .name = NULL, } }; #undef bit_name diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d41caeb35cf6c..44ef28302fc77 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -597,6 +597,7 @@ static struct perf_cpu_map *__pmu_cpumask(const char *path) * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) * may have a "cpus" file. */ +#define SYS_TEMPLATE_ID "./bus/event_source/devices/%s/identifier" #define CPUS_TEMPLATE_UNCORE "%s/bus/event_source/devices/%s/cpumask" #define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus" @@ -635,6 +636,21 @@ static bool pmu_is_uncore(const char *name) return file_available(path); } +static char *pmu_id(const char *name) +{ + char path[PATH_MAX], *str; + size_t len; + + snprintf(path, PATH_MAX, SYS_TEMPLATE_ID, name); + + if (sysfs__read_str(path, &str, &len) < 0) + return NULL; + + str[len - 1] = 0; /* remove line feed */ + + return str; +} + /* * PMU CORE devices have different name other than cpu in sysfs on some * platforms. @@ -796,6 +812,83 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) pmu_add_cpu_aliases_map(head, pmu, map); } +void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data) +{ + int i = 0; + + while (1) { + struct pmu_sys_events *event_table; + int j = 0; + + event_table = &pmu_sys_event_tables[i++]; + + if (!event_table->table) + break; + + while (1) { + struct pmu_event *pe = &event_table->table[j++]; + int ret; + + if (!pe->name && !pe->metric_group && !pe->metric_name) + break; + + ret = fn(pe, data); + if (ret) + break; + } + } +} + +struct pmu_sys_event_iter_data { + struct list_head *head; + struct perf_pmu *pmu; +}; + +static int pmu_add_sys_aliases_iter_fn(struct pmu_event *pe, void *data) +{ + struct pmu_sys_event_iter_data *idata = data; + struct perf_pmu *pmu = idata->pmu; + + if (!pe->name) { + if (pe->metric_group || pe->metric_name) + return 0; + return -EINVAL; + } + + if (!pe->compat || !pe->pmu) + return 0; + + if (!strcmp(pmu->id, pe->compat) && + pmu_uncore_alias_match(pe->pmu, pmu->name)) { + __perf_pmu__new_alias(idata->head, NULL, + (char *)pe->name, + (char *)pe->desc, + (char *)pe->event, + (char *)pe->long_desc, + (char *)pe->topic, + (char *)pe->unit, + (char *)pe->perpkg, + (char *)pe->metric_expr, + (char *)pe->metric_name, + (char *)pe->deprecated); + } + + return 0; +} + +static void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu) +{ + struct pmu_sys_event_iter_data idata = { + .head = head, + .pmu = pmu, + }; + + if (!pmu->id) + return; + + pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, &idata); +} + struct perf_event_attr * __weak perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) { @@ -847,8 +940,11 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->name = strdup(name); pmu->type = type; pmu->is_uncore = pmu_is_uncore(name); + if (pmu->is_uncore) + pmu->id = pmu_id(name); pmu->max_precise = pmu_max_precise(name); pmu_add_cpu_aliases(&aliases, pmu); + pmu_add_sys_aliases(&aliases, pmu); INIT_LIST_HEAD(&pmu->format); INIT_LIST_HEAD(&pmu->aliases); diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index a64e9c9ce731a..8164388478c65 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -30,6 +30,7 @@ struct perf_pmu_caps { struct perf_pmu { char *name; + char *id; __u32 type; bool selectable; bool is_uncore; @@ -116,6 +117,8 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu); bool pmu_uncore_alias_match(const char *pmu_name, const char *name); void perf_pmu_free_alias(struct perf_pmu_alias *alias); +typedef int (*pmu_sys_event_iter_fn)(struct pmu_event *pe, void *data); +void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data); int perf_pmu__convert_scale(const char *scale, char **end, double *sval); int perf_pmu__caps_parse(struct perf_pmu *pmu); diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c index 599a1543871de..13fdc51c61d96 100644 --- a/tools/perf/util/print_binary.c +++ b/tools/perf/util/print_binary.c @@ -50,7 +50,7 @@ int is_printable_array(char *p, unsigned int len) len--; - for (i = 0; i < len; i++) { + for (i = 0; i < len && p[i]; i++) { if (!isprint(p[i]) && !isspace(p[i])) return 0; } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 99d36ac77c084..8eae2afff71a9 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -43,6 +43,10 @@ #include <linux/ctype.h> #include <linux/zalloc.h> +#ifdef HAVE_DEBUGINFOD_SUPPORT +#include <elfutils/debuginfod.h> +#endif + #define PERFPROBE_GROUP "probe" bool probe_event_dry_run; /* Dry run flag */ @@ -129,9 +133,10 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, struct map *map; /* ref_reloc_sym is just a label. Need a special fix*/ - reloc_sym = kernel_get_ref_reloc_sym(NULL); + reloc_sym = kernel_get_ref_reloc_sym(&map); if (reloc_sym && strcmp(name, reloc_sym->name) == 0) - *addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr; + *addr = (!map->reloc || reloc) ? reloc_sym->addr : + reloc_sym->unrelocated_addr; else { sym = machine__find_kernel_symbol_by_name(host_machine, name, &map); if (!sym) @@ -337,6 +342,8 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso) map = machine__kernel_map(host_machine); dso = map->dso; + if (!dso->has_build_id) + dso__read_running_kernel_build_id(dso, host_machine); vmlinux_name = symbol_conf.vmlinux_name; dso->load_errno = 0; @@ -452,6 +459,49 @@ static int get_alternative_line_range(struct debuginfo *dinfo, return ret; } +#ifdef HAVE_DEBUGINFOD_SUPPORT +static struct debuginfo *open_from_debuginfod(struct dso *dso, struct nsinfo *nsi, + bool silent) +{ + debuginfod_client *c = debuginfod_begin(); + char sbuild_id[SBUILD_ID_SIZE + 1]; + struct debuginfo *ret = NULL; + struct nscookie nsc; + char *path; + int fd; + + if (!c) + return NULL; + + build_id__sprintf(&dso->bid, sbuild_id); + fd = debuginfod_find_debuginfo(c, (const unsigned char *)sbuild_id, + 0, &path); + if (fd >= 0) + close(fd); + debuginfod_end(c); + if (fd < 0) { + if (!silent) + pr_debug("Failed to find debuginfo in debuginfod.\n"); + return NULL; + } + if (!silent) + pr_debug("Load debuginfo from debuginfod (%s)\n", path); + + nsinfo__mountns_enter(nsi, &nsc); + ret = debuginfo__new((const char *)path); + nsinfo__mountns_exit(&nsc); + return ret; +} +#else +static inline +struct debuginfo *open_from_debuginfod(struct dso *dso __maybe_unused, + struct nsinfo *nsi __maybe_unused, + bool silent __maybe_unused) +{ + return NULL; +} +#endif + /* Open new debuginfo of given module */ static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi, bool silent) @@ -471,6 +521,10 @@ static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi, strcpy(reason, "(unknown)"); } else dso__strerror_load(dso, reason, STRERR_BUFSIZE); + if (dso) + ret = open_from_debuginfod(dso, nsi, silent); + if (ret) + return ret; if (!silent) { if (module) pr_err("Module %s is not loaded, please specify its full path name.\n", module); @@ -795,7 +849,8 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, free(tevs[i].point.symbol); tevs[i].point.symbol = tmp; tevs[i].point.offset = tevs[i].point.address - - reloc_sym->unrelocated_addr; + (map->reloc ? reloc_sym->unrelocated_addr : + reloc_sym->addr); } return skipped; } @@ -950,6 +1005,7 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num) static int __show_line_range(struct line_range *lr, const char *module, bool user) { + struct build_id bid; int l = 1; struct int_node *ln; struct debuginfo *dinfo; @@ -957,6 +1013,7 @@ static int __show_line_range(struct line_range *lr, const char *module, int ret; char *tmp; char sbuf[STRERR_BUFSIZE]; + char sbuild_id[SBUILD_ID_SIZE] = ""; /* Search a line range */ dinfo = open_debuginfo(module, NULL, false); @@ -969,6 +1026,10 @@ static int __show_line_range(struct line_range *lr, const char *module, if (!ret) ret = debuginfo__find_line_range(dinfo, lr); } + if (dinfo->build_id) { + build_id__init(&bid, dinfo->build_id, BUILD_ID_SIZE); + build_id__sprintf(&bid, sbuild_id); + } debuginfo__delete(dinfo); if (ret == 0 || ret == -ENOENT) { pr_warning("Specified source line is not found.\n"); @@ -980,7 +1041,7 @@ static int __show_line_range(struct line_range *lr, const char *module, /* Convert source file path */ tmp = lr->path; - ret = get_real_path(tmp, lr->comp_dir, &lr->path); + ret = find_source_path(tmp, sbuild_id, lr->comp_dir, &lr->path); /* Free old path when new path is assigned */ if (tmp != lr->path) diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 064b63a6a3f31..bbecb449ea944 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -791,7 +791,7 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note, const char *sdtgrp) { struct strbuf buf; - char *ret = NULL, **args; + char *ret = NULL; int i, args_count, err; unsigned long long ref_ctr_offset; @@ -813,12 +813,19 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note, goto out; if (note->args) { - args = argv_split(note->args, &args_count); + char **args = argv_split(note->args, &args_count); + + if (args == NULL) + goto error; for (i = 0; i < args_count; ++i) { - if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0) + if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0) { + argv_free(args); goto error; + } } + + argv_free(args); } out: diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 659024342e9ac..76dd349aa48d8 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -31,6 +31,10 @@ #include "probe-file.h" #include "string2.h" +#ifdef HAVE_DEBUGINFOD_SUPPORT +#include <elfutils/debuginfod.h> +#endif + /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 @@ -51,6 +55,7 @@ static const Dwfl_Callbacks offline_callbacks = { static int debuginfo__init_offline_dwarf(struct debuginfo *dbg, const char *path) { + GElf_Addr dummy; int fd; fd = open(path, O_RDONLY); @@ -70,6 +75,8 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg, if (!dbg->dbg) goto error; + dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy); + dwfl_report_end(dbg->dwfl, NULL, NULL); return 0; @@ -942,6 +949,8 @@ static int probe_point_lazy_walker(const char *fname, int lineno, /* Find probe points from lazy pattern */ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) { + struct build_id bid; + char sbuild_id[SBUILD_ID_SIZE] = ""; int ret = 0; char *fpath; @@ -949,7 +958,11 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) const char *comp_dir; comp_dir = cu_get_comp_dir(&pf->cu_die); - ret = get_real_path(pf->fname, comp_dir, &fpath); + if (pf->dbg->build_id) { + build_id__init(&bid, pf->dbg->build_id, BUILD_ID_SIZE); + build_id__sprintf(&bid, sbuild_id); + } + ret = find_source_path(pf->fname, sbuild_id, comp_dir, &fpath); if (ret < 0) { pr_warning("Failed to find source file path.\n"); return ret; @@ -1448,7 +1461,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, struct probe_trace_event **tevs) { struct trace_event_finder tf = { - .pf = {.pev = pev, .callback = add_probe_trace_event}, + .pf = {.pev = pev, .dbg = dbg, .callback = add_probe_trace_event}, .max_tevs = probe_conf.max_probes, .mod = dbg->mod}; int ret, i; @@ -1618,7 +1631,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg, struct variable_list **vls) { struct available_var_finder af = { - .pf = {.pev = pev, .callback = add_available_vars}, + .pf = {.pev = pev, .dbg = dbg, .callback = add_available_vars}, .mod = dbg->mod, .max_vls = probe_conf.max_probes}; int ret; @@ -1872,8 +1885,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - if (die_is_func_def(sp_die) && - die_match_name(sp_die, lr->function)) { + if (die_match_name(sp_die, lr->function) && die_is_func_def(sp_die)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset); @@ -1973,17 +1985,57 @@ found: return (ret < 0) ? ret : lf.found; } +#ifdef HAVE_DEBUGINFOD_SUPPORT +/* debuginfod doesn't require the comp_dir but buildid is required */ +static int get_source_from_debuginfod(const char *raw_path, + const char *sbuild_id, char **new_path) +{ + debuginfod_client *c = debuginfod_begin(); + const char *p = raw_path; + int fd; + + if (!c) + return -ENOMEM; + + fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id, + 0, p, new_path); + pr_debug("Search %s from debuginfod -> %d\n", p, fd); + if (fd >= 0) + close(fd); + debuginfod_end(c); + if (fd < 0) { + pr_debug("Failed to find %s in debuginfod (%s)\n", + raw_path, sbuild_id); + return -ENOENT; + } + pr_debug("Got a source %s\n", *new_path); + + return 0; +} +#else +static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused, + const char *sbuild_id __maybe_unused, + char **new_path __maybe_unused) +{ + return -ENOTSUP; +} +#endif /* * Find a src file from a DWARF tag path. Prepend optional source path prefix * and chop off leading directories that do not exist. Result is passed back as * a newly allocated path on success. * Return 0 if file was found and readable, -errno otherwise. */ -int get_real_path(const char *raw_path, const char *comp_dir, - char **new_path) +int find_source_path(const char *raw_path, const char *sbuild_id, + const char *comp_dir, char **new_path) { const char *prefix = symbol_conf.source_prefix; + if (sbuild_id && !prefix) { + if (!get_source_from_debuginfod(raw_path, sbuild_id, new_path)) + return 0; + } + if (!prefix) { if (raw_path[0] != '/' && comp_dir) /* If not an absolute path, try to use comp_dir */ diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 11be100806136..2febb58756789 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -4,6 +4,7 @@ #include <stdbool.h> #include "intlist.h" +#include "build-id.h" #include "probe-event.h" #include <linux/ctype.h> @@ -32,6 +33,7 @@ struct debuginfo { Dwfl_Module *mod; Dwfl *dwfl; Dwarf_Addr bias; + const unsigned char *build_id; }; /* This also tries to open distro debuginfo */ @@ -59,11 +61,12 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg, struct variable_list **vls); /* Find a src file from a DWARF tag path */ -int get_real_path(const char *raw_path, const char *comp_dir, - char **new_path); +int find_source_path(const char *raw_path, const char *sbuild_id, + const char *comp_dir, char **new_path); struct probe_finder { struct perf_probe_event *pev; /* Target probe event */ + struct debuginfo *dbg; /* Callback when a probe point is found */ int (*callback)(Dwarf_Die *sc_die, struct probe_finder *pf); diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 75a9b1d62bba7..cc5ade85a33fc 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -15,9 +15,11 @@ #include "thread_map.h" #include "trace-event.h" #include "mmap.h" +#include "stat.h" +#include "metricgroup.h" #include "util/env.h" #include <internal/lib.h> -#include "../perf-sys.h" +#include "util.h" #if PY_MAJOR_VERSION < 3 #define _PyUnicode_FromString(arg) \ @@ -61,6 +63,23 @@ int parse_callchain_record(const char *arg __maybe_unused, struct perf_env perf_env; /* + * Add this one here not to drag util/stat-shadow.c + */ +void perf_stat__collect_metric_expr(struct evlist *evsel_list) +{ +} + +/* + * Add this one here not to drag util/metricgroup.c + */ +int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, + struct rblist *new_metric_events, + struct rblist *old_metric_events) +{ + return 0; +} + +/* * Support debug printing even though util/debug.c is not linked. That means * implementing 'verbose' and 'eprintf'. */ @@ -1036,7 +1055,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, if (pyevent == NULL) return PyErr_NoMemory(); - evsel = perf_evlist__event2evsel(evlist, event); + evsel = evlist__event2evsel(evlist, event); if (!evsel) { Py_INCREF(Py_None); return Py_None; @@ -1070,7 +1089,7 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, return NULL; if (group) - perf_evlist__set_leader(evlist); + evlist__set_leader(evlist); if (evlist__open(evlist) < 0) { PyErr_SetFromErrno(PyExc_OSError); diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index ea9aa1d7cf501..e70c9dd04567b 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -14,6 +14,7 @@ #include "util/perf_api_probe.h" #include "record.h" #include "../perf-sys.h" +#include "topdown.h" /* * evsel__config_leader_sampling() uses special rules for leader sampling. @@ -24,7 +25,7 @@ static struct evsel *evsel__read_sampler(struct evsel *evsel, struct evlist *evl { struct evsel *leader = evsel->leader; - if (evsel__is_aux_event(leader)) { + if (evsel__is_aux_event(leader) || arch_topdown_sample_read(leader)) { evlist__for_each_entry(evlist, evsel) { if (evsel->leader == leader && evsel != evsel->leader) return evsel; @@ -88,8 +89,7 @@ static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *ev leader->core.attr.sample_type; } -void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, - struct callchain_param *callchain) +void evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain) { struct evsel *evsel; bool use_sample_identifier = false; @@ -101,7 +101,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, * since some might depend on this info. */ if (opts->group) - perf_evlist__set_leader(evlist); + evlist__set_leader(evlist); if (evlist->core.cpus->map[0] < 0) opts->no_inherit = true; @@ -143,7 +143,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, evsel__set_sample_id(evsel, use_sample_identifier); } - perf_evlist__set_id_pos(evlist); + evlist__set_id_pos(evlist); } static int get_max_rate(unsigned int *rate) @@ -216,7 +216,7 @@ int record_opts__config(struct record_opts *opts) return record_opts__config_freq(opts); } -bool perf_evlist__can_select_event(struct evlist *evlist, const char *str) +bool evlist__can_select_event(struct evlist *evlist, const char *str) { struct evlist *temp_evlist; struct evsel *evsel; diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 03678ff255391..694b351dcd278 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -22,6 +22,7 @@ struct record_opts { bool raw_samples; bool sample_address; bool sample_phys_addr; + bool sample_data_page_size; bool sample_weight; bool sample_time; bool sample_time_set; @@ -73,6 +74,7 @@ struct record_opts { unsigned int nr_threads_synthesize; int ctl_fd; int ctl_fd_ack; + bool ctl_fd_close; }; extern const char * const *record_usage; diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index f8861998e5bd2..078a717735654 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -96,9 +96,9 @@ * | than PERF_RECORD_USER_TYPE_START) are handled by * | perf_session__process_user_event(see below) * | - Those generated by the kernel are handled by - * | perf_evlist__parse_sample_timestamp() + * | evlist__parse_sample_timestamp() * | - * perf_evlist__parse_sample_timestamp() + * evlist__parse_sample_timestamp() * | Extract time stamp from sample data. * | * perf_session__queue_event() @@ -932,7 +932,7 @@ s390_cpumsf_process_event(struct perf_session *session, if (event->header.type == PERF_RECORD_SAMPLE && sample->raw_size) { /* Handle event with raw data */ - ev_bc000 = perf_evlist__event2evsel(session->evlist, event); + ev_bc000 = evlist__event2evsel(session->evlist, event); if (ev_bc000 && ev_bc000->core.attr.config == PERF_EVENT_CPUM_CF_DIAG) err = s390_cpumcf_dumpctr(sf, sample); diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index 05b43ab4eeefc..cfcf8d534d767 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -197,15 +197,14 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample) * its raw data. * The function is only invoked when the dump flag -D is set. */ -void perf_evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, - struct perf_sample *sample) +void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { struct evsel *ev_bc000; if (event->header.type != PERF_RECORD_SAMPLE) return; - ev_bc000 = perf_evlist__event2evsel(evlist, event); + ev_bc000 = evlist__event2evsel(evlist, event); if (ev_bc000 == NULL || ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG) return; diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c index e84bbe0e441a0..cde5cd3ce49bf 100644 --- a/tools/perf/util/sample-raw.c +++ b/tools/perf/util/sample-raw.c @@ -9,10 +9,10 @@ * Check platform the perf data file was created on and perform platform * specific interpretation. */ -void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist) +void evlist__init_trace_event_sample_raw(struct evlist *evlist) { const char *arch_pf = perf_env__arch(evlist->env); if (arch_pf && !strcmp("s390", arch_pf)) - evlist->trace_event_sample_raw = perf_evlist__s390_sample_raw; + evlist->trace_event_sample_raw = evlist__s390_sample_raw; } diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h index afe1491a117e7..4be84a5510cf0 100644 --- a/tools/perf/util/sample-raw.h +++ b/tools/perf/util/sample-raw.h @@ -6,9 +6,6 @@ struct evlist; union perf_event; struct perf_sample; -void perf_evlist__s390_sample_raw(struct evlist *evlist, - union perf_event *event, - struct perf_sample *sample); - -void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist); +void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); +void evlist__init_trace_event_sample_raw(struct evlist *evlist); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 739516fdf6e38..c83c2c6564e01 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -1064,7 +1064,7 @@ static int python_export_dso(struct db_export *dbe, struct dso *dso, char sbuild_id[SBUILD_ID_SIZE]; PyObject *t; - build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + build_id__sprintf(&dso->bid, sbuild_id); t = tuple_new(5); @@ -1592,7 +1592,6 @@ static void _free_command_line(wchar_t **command_line, int num) static int python_start_script(const char *script, int argc, const char **argv) { struct tables *tables = &tables_global; - PyMODINIT_FUNC (*initfunc)(void); #if PY_MAJOR_VERSION < 3 const char **command_line; #else @@ -1607,20 +1606,18 @@ static int python_start_script(const char *script, int argc, const char **argv) FILE *fp; #if PY_MAJOR_VERSION < 3 - initfunc = initperf_trace_context; command_line = malloc((argc + 1) * sizeof(const char *)); command_line[0] = script; for (i = 1; i < argc + 1; i++) command_line[i] = argv[i - 1]; + PyImport_AppendInittab(name, initperf_trace_context); #else - initfunc = PyInit_perf_trace_context; command_line = malloc((argc + 1) * sizeof(wchar_t *)); command_line[0] = Py_DecodeLocale(script, NULL); for (i = 1; i < argc + 1; i++) command_line[i] = Py_DecodeLocale(argv[i - 1], NULL); + PyImport_AppendInittab(name, PyInit_perf_trace_context); #endif - - PyImport_AppendInittab(name, initfunc); Py_Initialize(); #if PY_MAJOR_VERSION < 3 diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 7a5f03764702b..25adbcce02814 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -32,6 +32,7 @@ #include "ui/progress.h" #include "../perf.h" #include "arch/common.h" +#include "units.h" #include <internal/lib.h> #ifdef HAVE_ZSTD_SUPPORT @@ -125,7 +126,7 @@ static int perf_session__open(struct perf_session *session) return -1; } - if (!perf_evlist__valid_read_format(session->evlist)) { + if (!evlist__valid_read_format(session->evlist)) { pr_err("non matching read_format\n"); return -1; } @@ -135,7 +136,7 @@ static int perf_session__open(struct perf_session *session) void perf_session__set_id_hdr_size(struct perf_session *session) { - u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist); + u16 id_hdr_size = evlist__id_hdr_size(session->evlist); machines__set_id_hdr_size(&session->machines, id_hdr_size); } @@ -221,7 +222,7 @@ struct perf_session *perf_session__new(struct perf_data *data, perf_session__set_comm_exec(session); } - perf_evlist__init_trace_event_sample_raw(session->evlist); + evlist__init_trace_event_sample_raw(session->evlist); /* Open the directory data. */ if (data->is_dir) { @@ -595,6 +596,7 @@ static void perf_event__mmap2_swap(union perf_event *event, event->mmap2.maj = bswap_32(event->mmap2.maj); event->mmap2.min = bswap_32(event->mmap2.min); event->mmap2.ino = bswap_64(event->mmap2.ino); + event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation); if (sample_id_all) { void *data = &event->mmap2.filename; @@ -710,6 +712,18 @@ static void perf_event__namespaces_swap(union perf_event *event, swap_sample_id_all(event, &event->namespaces.link_info[i]); } +static void perf_event__cgroup_swap(union perf_event *event, bool sample_id_all) +{ + event->cgroup.id = bswap_64(event->cgroup.id); + + if (sample_id_all) { + void *data = &event->cgroup.path; + + data += PERF_ALIGN(strlen(data) + 1, sizeof(u64)); + swap_sample_id_all(event, data); + } +} + static u8 revbyte(u8 b) { int rev = (b >> 4) | ((b & 0xf) << 4); @@ -952,6 +966,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_SWITCH] = perf_event__switch_swap, [PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap, [PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap, + [PERF_RECORD_CGROUP] = perf_event__cgroup_swap, [PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, @@ -1177,9 +1192,7 @@ static void stack_user__printf(struct stack_dump *dump) dump->size, dump->offset); } -static void perf_evlist__print_tstamp(struct evlist *evlist, - union perf_event *event, - struct perf_sample *sample) +static void evlist__print_tstamp(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { u64 sample_type = __evlist__combined_sample_type(evlist); @@ -1240,16 +1253,25 @@ static void dump_event(struct evlist *evlist, union perf_event *event, evlist->trace_event_sample_raw(evlist, event, sample); if (sample) - perf_evlist__print_tstamp(evlist, event, sample); + evlist__print_tstamp(evlist, event, sample); printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset, event->header.size, perf_event__name(event->header.type)); } +char *get_page_size_name(u64 size, char *str) +{ + if (!size || !unit_number__scnprintf(str, PAGE_SIZE_NAME_LEN, size)) + snprintf(str, PAGE_SIZE_NAME_LEN, "%s", "N/A"); + + return str; +} + static void dump_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *sample) { u64 sample_type; + char str[PAGE_SIZE_NAME_LEN]; if (!dump_trace) return; @@ -1284,6 +1306,9 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_PHYS_ADDR) printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr); + if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE) + printf(" .. data page size: %s\n", get_page_size_name(sample->data_page_size, str)); + if (sample_type & PERF_SAMPLE_TRANSACTION) printf("... transaction: %" PRIx64 "\n", sample->transaction); @@ -1350,7 +1375,7 @@ static int deliver_sample_value(struct evlist *evlist, struct sample_read_value *v, struct machine *machine) { - struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id); + struct perf_sample_id *sid = evlist__id2sid(evlist, v->id); struct evsel *evsel; if (sid) { @@ -1395,13 +1420,9 @@ static int deliver_sample_group(struct evlist *evlist, return ret; } -static int - perf_evlist__deliver_sample(struct evlist *evlist, - struct perf_tool *tool, - union perf_event *event, - struct perf_sample *sample, - struct evsel *evsel, - struct machine *machine) +static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool, + union perf_event *event, struct perf_sample *sample, + struct evsel *evsel, struct machine *machine) { /* We know evsel != NULL. */ u64 sample_type = evsel->core.attr.sample_type; @@ -1431,7 +1452,7 @@ static int machines__deliver_event(struct machines *machines, dump_event(evlist, event, file_offset, sample); - evsel = perf_evlist__id2evsel(evlist, sample->id); + evsel = evlist__id2evsel(evlist, sample->id); machine = machines__find_for_cpumode(machines, event, sample); @@ -1446,7 +1467,7 @@ static int machines__deliver_event(struct machines *machines, ++evlist->stats.nr_unprocessable_samples; return 0; } - return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); + return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); case PERF_RECORD_MMAP2: @@ -1509,9 +1530,8 @@ static int perf_session__deliver_event(struct perf_session *session, u64 file_offset) { struct perf_sample sample; - int ret; + int ret = evlist__parse_sample(session->evlist, event, &sample); - ret = perf_evlist__parse_sample(session->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); return ret; @@ -1683,7 +1703,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, out_parse_sample: if (sample && event->header.type < PERF_RECORD_USER_TYPE_START && - perf_evlist__parse_sample(session->evlist, event, sample)) + evlist__parse_sample(session->evlist, event, sample)) return -1; *event_ptr = event; @@ -1740,7 +1760,7 @@ static s64 perf_session__process_event(struct perf_session *session, if (tool->ordered_events) { u64 timestamp = -1ULL; - ret = perf_evlist__parse_sample_timestamp(evlist, event, ×tamp); + ret = evlist__parse_sample_timestamp(evlist, event, ×tamp); if (ret && ret != -1) return ret; @@ -1923,7 +1943,6 @@ static int __perf_session__process_pipe_events(struct perf_session *session) { struct ordered_events *oe = &session->ordered_events; struct perf_tool *tool = session->tool; - int fd = perf_data__fd(session->data); union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; @@ -1943,7 +1962,8 @@ static int __perf_session__process_pipe_events(struct perf_session *session) ordered_events__set_copy_on_queue(oe, true); more: event = buf; - err = readn(fd, event, sizeof(struct perf_event_header)); + err = perf_data__read(session->data, event, + sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) goto done; @@ -1975,7 +1995,8 @@ more: p += sizeof(struct perf_event_header); if (size - sizeof(struct perf_event_header)) { - err = readn(fd, p, size - sizeof(struct perf_event_header)); + err = perf_data__read(session->data, p, + size - sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) { pr_err("unexpected end of event stream\n"); @@ -2383,7 +2404,7 @@ int perf_session__cpu_bitmap(struct perf_session *session, { int i, err = -1; struct perf_cpu_map *map; - int nr_cpus = min(session->header.env.nr_cpus_online, MAX_NR_CPUS); + int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS); for (i = 0; i < PERF_TYPE_MAX; ++i) { struct evsel *evsel; @@ -2462,7 +2483,7 @@ int perf_event__process_id_index(struct perf_session *session, fprintf(stdout, " tid: %"PRI_ld64"\n", e->tid); } - sid = perf_evlist__id2sid(evlist, e->id); + sid = evlist__id2sid(evlist, e->id); if (!sid) return -ENOENT; sid->idx = e->idx; diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c index ded9ced027973..748371ac22bec 100644 --- a/tools/perf/util/sideband_evlist.c +++ b/tools/perf/util/sideband_evlist.c @@ -12,8 +12,8 @@ #include <sched.h> #include <stdbool.h> -int perf_evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, - evsel__sb_cb_t cb, void *data) +int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, + evsel__sb_cb_t cb, void *data) { struct evsel *evsel; @@ -62,7 +62,7 @@ static void *perf_evlist__poll_thread(void *arg) if (perf_mmap__read_init(&map->core)) continue; while ((event = perf_mmap__read_event(&map->core)) != NULL) { - struct evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = evlist__event2evsel(evlist, event); if (evsel && evsel->side_band.cb) evsel->side_band.cb(event, evsel->side_band.data); @@ -94,14 +94,14 @@ void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data) } } -int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target) +int evlist__start_sb_thread(struct evlist *evlist, struct target *target) { struct evsel *counter; if (!evlist) return 0; - if (perf_evlist__create_maps(evlist, target)) + if (evlist__create_maps(evlist, target)) goto out_delete_evlist; if (evlist->core.nr_entries > 1) { @@ -110,7 +110,7 @@ int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target) evlist__for_each_entry(evlist, counter) evsel__set_sample_id(counter, can_sample_identifier); - perf_evlist__set_id_pos(evlist); + evlist__set_id_pos(evlist); } evlist__for_each_entry(evlist, counter) { @@ -138,7 +138,7 @@ out_delete_evlist: return -1; } -void perf_evlist__stop_sb_thread(struct evlist *evlist) +void evlist__stop_sb_thread(struct evlist *evlist) { if (!evlist) return; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index d42339df20f8d..80907bc32683a 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1463,6 +1463,35 @@ struct sort_entry sort_mem_phys_daddr = { }; static int64_t +sort__data_page_size_cmp(struct hist_entry *left, struct hist_entry *right) +{ + uint64_t l = 0, r = 0; + + if (left->mem_info) + l = left->mem_info->daddr.data_page_size; + if (right->mem_info) + r = right->mem_info->daddr.data_page_size; + + return (int64_t)(r - l); +} + +static int hist_entry__data_page_size_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + char str[PAGE_SIZE_NAME_LEN]; + + return repsep_snprintf(bf, size, "%-*s", width, + get_page_size_name(he->mem_info->daddr.data_page_size, str)); +} + +struct sort_entry sort_mem_data_page_size = { + .se_header = "Data Page Size", + .se_cmp = sort__data_page_size_cmp, + .se_snprintf = hist_entry__data_page_size_snprintf, + .se_width_idx = HISTC_MEM_DATA_PAGE_SIZE, +}; + +static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { if (!left->branch_info || !right->branch_info) @@ -1740,6 +1769,7 @@ static struct sort_dimension memory_sort_dimensions[] = { DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline), DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr), + DIM(SORT_MEM_DATA_PAGE_SIZE, "data_page_size", sort_mem_data_page_size), }; #undef DIM @@ -2756,7 +2786,7 @@ static const char *get_default_sort_order(struct evlist *evlist) BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); - if (evlist == NULL || perf_evlist__empty(evlist)) + if (evlist == NULL || evlist__empty(evlist)) goto out_no_evlist; evlist__for_each_entry(evlist, evsel) { diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 66d39c4cfe2b3..e50f2b695bc43 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -255,6 +255,7 @@ enum sort_type { SORT_MEM_DCACHELINE, SORT_MEM_IADDR_SYMBOL, SORT_MEM_PHYS_DADDR, + SORT_MEM_DATA_PAGE_SIZE, }; /* diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 493ec372fdec4..583ae4f09c5d1 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -68,15 +68,15 @@ static void print_cgroup(struct perf_stat_config *config, struct evsel *evsel) static void aggr_printout(struct perf_stat_config *config, - struct evsel *evsel, int id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int nr) { switch (config->aggr_mode) { case AGGR_CORE: fprintf(config->output, "S%d-D%d-C%*d%s%*d%s", - cpu_map__id_to_socket(id), - cpu_map__id_to_die(id), + id.socket, + id.die, config->csv_output ? 0 : -8, - cpu_map__id_to_cpu(id), + id.core, config->csv_sep, config->csv_output ? 0 : 4, nr, @@ -84,9 +84,9 @@ static void aggr_printout(struct perf_stat_config *config, break; case AGGR_DIE: fprintf(config->output, "S%d-D%*d%s%*d%s", - cpu_map__id_to_socket(id << 16), + id.socket, config->csv_output ? 0 : -8, - cpu_map__id_to_die(id << 16), + id.die, config->csv_sep, config->csv_output ? 0 : 4, nr, @@ -95,7 +95,7 @@ static void aggr_printout(struct perf_stat_config *config, case AGGR_SOCKET: fprintf(config->output, "S%*d%s%*d%s", config->csv_output ? 0 : -5, - id, + id.socket, config->csv_sep, config->csv_output ? 0 : 4, nr, @@ -104,7 +104,7 @@ static void aggr_printout(struct perf_stat_config *config, case AGGR_NODE: fprintf(config->output, "N%*d%s%*d%s", config->csv_output ? 0 : -5, - id, + id.node, config->csv_sep, config->csv_output ? 0 : 4, nr, @@ -113,23 +113,23 @@ static void aggr_printout(struct perf_stat_config *config, case AGGR_NONE: if (evsel->percore && !config->percore_show_thread) { fprintf(config->output, "S%d-D%d-C%*d%s", - cpu_map__id_to_socket(id), - cpu_map__id_to_die(id), + id.socket, + id.die, config->csv_output ? 0 : -3, - cpu_map__id_to_cpu(id), config->csv_sep); - } else if (id > -1) { + id.core, config->csv_sep); + } else if (id.core > -1) { fprintf(config->output, "CPU%*d%s", config->csv_output ? 0 : -7, - evsel__cpus(evsel)->map[id], + evsel__cpus(evsel)->map[id.core], config->csv_sep); } break; case AGGR_THREAD: fprintf(config->output, "%*s-%*d%s", config->csv_output ? 0 : 16, - perf_thread_map__comm(evsel->core.threads, id), + perf_thread_map__comm(evsel->core.threads, id.thread), config->csv_output ? 0 : -8, - perf_thread_map__pid(evsel->core.threads, id), + perf_thread_map__pid(evsel->core.threads, id.thread), config->csv_sep); break; case AGGR_GLOBAL: @@ -144,7 +144,8 @@ struct outstate { bool newline; const char *prefix; int nfields; - int id, nr; + int nr; + struct aggr_cpu_id id; struct evsel *evsel; }; @@ -319,31 +320,31 @@ static void print_metric_header(struct perf_stat_config *config, } static int first_shadow_cpu(struct perf_stat_config *config, - struct evsel *evsel, int id) + struct evsel *evsel, struct aggr_cpu_id id) { struct evlist *evlist = evsel->evlist; int i; - if (!config->aggr_get_id) - return 0; - if (config->aggr_mode == AGGR_NONE) - return id; + return id.core; - if (config->aggr_mode == AGGR_GLOBAL) + if (!config->aggr_get_id) return 0; for (i = 0; i < evsel__nr_cpus(evsel); i++) { int cpu2 = evsel__cpus(evsel)->map[i]; - if (config->aggr_get_id(config, evlist->core.cpus, cpu2) == id) + if (cpu_map__compare_aggr_cpu_id( + config->aggr_get_id(config, evlist->core.cpus, cpu2), + id)) { return cpu2; + } } return 0; } static void abs_printout(struct perf_stat_config *config, - int id, int nr, struct evsel *evsel, double avg) + struct aggr_cpu_id id, int nr, struct evsel *evsel, double avg) { FILE *output = config->output; double sc = evsel->scale; @@ -396,7 +397,7 @@ static bool is_mixed_hw_group(struct evsel *counter) return false; } -static void printout(struct perf_stat_config *config, int id, int nr, +static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int nr, struct evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise, struct runtime_stat *st) @@ -499,7 +500,8 @@ static void printout(struct perf_stat_config *config, int id, int nr, static void aggr_update_shadow(struct perf_stat_config *config, struct evlist *evlist) { - int cpu, s2, id, s; + int cpu, s; + struct aggr_cpu_id s2, id; u64 val; struct evsel *counter; @@ -509,7 +511,7 @@ static void aggr_update_shadow(struct perf_stat_config *config, val = 0; for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { s2 = config->aggr_get_id(config, evlist->core.cpus, cpu); - if (s2 != id) + if (!cpu_map__compare_aggr_cpu_id(s2, id)) continue; val += perf_counts(counter->counts, cpu, 0)->val; } @@ -587,7 +589,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter, struct aggr_data { u64 ena, run, val; - int id; + struct aggr_cpu_id id; int nr; int cpu; }; @@ -596,13 +598,14 @@ static void aggr_cb(struct perf_stat_config *config, struct evsel *counter, void *data, bool first) { struct aggr_data *ad = data; - int cpu, s2; + int cpu; + struct aggr_cpu_id s2; for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { struct perf_counts_values *counts; s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu); - if (s2 != ad->id) + if (!cpu_map__compare_aggr_cpu_id(s2, ad->id)) continue; if (first) ad->nr++; @@ -631,7 +634,8 @@ static void print_counter_aggrdata(struct perf_stat_config *config, struct aggr_data ad; FILE *output = config->output; u64 ena, run, val; - int id, nr; + int nr; + struct aggr_cpu_id id; double uval; ad.id = id = config->aggr_map->map[s]; @@ -652,8 +656,12 @@ static void print_counter_aggrdata(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = val * counter->scale; - printout(config, cpu != -1 ? cpu : id, nr, counter, uval, prefix, - run, ena, 1.0, &rt_stat); + if (cpu != -1) { + id = cpu_map__empty_aggr_cpu_id(); + id.core = cpu; + } + printout(config, id, nr, counter, uval, + prefix, run, ena, 1.0, &rt_stat); if (!metric_only) fputc('\n', output); } @@ -731,7 +739,8 @@ static struct perf_aggr_thread_value *sort_aggr_thread( continue; buf[i].counter = counter; - buf[i].id = thread; + buf[i].id = cpu_map__empty_aggr_cpu_id(); + buf[i].id.thread = thread; buf[i].uval = uval; buf[i].val = val; buf[i].run = run; @@ -754,7 +763,8 @@ static void print_aggr_thread(struct perf_stat_config *config, FILE *output = config->output; int nthreads = perf_thread_map__nr(counter->core.threads); int ncpus = perf_cpu_map__nr(counter->core.cpus); - int thread, sorted_threads, id; + int thread, sorted_threads; + struct aggr_cpu_id id; struct perf_aggr_thread_value *buf; buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target); @@ -771,7 +781,7 @@ static void print_aggr_thread(struct perf_stat_config *config, if (config->stats) printout(config, id, 0, buf[thread].counter, buf[thread].uval, prefix, buf[thread].run, buf[thread].ena, 1.0, - &config->stats[id]); + &config->stats[id.thread]); else printout(config, id, 0, buf[thread].counter, buf[thread].uval, prefix, buf[thread].run, buf[thread].ena, 1.0, @@ -817,8 +827,8 @@ static void print_counter_aggr(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = cd.avg * counter->scale; - printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, - cd.avg, &rt_stat); + printout(config, cpu_map__empty_aggr_cpu_id(), 0, counter, uval, prefix, cd.avg_running, + cd.avg_enabled, cd.avg, &rt_stat); if (!metric_only) fprintf(output, "\n"); } @@ -845,6 +855,7 @@ static void print_counter(struct perf_stat_config *config, u64 ena, run, val; double uval; int cpu; + struct aggr_cpu_id id; for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { struct aggr_data ad = { .cpu = cpu }; @@ -859,8 +870,10 @@ static void print_counter(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = val * counter->scale; - printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0, - &rt_stat); + id = cpu_map__empty_aggr_cpu_id(); + id.core = cpu; + printout(config, id, 0, counter, uval, prefix, + run, ena, 1.0, &rt_stat); fputc('\n', output); } @@ -875,6 +888,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config, struct evsel *counter; u64 ena, run, val; double uval; + struct aggr_cpu_id id; nrcpus = evlist->core.cpus->nr; for (cpu = 0; cpu < nrcpus; cpu++) { @@ -883,8 +897,10 @@ static void print_no_aggr_metric(struct perf_stat_config *config, if (prefix) fputs(prefix, config->output); evlist__for_each_entry(evlist, counter) { + id = cpu_map__empty_aggr_cpu_id(); + id.core = cpu; if (first) { - aggr_printout(config, counter, cpu, 0); + aggr_printout(config, counter, id, 0); first = false; } val = perf_counts(counter->counts, cpu, 0)->val; @@ -892,8 +908,8 @@ static void print_no_aggr_metric(struct perf_stat_config *config, run = perf_counts(counter->counts, cpu, 0)->run; uval = val * counter->scale; - printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0, - &rt_stat); + printout(config, id, 0, counter, uval, prefix, + run, ena, 1.0, &rt_stat); } fputc('\n', config->output); } @@ -946,7 +962,6 @@ static void print_metric_headers(struct perf_stat_config *config, out.print_metric = print_metric_header; out.new_line = new_line_metric; out.force_header = true; - os.evsel = counter; perf_stat__print_shadow_stats(config, counter, 0, 0, &out, @@ -1144,14 +1159,15 @@ static void print_footer(struct perf_stat_config *config) static void print_percore_thread(struct perf_stat_config *config, struct evsel *counter, char *prefix) { - int s, s2, id; + int s; + struct aggr_cpu_id s2, id; bool first = true; for (int i = 0; i < evsel__nr_cpus(counter); i++) { s2 = config->aggr_get_id(config, evsel__cpus(counter), i); for (s = 0; s < config->aggr_map->nr; s++) { id = config->aggr_map->map[s]; - if (s2 == id) + if (cpu_map__compare_aggr_cpu_id(s2, id)) break; } @@ -1188,12 +1204,8 @@ static void print_percore(struct perf_stat_config *config, fputc('\n', output); } -void -perf_evlist__print_counters(struct evlist *evlist, - struct perf_stat_config *config, - struct target *_target, - struct timespec *ts, - int argc, const char **argv) +void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, + struct target *_target, struct timespec *ts, int argc, const char **argv) { bool metric_only = config->metric_only; int interval = config->interval; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 924b54d15d540..12eafd12a693c 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -8,6 +8,7 @@ #include "evlist.h" #include "expr.h" #include "metricgroup.h" +#include "cgroup.h" #include <linux/zalloc.h> /* @@ -28,6 +29,7 @@ struct saved_value { enum stat_type type; int ctx; int cpu; + struct cgroup *cgrp; struct runtime_stat *stat; struct stats stats; u64 metric_total; @@ -57,6 +59,9 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry) if (a->ctx != b->ctx) return a->ctx - b->ctx; + if (a->cgrp != b->cgrp) + return (char *)a->cgrp < (char *)b->cgrp ? -1 : +1; + if (a->evsel == NULL && b->evsel == NULL) { if (a->stat == b->stat) return 0; @@ -100,7 +105,8 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, bool create, enum stat_type type, int ctx, - struct runtime_stat *st) + struct runtime_stat *st, + struct cgroup *cgrp) { struct rblist *rblist; struct rb_node *nd; @@ -110,10 +116,15 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, .type = type, .ctx = ctx, .stat = st, + .cgrp = cgrp, }; rblist = &st->value_list; + /* don't use context info for clock events */ + if (type == STAT_NSECS) + dm.ctx = 0; + nd = rblist__find(rblist, &dm); if (nd) return container_of(nd, struct saved_value, rb_node); @@ -191,12 +202,18 @@ void perf_stat__reset_shadow_per_stat(struct runtime_stat *st) reset_stat(st); } +struct runtime_stat_data { + int ctx; + struct cgroup *cgrp; +}; + static void update_runtime_stat(struct runtime_stat *st, enum stat_type type, - int ctx, int cpu, u64 count) + int cpu, u64 count, + struct runtime_stat_data *rsd) { - struct saved_value *v = saved_value_lookup(NULL, cpu, true, - type, ctx, st); + struct saved_value *v = saved_value_lookup(NULL, cpu, true, type, + rsd->ctx, st, rsd->cgrp); if (v) update_stats(&v->stats, count); @@ -210,70 +227,86 @@ static void update_runtime_stat(struct runtime_stat *st, void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int cpu, struct runtime_stat *st) { - int ctx = evsel_context(counter); u64 count_ns = count; struct saved_value *v; + struct runtime_stat_data rsd = { + .ctx = evsel_context(counter), + .cgrp = counter->cgrp, + }; count *= counter->scale; if (evsel__is_clock(counter)) - update_runtime_stat(st, STAT_NSECS, 0, cpu, count_ns); + update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd); else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count); + update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd); else if (perf_stat_evsel__is(counter, CYCLES_IN_TX)) - update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count); + update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd); else if (perf_stat_evsel__is(counter, TRANSACTION_START)) - update_runtime_stat(st, STAT_TRANSACTION, ctx, cpu, count); + update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd); else if (perf_stat_evsel__is(counter, ELISION_START)) - update_runtime_stat(st, STAT_ELISION, ctx, cpu, count); + update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS)) update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS, - ctx, cpu, count); + cpu, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED)) update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED, - ctx, cpu, count); + cpu, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED)) update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED, - ctx, cpu, count); + cpu, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES)) update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES, - ctx, cpu, count); + cpu, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES)) update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES, - ctx, cpu, count); + cpu, count, &rsd); + else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING)) + update_runtime_stat(st, STAT_TOPDOWN_RETIRING, + cpu, count, &rsd); + else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC)) + update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC, + cpu, count, &rsd); + else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND)) + update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND, + cpu, count, &rsd); + else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND)) + update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND, + cpu, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT, - ctx, cpu, count); + cpu, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_BACK, - ctx, cpu, count); + cpu, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count); + update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count); + update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count); + update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count); + update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count); + update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count); + update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count); + update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd); else if (perf_stat_evsel__is(counter, SMI_NUM)) - update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count); + update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd); else if (perf_stat_evsel__is(counter, APERF)) - update_runtime_stat(st, STAT_APERF, ctx, cpu, count); + update_runtime_stat(st, STAT_APERF, cpu, count, &rsd); if (counter->collect_stat) { - v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st); + v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st, + rsd.cgrp); update_stats(&v->stats, count); if (counter->metric_leader) v->metric_total += count; } else if (counter->metric_leader) { v = saved_value_lookup(counter->metric_leader, - cpu, true, STAT_NONE, 0, st); + cpu, true, STAT_NONE, 0, st, rsd.cgrp); v->metric_total += count; v->metric_other++; } @@ -410,11 +443,12 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) } static double runtime_stat_avg(struct runtime_stat *st, - enum stat_type type, int ctx, int cpu) + enum stat_type type, int cpu, + struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, cpu, false, type, ctx, st); + v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp); if (!v) return 0.0; @@ -422,11 +456,12 @@ static double runtime_stat_avg(struct runtime_stat *st, } static double runtime_stat_n(struct runtime_stat *st, - enum stat_type type, int ctx, int cpu) + enum stat_type type, int cpu, + struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, cpu, false, type, ctx, st); + v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp); if (!v) return 0.0; @@ -434,16 +469,15 @@ static double runtime_stat_n(struct runtime_stat *st, } static void print_stalled_cycles_frontend(struct perf_stat_config *config, - int cpu, - struct evsel *evsel, double avg, + int cpu, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st) + struct runtime_stat *st, + struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - int ctx = evsel_context(evsel); - total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu); + total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd); if (total) ratio = avg / total * 100.0; @@ -458,16 +492,15 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, } static void print_stalled_cycles_backend(struct perf_stat_config *config, - int cpu, - struct evsel *evsel, double avg, + int cpu, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st) + struct runtime_stat *st, + struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - int ctx = evsel_context(evsel); - total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu); + total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd); if (total) ratio = avg / total * 100.0; @@ -478,17 +511,15 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, } static void print_branch_misses(struct perf_stat_config *config, - int cpu, - struct evsel *evsel, - double avg, + int cpu, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st) + struct runtime_stat *st, + struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - int ctx = evsel_context(evsel); - total = runtime_stat_avg(st, STAT_BRANCHES, ctx, cpu); + total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd); if (total) ratio = avg / total * 100.0; @@ -499,18 +530,15 @@ static void print_branch_misses(struct perf_stat_config *config, } static void print_l1_dcache_misses(struct perf_stat_config *config, - int cpu, - struct evsel *evsel, - double avg, + int cpu, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st) - + struct runtime_stat *st, + struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - int ctx = evsel_context(evsel); - total = runtime_stat_avg(st, STAT_L1_DCACHE, ctx, cpu); + total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd); if (total) ratio = avg / total * 100.0; @@ -521,18 +549,15 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, } static void print_l1_icache_misses(struct perf_stat_config *config, - int cpu, - struct evsel *evsel, - double avg, + int cpu, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st) - + struct runtime_stat *st, + struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - int ctx = evsel_context(evsel); - total = runtime_stat_avg(st, STAT_L1_ICACHE, ctx, cpu); + total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd); if (total) ratio = avg / total * 100.0; @@ -542,17 +567,15 @@ static void print_l1_icache_misses(struct perf_stat_config *config, } static void print_dtlb_cache_misses(struct perf_stat_config *config, - int cpu, - struct evsel *evsel, - double avg, + int cpu, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st) + struct runtime_stat *st, + struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - int ctx = evsel_context(evsel); - total = runtime_stat_avg(st, STAT_DTLB_CACHE, ctx, cpu); + total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd); if (total) ratio = avg / total * 100.0; @@ -562,17 +585,15 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, } static void print_itlb_cache_misses(struct perf_stat_config *config, - int cpu, - struct evsel *evsel, - double avg, + int cpu, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st) + struct runtime_stat *st, + struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - int ctx = evsel_context(evsel); - total = runtime_stat_avg(st, STAT_ITLB_CACHE, ctx, cpu); + total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd); if (total) ratio = avg / total * 100.0; @@ -582,17 +603,15 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, } static void print_ll_cache_misses(struct perf_stat_config *config, - int cpu, - struct evsel *evsel, - double avg, + int cpu, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st) + struct runtime_stat *st, + struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - int ctx = evsel_context(evsel); - total = runtime_stat_avg(st, STAT_LL_CACHE, ctx, cpu); + total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd); if (total) ratio = avg / total * 100.0; @@ -650,73 +669,118 @@ static double sanitize_val(double x) return x; } -static double td_total_slots(int ctx, int cpu, struct runtime_stat *st) +static double td_total_slots(int cpu, struct runtime_stat *st, + struct runtime_stat_data *rsd) { - return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, ctx, cpu); + return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd); } -static double td_bad_spec(int ctx, int cpu, struct runtime_stat *st) +static double td_bad_spec(int cpu, struct runtime_stat *st, + struct runtime_stat_data *rsd) { double bad_spec = 0; double total_slots; double total; - total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) - - runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) + - runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu); + total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) - + runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) + + runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd); - total_slots = td_total_slots(ctx, cpu, st); + total_slots = td_total_slots(cpu, st, rsd); if (total_slots) bad_spec = total / total_slots; return sanitize_val(bad_spec); } -static double td_retiring(int ctx, int cpu, struct runtime_stat *st) +static double td_retiring(int cpu, struct runtime_stat *st, + struct runtime_stat_data *rsd) { double retiring = 0; - double total_slots = td_total_slots(ctx, cpu, st); + double total_slots = td_total_slots(cpu, st, rsd); double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, - ctx, cpu); + cpu, rsd); if (total_slots) retiring = ret_slots / total_slots; return retiring; } -static double td_fe_bound(int ctx, int cpu, struct runtime_stat *st) +static double td_fe_bound(int cpu, struct runtime_stat *st, + struct runtime_stat_data *rsd) { double fe_bound = 0; - double total_slots = td_total_slots(ctx, cpu, st); + double total_slots = td_total_slots(cpu, st, rsd); double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES, - ctx, cpu); + cpu, rsd); if (total_slots) fe_bound = fetch_bub / total_slots; return fe_bound; } -static double td_be_bound(int ctx, int cpu, struct runtime_stat *st) +static double td_be_bound(int cpu, struct runtime_stat *st, + struct runtime_stat_data *rsd) { - double sum = (td_fe_bound(ctx, cpu, st) + - td_bad_spec(ctx, cpu, st) + - td_retiring(ctx, cpu, st)); + double sum = (td_fe_bound(cpu, st, rsd) + + td_bad_spec(cpu, st, rsd) + + td_retiring(cpu, st, rsd)); if (sum == 0) return 0; return sanitize_val(1.0 - sum); } -static void print_smi_cost(struct perf_stat_config *config, - int cpu, struct evsel *evsel, +/* + * Kernel reports metrics multiplied with slots. To get back + * the ratios we need to recreate the sum. + */ + +static double td_metric_ratio(int cpu, enum stat_type type, + struct runtime_stat *stat, + struct runtime_stat_data *rsd) +{ + double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) + + runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) + + runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) + + runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd); + double d = runtime_stat_avg(stat, type, cpu, rsd); + + if (sum) + return d / sum; + return 0; +} + +/* + * ... but only if most of the values are actually available. + * We allow two missing. + */ + +static bool full_td(int cpu, struct runtime_stat *stat, + struct runtime_stat_data *rsd) +{ + int c = 0; + + if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0) + c++; + if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0) + c++; + if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0) + c++; + if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0) + c++; + return c >= 2; +} + +static void print_smi_cost(struct perf_stat_config *config, int cpu, struct perf_stat_output_ctx *out, - struct runtime_stat *st) + struct runtime_stat *st, + struct runtime_stat_data *rsd) { double smi_num, aperf, cycles, cost = 0.0; - int ctx = evsel_context(evsel); const char *color = NULL; - smi_num = runtime_stat_avg(st, STAT_SMI_NUM, ctx, cpu); - aperf = runtime_stat_avg(st, STAT_APERF, ctx, cpu); - cycles = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu); + smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd); + aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd); + cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd); if ((cycles == 0) || (aperf == 0)) return; @@ -751,7 +815,8 @@ static int prepare_metric(struct evsel **metric_events, scale = 1e-9; } else { v = saved_value_lookup(metric_events[i], cpu, false, - STAT_NONE, 0, st); + STAT_NONE, 0, st, + metric_events[i]->cgrp); if (!v) break; stats = &v->stats; @@ -877,12 +942,15 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric_t print_metric = out->print_metric; double total, ratio = 0.0, total2; const char *color = NULL; - int ctx = evsel_context(evsel); + struct runtime_stat_data rsd = { + .ctx = evsel_context(evsel), + .cgrp = evsel->cgrp, + }; struct metric_event *me; int num = 1; if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu); + total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); if (total) { ratio = avg / total; @@ -892,12 +960,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); } - total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, - ctx, cpu); + total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd); total = max(total, runtime_stat_avg(st, STAT_STALLED_CYCLES_BACK, - ctx, cpu)); + cpu, &rsd)); if (total && avg) { out->new_line(config, ctxp); @@ -907,8 +974,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ratio); } } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { - if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0) - print_branch_misses(config, cpu, evsel, avg, out, st); + if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0) + print_branch_misses(config, cpu, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( @@ -917,8 +984,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0) - print_l1_dcache_misses(config, cpu, evsel, avg, out, st); + if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0) + print_l1_dcache_misses(config, cpu, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0); } else if ( @@ -927,8 +994,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0) - print_l1_icache_misses(config, cpu, evsel, avg, out, st); + if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0) + print_l1_icache_misses(config, cpu, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0); } else if ( @@ -937,8 +1004,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0) - print_dtlb_cache_misses(config, cpu, evsel, avg, out, st); + if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0) + print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0); } else if ( @@ -947,8 +1014,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0) - print_itlb_cache_misses(config, cpu, evsel, avg, out, st); + if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0) + print_itlb_cache_misses(config, cpu, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0); } else if ( @@ -957,27 +1024,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0) - print_ll_cache_misses(config, cpu, evsel, avg, out, st); + if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0) + print_ll_cache_misses(config, cpu, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0); } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { - total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu); + total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd); if (total) ratio = avg * 100 / total; - if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0) + if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.3f %%", "of all cache refs", ratio); else print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st); + print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(config, cpu, evsel, avg, out, st); + print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = runtime_stat_avg(st, STAT_NSECS, 0, cpu); + total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd); if (total) { ratio = avg / total; @@ -986,7 +1053,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "Ghz", 0); } } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) { - total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu); + total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); if (total) print_metric(config, ctxp, NULL, @@ -996,8 +1063,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "transactional cycles", 0); } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) { - total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu); - total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu); + total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); + total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd); if (total2 < avg) total2 = avg; @@ -1007,21 +1074,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0); } else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, - ctx, cpu); + total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd); if (avg) ratio = total / avg; - if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0) + if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.0f", "cycles / transaction", ratio); else print_metric(config, ctxp, NULL, NULL, "cycles / transaction", 0); } else if (perf_stat_evsel__is(evsel, ELISION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, - ctx, cpu); + total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd); if (avg) ratio = total / avg; @@ -1034,28 +1099,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { - double fe_bound = td_fe_bound(ctx, cpu, st); + double fe_bound = td_fe_bound(cpu, st, &rsd); if (fe_bound > 0.2) color = PERF_COLOR_RED; print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", fe_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) { - double retiring = td_retiring(ctx, cpu, st); + double retiring = td_retiring(cpu, st, &rsd); if (retiring > 0.7) color = PERF_COLOR_GREEN; print_metric(config, ctxp, color, "%8.1f%%", "retiring", retiring * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) { - double bad_spec = td_bad_spec(ctx, cpu, st); + double bad_spec = td_bad_spec(cpu, st, &rsd); if (bad_spec > 0.1) color = PERF_COLOR_RED; print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", bad_spec * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) { - double be_bound = td_be_bound(ctx, cpu, st); + double be_bound = td_be_bound(cpu, st, &rsd); const char *name = "backend bound"; static int have_recovery_bubbles = -1; @@ -1068,19 +1133,55 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (be_bound > 0.2) color = PERF_COLOR_RED; - if (td_total_slots(ctx, cpu, st) > 0) + if (td_total_slots(cpu, st, &rsd) > 0) print_metric(config, ctxp, color, "%8.1f%%", name, be_bound * 100.); else print_metric(config, ctxp, NULL, NULL, name, 0); + } else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) && + full_td(cpu, st, &rsd)) { + double retiring = td_metric_ratio(cpu, + STAT_TOPDOWN_RETIRING, st, + &rsd); + if (retiring > 0.7) + color = PERF_COLOR_GREEN; + print_metric(config, ctxp, color, "%8.1f%%", "retiring", + retiring * 100.); + } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) && + full_td(cpu, st, &rsd)) { + double fe_bound = td_metric_ratio(cpu, + STAT_TOPDOWN_FE_BOUND, st, + &rsd); + if (fe_bound > 0.2) + color = PERF_COLOR_RED; + print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", + fe_bound * 100.); + } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) && + full_td(cpu, st, &rsd)) { + double be_bound = td_metric_ratio(cpu, + STAT_TOPDOWN_BE_BOUND, st, + &rsd); + if (be_bound > 0.2) + color = PERF_COLOR_RED; + print_metric(config, ctxp, color, "%8.1f%%", "backend bound", + be_bound * 100.); + } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) && + full_td(cpu, st, &rsd)) { + double bad_spec = td_metric_ratio(cpu, + STAT_TOPDOWN_BAD_SPEC, st, + &rsd); + if (bad_spec > 0.1) + color = PERF_COLOR_RED; + print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", + bad_spec * 100.); } else if (evsel->metric_expr) { generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL, evsel->name, evsel->metric_name, NULL, 1, cpu, out, st); - } else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) { + } else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) { char unit = 'M'; char unit_buf[10]; - total = runtime_stat_avg(st, STAT_NSECS, 0, cpu); + total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd); if (total) ratio = 1000.0 * avg / total; @@ -1091,7 +1192,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { - print_smi_cost(config, cpu, evsel, out, st); + print_smi_cost(config, cpu, out, st, &rsd); } else { num = 0; } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index cdb154381a873..8ce1479c98f03 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -95,6 +95,10 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired), ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles), ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles), + ID(TOPDOWN_RETIRING, topdown-retiring), + ID(TOPDOWN_BAD_SPEC, topdown-bad-spec), + ID(TOPDOWN_FE_BOUND, topdown-fe-bound), + ID(TOPDOWN_BE_BOUND, topdown-be-bound), ID(SMI_NUM, msr/smi/), ID(APERF, msr/aperf/), }; @@ -180,7 +184,7 @@ static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw) return 0; } -int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw) +int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw) { struct evsel *evsel; @@ -192,11 +196,11 @@ int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw) return 0; out_free: - perf_evlist__free_stats(evlist); + evlist__free_stats(evlist); return -1; } -void perf_evlist__free_stats(struct evlist *evlist) +void evlist__free_stats(struct evlist *evlist) { struct evsel *evsel; @@ -207,7 +211,7 @@ void perf_evlist__free_stats(struct evlist *evlist) } } -void perf_evlist__reset_stats(struct evlist *evlist) +void evlist__reset_stats(struct evlist *evlist) { struct evsel *evsel; @@ -217,7 +221,7 @@ void perf_evlist__reset_stats(struct evlist *evlist) } } -void perf_evlist__reset_prev_raw_counts(struct evlist *evlist) +void evlist__reset_prev_raw_counts(struct evlist *evlist) { struct evsel *evsel; @@ -225,7 +229,7 @@ void perf_evlist__reset_prev_raw_counts(struct evlist *evlist) evsel__reset_prev_raw_counts(evsel); } -static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel) +static void evsel__copy_prev_raw_counts(struct evsel *evsel) { int ncpus = evsel__nr_cpus(evsel); int nthreads = perf_thread_map__nr(evsel->core.threads); @@ -241,15 +245,15 @@ static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel) evsel->counts->aggr = evsel->prev_raw_counts->aggr; } -void perf_evlist__copy_prev_raw_counts(struct evlist *evlist) +void evlist__copy_prev_raw_counts(struct evlist *evlist) { struct evsel *evsel; evlist__for_each_entry(evlist, evsel) - perf_evsel__copy_prev_raw_counts(evsel); + evsel__copy_prev_raw_counts(evsel); } -void perf_evlist__save_aggr_prev_raw_counts(struct evlist *evlist) +void evlist__save_aggr_prev_raw_counts(struct evlist *evlist) { struct evsel *evsel; @@ -309,7 +313,7 @@ static int check_per_pkg(struct evsel *counter, if (!(vals->run && vals->ena)) return 0; - s = cpu_map__get_socket(cpus, cpu, NULL); + s = cpu_map__get_socket(cpus, cpu, NULL).socket; if (s < 0) return -1; @@ -454,7 +458,7 @@ int perf_event__process_stat_event(struct perf_session *session, count.ena = st->ena; count.run = st->run; - counter = perf_evlist__id2evsel(session->evlist, st->id); + counter = evlist__id2evsel(session->evlist, st->id); if (!counter) { pr_err("Failed to resolve counter for stat event.\n"); return -EINVAL; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index aa3bed48511b3..b5369730b4a2a 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -6,6 +6,7 @@ #include <stdio.h> #include <sys/types.h> #include <sys/resource.h> +#include "cpumap.h" #include "rblist.h" struct perf_cpu_map; @@ -28,6 +29,10 @@ enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED, PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES, PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES, + PERF_STAT_EVSEL_ID__TOPDOWN_RETIRING, + PERF_STAT_EVSEL_ID__TOPDOWN_BAD_SPEC, + PERF_STAT_EVSEL_ID__TOPDOWN_FE_BOUND, + PERF_STAT_EVSEL_ID__TOPDOWN_BE_BOUND, PERF_STAT_EVSEL_ID__SMI_NUM, PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, @@ -82,6 +87,10 @@ enum stat_type { STAT_TOPDOWN_SLOTS_RETIRED, STAT_TOPDOWN_FETCH_BUBBLES, STAT_TOPDOWN_RECOVERY_BUBBLES, + STAT_TOPDOWN_RETIRING, + STAT_TOPDOWN_BAD_SPEC, + STAT_TOPDOWN_FE_BOUND, + STAT_TOPDOWN_BE_BOUND, STAT_SMI_NUM, STAT_APERF, STAT_MAX @@ -91,7 +100,7 @@ struct runtime_stat { struct rblist value_list; }; -typedef int (*aggr_get_id_t)(struct perf_stat_config *config, +typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu_map *m, int cpu); struct perf_stat_config { @@ -114,6 +123,7 @@ struct perf_stat_config { bool metric_no_group; bool metric_no_merge; bool stop_read_counter; + bool quiet; FILE *output; unsigned int interval; unsigned int timeout; @@ -129,13 +139,15 @@ struct perf_stat_config { const char *csv_sep; struct stats *walltime_nsecs_stats; struct rusage ru_data; - struct perf_cpu_map *aggr_map; + struct cpu_aggr_map *aggr_map; aggr_get_id_t aggr_get_id; - struct perf_cpu_map *cpus_aggr_map; + struct cpu_aggr_map *cpus_aggr_map; u64 *walltime_run; struct rblist metric_events; int ctl_fd; int ctl_fd_ack; + bool ctl_fd_close; + const char *cgroup_list; }; void perf_stat__set_big_num(int set); @@ -159,7 +171,7 @@ struct evlist; struct perf_aggr_thread_value { struct evsel *counter; - int id; + struct aggr_cpu_id id; double uval; u64 val; u64 run; @@ -202,12 +214,12 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct runtime_stat *st); void perf_stat__collect_metric_expr(struct evlist *); -int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw); -void perf_evlist__free_stats(struct evlist *evlist); -void perf_evlist__reset_stats(struct evlist *evlist); -void perf_evlist__reset_prev_raw_counts(struct evlist *evlist); -void perf_evlist__copy_prev_raw_counts(struct evlist *evlist); -void perf_evlist__save_aggr_prev_raw_counts(struct evlist *evlist); +int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw); +void evlist__free_stats(struct evlist *evlist); +void evlist__reset_stats(struct evlist *evlist); +void evlist__reset_prev_raw_counts(struct evlist *evlist); +void evlist__copy_prev_raw_counts(struct evlist *evlist); +void evlist__save_aggr_prev_raw_counts(struct evlist *evlist); int perf_stat_process_counter(struct perf_stat_config *config, struct evsel *counter); @@ -227,12 +239,8 @@ int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, struct target *target, int cpu); -void -perf_evlist__print_counters(struct evlist *evlist, - struct perf_stat_config *config, - struct target *_target, - struct timespec *ts, - int argc, const char **argv); +void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, + struct target *_target, struct timespec *ts, int argc, const char **argv); struct metric_expr; double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st); diff --git a/tools/perf/util/stream.c b/tools/perf/util/stream.c new file mode 100644 index 0000000000000..4bd5e5a00aa5e --- /dev/null +++ b/tools/perf/util/stream.c @@ -0,0 +1,342 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Compare and figure out the top N hottest streams + * Copyright (c) 2020, Intel Corporation. + * Author: Jin Yao + */ + +#include <inttypes.h> +#include <stdlib.h> +#include <linux/zalloc.h> +#include "debug.h" +#include "hist.h" +#include "sort.h" +#include "stream.h" +#include "evlist.h" + +static void evsel_streams__delete(struct evsel_streams *es, int nr_evsel) +{ + for (int i = 0; i < nr_evsel; i++) + zfree(&es[i].streams); + + free(es); +} + +void evlist_streams__delete(struct evlist_streams *els) +{ + evsel_streams__delete(els->ev_streams, els->nr_evsel); + free(els); +} + +static struct evlist_streams *evlist_streams__new(int nr_evsel, + int nr_streams_max) +{ + struct evlist_streams *els; + struct evsel_streams *es; + + els = zalloc(sizeof(*els)); + if (!els) + return NULL; + + es = calloc(nr_evsel, sizeof(struct evsel_streams)); + if (!es) { + free(els); + return NULL; + } + + for (int i = 0; i < nr_evsel; i++) { + struct evsel_streams *s = &es[i]; + + s->streams = calloc(nr_streams_max, sizeof(struct stream)); + if (!s->streams) + goto err; + + s->nr_streams_max = nr_streams_max; + s->evsel_idx = -1; + } + + els->ev_streams = es; + els->nr_evsel = nr_evsel; + return els; + +err: + evsel_streams__delete(es, nr_evsel); + return NULL; +} + +/* + * The cnodes with high hit number are hot callchains. + */ +static void evsel_streams__set_hot_cnode(struct evsel_streams *es, + struct callchain_node *cnode) +{ + int i, idx = 0; + u64 hit; + + if (es->nr_streams < es->nr_streams_max) { + i = es->nr_streams; + es->streams[i].cnode = cnode; + es->nr_streams++; + return; + } + + /* + * Considering a few number of hot streams, only use simple + * way to find the cnode with smallest hit number and replace. + */ + hit = (es->streams[0].cnode)->hit; + for (i = 1; i < es->nr_streams; i++) { + if ((es->streams[i].cnode)->hit < hit) { + hit = (es->streams[i].cnode)->hit; + idx = i; + } + } + + if (cnode->hit > hit) + es->streams[idx].cnode = cnode; +} + +static void update_hot_callchain(struct hist_entry *he, + struct evsel_streams *es) +{ + struct rb_root *root = &he->sorted_chain; + struct rb_node *rb_node = rb_first(root); + struct callchain_node *cnode; + + while (rb_node) { + cnode = rb_entry(rb_node, struct callchain_node, rb_node); + evsel_streams__set_hot_cnode(es, cnode); + rb_node = rb_next(rb_node); + } +} + +static void init_hot_callchain(struct hists *hists, struct evsel_streams *es) +{ + struct rb_node *next = rb_first_cached(&hists->entries); + + while (next) { + struct hist_entry *he; + + he = rb_entry(next, struct hist_entry, rb_node); + update_hot_callchain(he, es); + next = rb_next(&he->rb_node); + } + + es->streams_hits = callchain_total_hits(hists); +} + +static int evlist__init_callchain_streams(struct evlist *evlist, + struct evlist_streams *els) +{ + struct evsel_streams *es = els->ev_streams; + struct evsel *pos; + int i = 0; + + BUG_ON(els->nr_evsel < evlist->core.nr_entries); + + evlist__for_each_entry(evlist, pos) { + struct hists *hists = evsel__hists(pos); + + hists__output_resort(hists, NULL); + init_hot_callchain(hists, &es[i]); + es[i].evsel_idx = pos->idx; + i++; + } + + return 0; +} + +struct evlist_streams *evlist__create_streams(struct evlist *evlist, + int nr_streams_max) +{ + int nr_evsel = evlist->core.nr_entries, ret = -1; + struct evlist_streams *els = evlist_streams__new(nr_evsel, + nr_streams_max); + + if (!els) + return NULL; + + ret = evlist__init_callchain_streams(evlist, els); + if (ret) { + evlist_streams__delete(els); + return NULL; + } + + return els; +} + +struct evsel_streams *evsel_streams__entry(struct evlist_streams *els, + int evsel_idx) +{ + struct evsel_streams *es = els->ev_streams; + + for (int i = 0; i < els->nr_evsel; i++) { + if (es[i].evsel_idx == evsel_idx) + return &es[i]; + } + + return NULL; +} + +static struct stream *stream__callchain_match(struct stream *base_stream, + struct evsel_streams *es_pair) +{ + for (int i = 0; i < es_pair->nr_streams; i++) { + struct stream *pair_stream = &es_pair->streams[i]; + + if (callchain_cnode_matched(base_stream->cnode, + pair_stream->cnode)) { + return pair_stream; + } + } + + return NULL; +} + +static struct stream *stream__match(struct stream *base_stream, + struct evsel_streams *es_pair) +{ + return stream__callchain_match(base_stream, es_pair); +} + +static void stream__link(struct stream *base_stream, struct stream *pair_stream) +{ + base_stream->pair_cnode = pair_stream->cnode; + pair_stream->pair_cnode = base_stream->cnode; +} + +void evsel_streams__match(struct evsel_streams *es_base, + struct evsel_streams *es_pair) +{ + for (int i = 0; i < es_base->nr_streams; i++) { + struct stream *base_stream = &es_base->streams[i]; + struct stream *pair_stream; + + pair_stream = stream__match(base_stream, es_pair); + if (pair_stream) + stream__link(base_stream, pair_stream); + } +} + +static void print_callchain_pair(struct stream *base_stream, int idx, + struct evsel_streams *es_base, + struct evsel_streams *es_pair) +{ + struct callchain_node *base_cnode = base_stream->cnode; + struct callchain_node *pair_cnode = base_stream->pair_cnode; + struct callchain_list *base_chain, *pair_chain; + char buf1[512], buf2[512], cbuf1[256], cbuf2[256]; + char *s1, *s2; + double pct; + + printf("\nhot chain pair %d:\n", idx); + + pct = (double)base_cnode->hit / (double)es_base->streams_hits; + scnprintf(buf1, sizeof(buf1), "cycles: %ld, hits: %.2f%%", + callchain_avg_cycles(base_cnode), pct * 100.0); + + pct = (double)pair_cnode->hit / (double)es_pair->streams_hits; + scnprintf(buf2, sizeof(buf2), "cycles: %ld, hits: %.2f%%", + callchain_avg_cycles(pair_cnode), pct * 100.0); + + printf("%35s\t%35s\n", buf1, buf2); + + printf("%35s\t%35s\n", + "---------------------------", + "--------------------------"); + + pair_chain = list_first_entry(&pair_cnode->val, + struct callchain_list, + list); + + list_for_each_entry(base_chain, &base_cnode->val, list) { + if (&pair_chain->list == &pair_cnode->val) + return; + + s1 = callchain_list__sym_name(base_chain, cbuf1, sizeof(cbuf1), + false); + s2 = callchain_list__sym_name(pair_chain, cbuf2, sizeof(cbuf2), + false); + + scnprintf(buf1, sizeof(buf1), "%35s\t%35s", s1, s2); + printf("%s\n", buf1); + pair_chain = list_next_entry(pair_chain, list); + } +} + +static void print_stream_callchain(struct stream *stream, int idx, + struct evsel_streams *es, bool pair) +{ + struct callchain_node *cnode = stream->cnode; + struct callchain_list *chain; + char buf[512], cbuf[256], *s; + double pct; + + printf("\nhot chain %d:\n", idx); + + pct = (double)cnode->hit / (double)es->streams_hits; + scnprintf(buf, sizeof(buf), "cycles: %ld, hits: %.2f%%", + callchain_avg_cycles(cnode), pct * 100.0); + + if (pair) { + printf("%35s\t%35s\n", "", buf); + printf("%35s\t%35s\n", + "", "--------------------------"); + } else { + printf("%35s\n", buf); + printf("%35s\n", "--------------------------"); + } + + list_for_each_entry(chain, &cnode->val, list) { + s = callchain_list__sym_name(chain, cbuf, sizeof(cbuf), false); + + if (pair) + scnprintf(buf, sizeof(buf), "%35s\t%35s", "", s); + else + scnprintf(buf, sizeof(buf), "%35s", s); + + printf("%s\n", buf); + } +} + +static void callchain_streams_report(struct evsel_streams *es_base, + struct evsel_streams *es_pair) +{ + struct stream *base_stream; + int i, idx = 0; + + printf("[ Matched hot streams ]\n"); + for (i = 0; i < es_base->nr_streams; i++) { + base_stream = &es_base->streams[i]; + if (base_stream->pair_cnode) { + print_callchain_pair(base_stream, ++idx, + es_base, es_pair); + } + } + + idx = 0; + printf("\n[ Hot streams in old perf data only ]\n"); + for (i = 0; i < es_base->nr_streams; i++) { + base_stream = &es_base->streams[i]; + if (!base_stream->pair_cnode) { + print_stream_callchain(base_stream, ++idx, + es_base, false); + } + } + + idx = 0; + printf("\n[ Hot streams in new perf data only ]\n"); + for (i = 0; i < es_pair->nr_streams; i++) { + base_stream = &es_pair->streams[i]; + if (!base_stream->pair_cnode) { + print_stream_callchain(base_stream, ++idx, + es_pair, true); + } + } +} + +void evsel_streams__report(struct evsel_streams *es_base, + struct evsel_streams *es_pair) +{ + return callchain_streams_report(es_base, es_pair); +} diff --git a/tools/perf/util/stream.h b/tools/perf/util/stream.h new file mode 100644 index 0000000000000..bee768874feaa --- /dev/null +++ b/tools/perf/util/stream.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_STREAM_H +#define __PERF_STREAM_H + +#include "callchain.h" + +struct stream { + struct callchain_node *cnode; + struct callchain_node *pair_cnode; +}; + +struct evsel_streams { + struct stream *streams; + int nr_streams_max; + int nr_streams; + int evsel_idx; + u64 streams_hits; +}; + +struct evlist_streams { + struct evsel_streams *ev_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); + +void evsel_streams__match(struct evsel_streams *es_base, + struct evsel_streams *es_pair); + +void evsel_streams__report(struct evsel_streams *es_base, + struct evsel_streams *es_pair); + +#endif /* __PERF_STREAM_H */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 8cc4b0059fb00..f3577f7d72fee 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -50,6 +50,10 @@ typedef Elf64_Nhdr GElf_Nhdr; #define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ #endif +#ifdef HAVE_LIBBFD_SUPPORT +#define PACKAGE 'perf' +#include <bfd.h> +#else #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT extern char *cplus_demangle(const char *, int); @@ -65,9 +69,7 @@ static inline char *bfd_demangle(void __maybe_unused *v, { return NULL; } -#else -#define PACKAGE 'perf' -#include <bfd.h> +#endif #endif #endif @@ -530,8 +532,40 @@ out: return err; } -int filename__read_build_id(const char *filename, void *bf, size_t size) +#ifdef HAVE_LIBBFD_BUILDID_SUPPORT + +static int read_build_id(const char *filename, struct build_id *bid) +{ + size_t size = sizeof(bid->data); + int err = -1; + bfd *abfd; + + abfd = bfd_openr(filename, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename); + goto out_close; + } + + if (!abfd->build_id || abfd->build_id->size > size) + goto out_close; + + memcpy(bid->data, abfd->build_id->data, abfd->build_id->size); + memset(bid->data + abfd->build_id->size, 0, size - abfd->build_id->size); + err = bid->size = abfd->build_id->size; + +out_close: + bfd_close(abfd); + return err; +} + +#else // HAVE_LIBBFD_BUILDID_SUPPORT + +static int read_build_id(const char *filename, struct build_id *bid) { + size_t size = sizeof(bid->data); int fd, err = -1; Elf *elf; @@ -548,7 +582,9 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) goto out_close; } - err = elf_read_build_id(elf, bf, size); + err = elf_read_build_id(elf, bid->data, size); + if (err > 0) + bid->size = err; elf_end(elf); out_close: @@ -557,12 +593,45 @@ out: return err; } -int sysfs__read_build_id(const char *filename, void *build_id, size_t size) +#endif // HAVE_LIBBFD_BUILDID_SUPPORT + +int filename__read_build_id(const char *filename, struct build_id *bid) { - int fd, err = -1; + struct kmod_path m = { .name = NULL, }; + char path[PATH_MAX]; + int err; - if (size < BUILD_ID_SIZE) - goto out; + if (!filename) + return -EFAULT; + + err = kmod_path__parse(&m, filename); + if (err) + return -1; + + if (m.comp) { + int error = 0, fd; + + fd = filename__decompress(filename, path, sizeof(path), m.comp, &error); + if (fd < 0) { + pr_debug("Failed to decompress (error %d) %s\n", + error, filename); + return -1; + } + close(fd); + filename = path; + } + + err = read_build_id(filename, bid); + + if (m.comp) + unlink(filename); + return err; +} + +int sysfs__read_build_id(const char *filename, struct build_id *bid) +{ + size_t size = sizeof(bid->data); + int fd, err = -1; fd = open(filename, O_RDONLY); if (fd < 0) @@ -584,8 +653,9 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) break; if (memcmp(bf, "GNU", sizeof("GNU")) == 0) { size_t sz = min(descsz, size); - if (read(fd, build_id, sz) == (ssize_t)sz) { - memset(build_id + sz, 0, size - sz); + if (read(fd, bid->data, sz) == (ssize_t)sz) { + memset(bid->data + sz, 0, size - sz); + bid->size = sz; err = 0; break; } @@ -608,6 +678,44 @@ out: return err; } +#ifdef HAVE_LIBBFD_SUPPORT + +int filename__read_debuglink(const char *filename, char *debuglink, + size_t size) +{ + int err = -1; + asection *section; + bfd *abfd; + + abfd = bfd_openr(filename, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename); + goto out_close; + } + + section = bfd_get_section_by_name(abfd, ".gnu_debuglink"); + if (!section) + goto out_close; + + if (section->size > size) + goto out_close; + + if (!bfd_get_section_contents(abfd, section, debuglink, 0, + section->size)) + goto out_close; + + err = 0; + +out_close: + bfd_close(abfd); + return err; +} + +#else + int filename__read_debuglink(const char *filename, char *debuglink, size_t size) { @@ -660,6 +768,8 @@ out: return err; } +#endif + static int dso__swap_init(struct dso *dso, unsigned char eidata) { static unsigned int const endian = 1; @@ -757,13 +867,17 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, /* Always reject images with a mismatched build-id: */ if (dso->has_build_id && !symbol_conf.ignore_vmlinux_buildid) { u8 build_id[BUILD_ID_SIZE]; + struct build_id bid; + int size; - if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) { + size = elf_read_build_id(elf, build_id, BUILD_ID_SIZE); + if (size <= 0) { dso->load_errno = DSO_LOAD_ERRNO__CANNOT_READ_BUILDID; goto out_elf_end; } - if (!dso__build_id_equal(dso, build_id)) { + build_id__init(&bid, build_id, size); + if (!dso__build_id_equal(dso, &bid)) { pr_debug("%s: build id mismatch for %s.\n", __func__, name); dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID; goto out_elf_end; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index d6e99af263ecc..f9eb0bee7f157 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -31,9 +31,10 @@ static bool check_need_swap(int file_endian) #define NT_GNU_BUILD_ID 3 -static int read_build_id(void *note_data, size_t note_len, void *bf, - size_t size, bool need_swap) +static int read_build_id(void *note_data, size_t note_len, struct build_id *bid, + bool need_swap) { + size_t size = sizeof(bid->data); struct { u32 n_namesz; u32 n_descsz; @@ -63,8 +64,9 @@ static int read_build_id(void *note_data, size_t note_len, void *bf, nhdr->n_namesz == sizeof("GNU")) { if (memcmp(name, "GNU", sizeof("GNU")) == 0) { size_t sz = min(size, descsz); - memcpy(bf, ptr, sz); - memset(bf + sz, 0, size - sz); + memcpy(bid->data, ptr, sz); + memset(bid->data + sz, 0, size - sz); + bid->size = sz; return 0; } } @@ -84,7 +86,7 @@ int filename__read_debuglink(const char *filename __maybe_unused, /* * Just try PT_NOTE header otherwise fails */ -int filename__read_build_id(const char *filename, void *bf, size_t size) +int filename__read_build_id(const char *filename, struct build_id *bid) { FILE *fp; int ret = -1; @@ -156,9 +158,9 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) if (fread(buf, buf_size, 1, fp) != 1) goto out_free; - ret = read_build_id(buf, buf_size, bf, size, need_swap); + ret = read_build_id(buf, buf_size, bid, need_swap); if (ret == 0) - ret = size; + ret = bid->size; break; } } else { @@ -207,9 +209,9 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) if (fread(buf, buf_size, 1, fp) != 1) goto out_free; - ret = read_build_id(buf, buf_size, bf, size, need_swap); + ret = read_build_id(buf, buf_size, bid, need_swap); if (ret == 0) - ret = size; + ret = bid->size; break; } } @@ -220,7 +222,7 @@ out: return ret; } -int sysfs__read_build_id(const char *filename, void *build_id, size_t size) +int sysfs__read_build_id(const char *filename, struct build_id *bid) { int fd; int ret = -1; @@ -243,7 +245,7 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) if (read(fd, buf, buf_size) != (ssize_t) buf_size) goto out_free; - ret = read_build_id(buf, buf_size, build_id, size, false); + ret = read_build_id(buf, buf_size, bid, false); out_free: free(buf); out: @@ -339,16 +341,15 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, struct symsrc *runtime_ss __maybe_unused, int kmodule __maybe_unused) { - unsigned char build_id[BUILD_ID_SIZE]; + struct build_id bid; int ret; ret = fd__is_64_bit(ss->fd); if (ret >= 0) dso->is_64_bit = ret; - if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) { - dso__set_build_id(dso, build_id); - } + if (filename__read_build_id(ss->name, &bid) > 0) + dso__set_build_id(dso, &bid); return 0; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 5151a8c0b791a..64a039cbba1b5 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -515,6 +515,13 @@ void dso__insert_symbol(struct dso *dso, struct symbol *sym) } } +void dso__delete_symbol(struct dso *dso, struct symbol *sym) +{ + rb_erase_cached(&sym->rb_node, &dso->symbols); + symbol__delete(sym); + dso__reset_find_symbol_cache(dso); +} + struct symbol *dso__find_symbol(struct dso *dso, u64 addr) { if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) { @@ -1526,6 +1533,138 @@ out_failure: return -1; } +#ifdef HAVE_LIBBFD_SUPPORT +#define PACKAGE 'perf' +#include <bfd.h> + +static int bfd_symbols__cmpvalue(const void *a, const void *b) +{ + const asymbol *as = *(const asymbol **)a, *bs = *(const asymbol **)b; + + if (bfd_asymbol_value(as) != bfd_asymbol_value(bs)) + return bfd_asymbol_value(as) - bfd_asymbol_value(bs); + + return bfd_asymbol_name(as)[0] - bfd_asymbol_name(bs)[0]; +} + +static int bfd2elf_binding(asymbol *symbol) +{ + if (symbol->flags & BSF_WEAK) + return STB_WEAK; + if (symbol->flags & BSF_GLOBAL) + return STB_GLOBAL; + if (symbol->flags & BSF_LOCAL) + return STB_LOCAL; + return -1; +} + +int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) +{ + int err = -1; + long symbols_size, symbols_count; + asection *section; + asymbol **symbols, *sym; + struct symbol *symbol; + bfd *abfd; + u_int i; + u64 start, len; + + abfd = bfd_openr(dso->long_name, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, + dso->long_name); + goto out_close; + } + + if (bfd_get_flavour(abfd) == bfd_target_elf_flavour) + goto out_close; + + section = bfd_get_section_by_name(abfd, ".text"); + if (section) + dso->text_offset = section->vma - section->filepos; + + bfd_close(abfd); + + abfd = bfd_openr(debugfile, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, + debugfile); + goto out_close; + } + + if (bfd_get_flavour(abfd) == bfd_target_elf_flavour) + goto out_close; + + symbols_size = bfd_get_symtab_upper_bound(abfd); + if (symbols_size == 0) { + bfd_close(abfd); + return 0; + } + + if (symbols_size < 0) + goto out_close; + + symbols = malloc(symbols_size); + if (!symbols) + goto out_close; + + symbols_count = bfd_canonicalize_symtab(abfd, symbols); + if (symbols_count < 0) + goto out_free; + + qsort(symbols, symbols_count, sizeof(asymbol *), bfd_symbols__cmpvalue); + +#ifdef bfd_get_section +#define bfd_asymbol_section bfd_get_section +#endif + for (i = 0; i < symbols_count; ++i) { + sym = symbols[i]; + section = bfd_asymbol_section(sym); + if (bfd2elf_binding(sym) < 0) + continue; + + while (i + 1 < symbols_count && + bfd_asymbol_section(symbols[i + 1]) == section && + bfd2elf_binding(symbols[i + 1]) < 0) + i++; + + if (i + 1 < symbols_count && + bfd_asymbol_section(symbols[i + 1]) == section) + len = symbols[i + 1]->value - sym->value; + else + len = section->size - sym->value; + + start = bfd_asymbol_value(sym) - dso->text_offset; + symbol = symbol__new(start, len, bfd2elf_binding(sym), STT_FUNC, + bfd_asymbol_name(sym)); + if (!symbol) + goto out_free; + + symbols__insert(&dso->symbols, symbol); + } +#ifdef bfd_get_section +#undef bfd_asymbol_section +#endif + + symbols__fixup_end(&dso->symbols); + symbols__fixup_duplicate(&dso->symbols); + dso->adjust_symbols = 1; + + err = 0; +out_free: + free(symbols); +out_close: + bfd_close(abfd); + return err; +} +#endif + static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, enum dso_binary_type type) { @@ -1623,7 +1762,7 @@ int dso__load(struct dso *dso, struct map *map) struct symsrc *syms_ss = NULL, *runtime_ss = NULL; bool kmod; bool perfmap; - unsigned char build_id[BUILD_ID_SIZE]; + struct build_id bid; struct nscookie nsc; char newmapname[PATH_MAX]; const char *map_path = dso->long_name; @@ -1685,8 +1824,8 @@ int dso__load(struct dso *dso, struct map *map) if (!dso->has_build_id && is_regular_file(dso->long_name)) { __symbol__join_symfs(name, PATH_MAX, dso->long_name); - if (filename__read_build_id(name, build_id, BUILD_ID_SIZE) > 0) - dso__set_build_id(dso, build_id); + if (filename__read_build_id(name, &bid) > 0) + dso__set_build_id(dso, &bid); } /* @@ -1699,6 +1838,7 @@ int dso__load(struct dso *dso, struct map *map) bool next_slot = false; bool is_reg; bool nsexit; + int bfdrc = -1; int sirc = -1; enum dso_binary_type symtab_type = binary_type_symtab[i]; @@ -1717,12 +1857,19 @@ int dso__load(struct dso *dso, struct map *map) nsinfo__mountns_exit(&nsc); is_reg = is_regular_file(name); +#ifdef HAVE_LIBBFD_SUPPORT if (is_reg) + bfdrc = dso__load_bfd_symbols(dso, name); +#endif + if (is_reg && bfdrc < 0) sirc = symsrc__init(ss, dso, name, symtab_type); if (nsexit) nsinfo__mountns_enter(dso->nsinfo, &nsc); + if (bfdrc == 0) + break; + if (!is_reg || sirc < 0) continue; @@ -1982,7 +2129,7 @@ static bool filename__readable(const char *file) static char *dso__find_kallsyms(struct dso *dso, struct map *map) { - u8 host_build_id[BUILD_ID_SIZE]; + struct build_id bid; char sbuild_id[SBUILD_ID_SIZE]; bool is_host = false; char path[PATH_MAX]; @@ -1995,9 +2142,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map) goto proc_kallsyms; } - if (sysfs__read_build_id("/sys/kernel/notes", host_build_id, - sizeof(host_build_id)) == 0) - is_host = dso__build_id_equal(dso, host_build_id); + if (sysfs__read_build_id("/sys/kernel/notes", &bid) == 0) + is_host = dso__build_id_equal(dso, &bid); /* Try a fast path for /proc/kallsyms if possible */ if (is_host) { @@ -2013,7 +2159,7 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map) goto proc_kallsyms; } - build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + build_id__sprintf(&dso->bid, sbuild_id); /* Find kallsyms in build-id cache with kcore */ scnprintf(path, sizeof(path), "%s/%s/%s", @@ -2043,6 +2189,8 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map) int err; const char *kallsyms_filename = NULL; char *kallsyms_allocated_filename = NULL; + char *filename = NULL; + /* * Step 1: if the user specified a kallsyms or vmlinux filename, use * it and only it, reporting errors to the user if it cannot be used. @@ -2067,6 +2215,20 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map) return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, false); } + /* + * Before checking on common vmlinux locations, check if it's + * stored as standard build id binary (not kallsyms) under + * .debug cache. + */ + if (!symbol_conf.ignore_vmlinux_buildid) + filename = __dso__build_id_filename(dso, NULL, 0, false, false); + if (filename != NULL) { + err = dso__load_vmlinux(dso, map, filename, true); + if (err > 0) + return err; + free(filename); + } + if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) { err = dso__load_vmlinux_path(dso, map); if (err > 0) diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index ff4f4c47e1484..954d6a049ee23 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -23,12 +23,13 @@ struct dso; struct map; struct maps; struct option; +struct build_id; /* * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP; * for newer versions we can use mmap to reduce memory usage: */ -#ifdef HAVE_LIBELF_MMAP_SUPPORT +#ifdef ELF_C_READ_MMAP # define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP #else # define PERF_ELF_C_READ_MMAP ELF_C_READ @@ -130,6 +131,8 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map); void dso__insert_symbol(struct dso *dso, struct symbol *sym); +void dso__delete_symbol(struct dso *dso, + struct symbol *sym); struct symbol *dso__find_symbol(struct dso *dso, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name); @@ -142,8 +145,8 @@ struct symbol *dso__next_symbol(struct symbol *sym); enum dso_type dso__type_fd(int fd); -int filename__read_build_id(const char *filename, void *bf, size_t size); -int sysfs__read_build_id(const char *filename, void *bf, size_t size); +int filename__read_build_id(const char *filename, struct build_id *id); +int sysfs__read_build_id(const char *filename, struct build_id *bid); int modules__parse(const char *filename, void *arg, int (*process_module)(void *arg, const char *name, u64 start, u64 size)); @@ -175,6 +178,10 @@ int symbol__config_symfs(const struct option *opt __maybe_unused, struct symsrc; +#ifdef HAVE_LIBBFD_SUPPORT +int dso__load_bfd_symbols(struct dso *dso, const char *debugfile); +#endif + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule); int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss); diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 89b390623b63d..2947e3f3c6d9d 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -563,6 +563,9 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool, char cgrp_root[PATH_MAX]; size_t mount_len; /* length of mount point in the path */ + if (!tool || !tool->cgroup_events) + return 0; + if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) { pr_debug("cannot find cgroup mount point\n"); return -1; @@ -1406,6 +1409,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_CGROUP) result += sizeof(u64); + if (type & PERF_SAMPLE_DATA_PAGE_SIZE) + result += sizeof(u64); + if (type & PERF_SAMPLE_AUX) { result += sizeof(u64); result += sample->aux_sample.size; @@ -1585,6 +1591,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo array++; } + if (type & PERF_SAMPLE_DATA_PAGE_SIZE) { + *array = sample->data_page_size; + array++; + } + if (type & PERF_SAMPLE_AUX) { sz = sample->aux_sample.size; *array++ = sz; @@ -1640,7 +1651,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_ e->id = evsel->core.id[j]; - sid = perf_evlist__id2sid(evlist, e->id); + sid = evlist__id2sid(evlist, e->id); if (!sid) { free(ev); return -ENOENT; @@ -1961,7 +1972,7 @@ int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 len = pos->long_name_len + 1; len = PERF_ALIGN(len, NAME_ALIGN); - memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id)); + memcpy(&ev.build_id.build_id, pos->bid.data, sizeof(pos->bid.data)); ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; ev.build_id.header.misc = misc; ev.build_id.pid = machine->pid; @@ -2006,14 +2017,6 @@ int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct p return 0; } -int __weak perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused, - struct perf_tool *tool __maybe_unused, - perf_event__handler_t process __maybe_unused, - struct machine *machine __maybe_unused) -{ - return 0; -} - extern const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE]; int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, diff --git a/tools/perf/util/topdown.c b/tools/perf/util/topdown.c new file mode 100644 index 0000000000000..1081b20f9891d --- /dev/null +++ b/tools/perf/util/topdown.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include "pmu.h" +#include "topdown.h" + +int topdown_filter_events(const char **attr, char **str, bool use_group) +{ + int off = 0; + int i; + int len = 0; + char *s; + + for (i = 0; attr[i]; i++) { + if (pmu_have_event("cpu", attr[i])) { + len += strlen(attr[i]) + 1; + attr[i - off] = attr[i]; + } else + off++; + } + attr[i - off] = NULL; + + *str = malloc(len + 1 + 2); + if (!*str) + return -1; + s = *str; + if (i - off == 0) { + *s = 0; + return 0; + } + if (use_group) + *s++ = '{'; + for (i = 0; attr[i]; i++) { + strcpy(s, attr[i]); + s += strlen(s); + *s++ = ','; + } + if (use_group) { + s[-1] = '}'; + *s = 0; + } else + s[-1] = 0; + return 0; +} + +__weak bool arch_topdown_check_group(bool *warn) +{ + *warn = false; + return false; +} + +__weak void arch_topdown_group_warn(void) +{ +} + +__weak bool arch_topdown_sample_read(struct evsel *leader __maybe_unused) +{ + return false; +} diff --git a/tools/perf/util/topdown.h b/tools/perf/util/topdown.h new file mode 100644 index 0000000000000..2f0d0b8876393 --- /dev/null +++ b/tools/perf/util/topdown.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef TOPDOWN_H +#define TOPDOWN_H 1 +#include "evsel.h" + +bool arch_topdown_check_group(bool *warn); +void arch_topdown_group_warn(void); +bool arch_topdown_sample_read(struct evsel *leader); + +int topdown_filter_events(const char **attr, char **str, bool use_group); + +#endif diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c index bfa782421cbdf..62b4c75c966ca 100644 --- a/tools/perf/util/tsc.c +++ b/tools/perf/util/tsc.c @@ -1,7 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 +#include <errno.h> + #include <linux/compiler.h> +#include <linux/perf_event.h> +#include <linux/stddef.h> #include <linux/types.h> +#include <asm/barrier.h> + +#include "event.h" +#include "synthetic-events.h" +#include "debug.h" #include "tsc.h" u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc) @@ -19,12 +28,84 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) { u64 quot, rem; + if (tc->cap_user_time_short) + cyc = tc->time_cycles + + ((cyc - tc->time_cycles) & tc->time_mask); + quot = cyc >> tc->time_shift; rem = cyc & (((u64)1 << tc->time_shift) - 1); return tc->time_zero + quot * tc->time_mult + ((rem * tc->time_mult) >> tc->time_shift); } +int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, + struct perf_tsc_conversion *tc) +{ + u32 seq; + int i = 0; + + while (1) { + seq = pc->lock; + rmb(); + tc->time_mult = pc->time_mult; + tc->time_shift = pc->time_shift; + tc->time_zero = pc->time_zero; + tc->time_cycles = pc->time_cycles; + tc->time_mask = pc->time_mask; + tc->cap_user_time_zero = pc->cap_user_time_zero; + tc->cap_user_time_short = pc->cap_user_time_short; + rmb(); + if (pc->lock == seq && !(seq & 1)) + break; + if (++i > 10000) { + pr_debug("failed to get perf_event_mmap_page lock\n"); + return -EINVAL; + } + } + + if (!tc->cap_user_time_zero) + return -EOPNOTSUPP; + + return 0; +} + +int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, + struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + union perf_event event = { + .time_conv = { + .header = { + .type = PERF_RECORD_TIME_CONV, + .size = sizeof(struct perf_record_time_conv), + }, + }, + }; + struct perf_tsc_conversion tc; + int err; + + if (!pc) + return 0; + err = perf_read_tsc_conversion(pc, &tc); + if (err == -EOPNOTSUPP) + return 0; + if (err) + return err; + + pr_debug2("Synthesizing TSC conversion information\n"); + + event.time_conv.time_mult = tc.time_mult; + event.time_conv.time_shift = tc.time_shift; + event.time_conv.time_zero = tc.time_zero; + event.time_conv.time_cycles = tc.time_cycles; + event.time_conv.time_mask = tc.time_mask; + event.time_conv.cap_user_time_zero = tc.cap_user_time_zero; + event.time_conv.cap_user_time_short = tc.cap_user_time_short; + + return process(tool, &event, NULL, machine); +} + u64 __weak rdtsc(void) { return 0; diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h index 3c5a632ee57c5..72a15419f3b3c 100644 --- a/tools/perf/util/tsc.h +++ b/tools/perf/util/tsc.h @@ -8,6 +8,11 @@ struct perf_tsc_conversion { u16 time_shift; u32 time_mult; u64 time_zero; + u64 time_cycles; + u64 time_mask; + + bool cap_user_time_zero; + bool cap_user_time_short; }; struct perf_event_mmap_page; diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 7a3dbc259cecc..0ada907c60d49 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -20,10 +20,24 @@ static char *debuginfo_path; +static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata, + const char *modname __maybe_unused, Dwarf_Addr base __maybe_unused, + const char *file_name, const char *debuglink_file __maybe_unused, + GElf_Word debuglink_crc __maybe_unused, char **debuginfo_file_name) +{ + const struct dso *dso = *userdata; + + assert(dso); + if (dso->symsrc_filename && strcmp (file_name, dso->symsrc_filename)) + *debuginfo_file_name = strdup(dso->symsrc_filename); + return -1; +} + static const Dwfl_Callbacks offline_callbacks = { - .find_debuginfo = dwfl_standard_find_debuginfo, + .find_debuginfo = __find_debuginfo, .debuginfo_path = &debuginfo_path, .section_address = dwfl_offline_section_address, + // .find_elf is not set as we use dwfl_report_elf() instead. }; static int __report_module(struct addr_location *al, u64 ip, @@ -46,16 +60,24 @@ static int __report_module(struct addr_location *al, u64 ip, mod = dwfl_addrmodule(ui->dwfl, ip); if (mod) { Dwarf_Addr s; + void **userdatap; - dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL); + dwfl_module_info(mod, &userdatap, &s, NULL, NULL, NULL, NULL, NULL); + *userdatap = dso; if (s != al->map->start - al->map->pgoff) mod = 0; } if (!mod) - mod = dwfl_report_elf(ui->dwfl, dso->short_name, - (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff, - false); + mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1, + al->map->start - al->map->pgoff, false); + if (!mod) { + char filename[PATH_MAX]; + + if (dso__build_id_filename(dso, filename, sizeof(filename), false)) + mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1, + al->map->start - al->map->pgoff, false); + } return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1; } diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index f486fdd3a538f..ad737052e5977 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -62,4 +62,10 @@ char *perf_exe(char *buf, int len); #endif #endif +extern bool test_attr__enabled; +void test_attr__ready(void); +void test_attr__init(void); +struct perf_event_attr; +void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, + int fd, int group_fd, unsigned long flags); #endif /* GIT_COMPAT_UTIL_H */ |