linux_dsm_epyc7002/tools/perf/util/pmu.h

94 lines
2.6 KiB
C
Raw Normal View History

#ifndef __PMU_H
#define __PMU_H
#include <linux/bitmap.h>
#include <linux/perf_event.h>
#include <stdbool.h>
#include "evsel.h"
#include "parse-events.h"
enum {
PERF_PMU_FORMAT_VALUE_CONFIG,
PERF_PMU_FORMAT_VALUE_CONFIG1,
PERF_PMU_FORMAT_VALUE_CONFIG2,
};
#define PERF_PMU_FORMAT_BITS 64
struct perf_event_attr;
struct perf_pmu {
char *name;
__u32 type;
bool selectable;
struct perf_event_attr *default_config;
struct cpu_map *cpus;
struct list_head format; /* HEAD struct perf_pmu_format -> list */
struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
struct list_head list; /* ELEM */
int (*set_drv_config) (struct perf_evsel_config_term *term);
};
struct perf_pmu_info {
const char *unit;
perf stat: Output JSON MetricExpr metric Add generic infrastructure to perf stat to output ratios for "MetricExpr" entries in the event lists. Many events are more useful as ratios than in raw form, typically some count in relation to total ticks. Transfer the MetricExpr information from the alias to the evsel. We mark the events that need to be collected for MetricExpr, and also link the events using them with a pointer. The code is careful to always prefer the right event in the same group to minimize multiplexing errors. At the moment only a single relation is supported. Then add a rblist to the stat shadow code that remembers stats based on the cpu and context. Then finally update and retrieve and print these values similarly to the existing hardcoded perf metrics. We use the simple expression parser added earlier to evaluate the expression. Normally we just output the result without further commentary, but for --metric-only this would lead to empty columns. So for this case use the original event as description. There is no attempt to automatically add the MetricExpr event, if it is missing, however we suggest it to the user, because the user tool doesn't have enough information to reliably construct a group that is guaranteed to schedule. So we leave that to the user. % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' 1.000147889 800,085,181 unc_p_clockticks 1.000147889 93,126,241 unc_p_freq_max_os_cycles # 11.6 2.000448381 800,218,217 unc_p_clockticks 2.000448381 142,516,095 unc_p_freq_max_os_cycles # 17.8 3.000639852 800,243,057 unc_p_clockticks 3.000639852 162,292,689 unc_p_freq_max_os_cycles # 20.3 % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' --metric-only # time freq_max_os_cycles % 1.000127077 0.9 2.000301436 0.7 3.000456379 0.0 v2: Change from DivideBy to MetricExpr v3: Use expr__ prefix. Support more than one other event. v4: Update description v5: Only print warning message once for multiple PMUs. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170320201711.14142-11-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-21 03:17:08 +07:00
const char *metric_expr;
const char *metric_name;
double scale;
bool per_pkg;
bool snapshot;
};
#define UNIT_MAX_LEN 31 /* max length for event unit name */
struct perf_pmu_alias {
char *name;
perf pmu: Support alias descriptions Add support to print alias descriptions in perf list, which are taken from the generated event files. The sorting code is changed to put the events with descriptions at the end. The descriptions are printed as possibly multiple word wrapped lines. Example output: % perf list ... arith.fpu_div [Divide operations executed] arith.fpu_div_active [Cycles when divider is busy executing divide operations] Committer notes: Further testing on a Broadwell machine (ThinkPad t450s), using these files: $ find tools/perf/pmu-events/arch/x86/ tools/perf/pmu-events/arch/x86/ tools/perf/pmu-events/arch/x86/Broadwell tools/perf/pmu-events/arch/x86/Broadwell/Cache.json tools/perf/pmu-events/arch/x86/Broadwell/Other.json tools/perf/pmu-events/arch/x86/Broadwell/Frontend.json tools/perf/pmu-events/arch/x86/Broadwell/Virtual-Memory.json tools/perf/pmu-events/arch/x86/Broadwell/Pipeline.json tools/perf/pmu-events/arch/x86/Broadwell/Floating-point.json tools/perf/pmu-events/arch/x86/Broadwell/Memory.json tools/perf/pmu-events/arch/x86/mapfile.csv $ Taken from: https://github.com/sukadev/linux/tree/json-code+data-v21/tools/perf/pmu-events/arch/x86/ to get this machinery to actually parse JSON files, generate $(OUTPUT)pmu-events/pmu-events.c, compile it and link it with perf, that will then use the table it contains, these files will be submitted right after this patchkit. [acme@jouet linux]$ perf list page_walker List of pre-defined events (to be used in -e): page_walker_loads.dtlb_l1 [Number of DTLB page walker hits in the L1+FB] page_walker_loads.dtlb_l2 [Number of DTLB page walker hits in the L2] page_walker_loads.dtlb_l3 [Number of DTLB page walker hits in the L3 + XSNP] page_walker_loads.dtlb_memory [Number of DTLB page walker hits in Memory] page_walker_loads.itlb_l1 [Number of ITLB page walker hits in the L1+FB] page_walker_loads.itlb_l2 [Number of ITLB page walker hits in the L2] page_walker_loads.itlb_l3 [Number of ITLB page walker hits in the L3 + XSNP] [acme@jouet linux]$ Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/1473978296-20712-7-git-send-email-sukadev@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-16 05:24:43 +07:00
char *desc;
char *long_desc;
perf list jevents: Add support for event list topics Add support to group the output of perf list by the Topic field in the JSON file. Example output: % perf list ... Cache: l1d.replacement [L1D data line replacements] l1d_pend_miss.pending [L1D miss oustandings duration in cycles] l1d_pend_miss.pending_cycles [Cycles with L1D load Misses outstanding] l2_l1d_wb_rqsts.all [Not rejected writebacks from L1D to L2 cache lines in any state] l2_l1d_wb_rqsts.hit_e [Not rejected writebacks from L1D to L2 cache lines in E state] l2_l1d_wb_rqsts.hit_m [Not rejected writebacks from L1D to L2 cache lines in M state] ... Pipeline: arith.fpu_div [Divide operations executed] arith.fpu_div_active [Cycles when divider is busy executing divide operations] baclears.any [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] br_inst_exec.all_branches [Speculative and retired branches] br_inst_exec.all_conditional [Speculative and retired macro-conditional branches] br_inst_exec.all_direct_jmp [Speculative and retired macro-unconditional branches excluding calls and indirects] br_inst_exec.all_direct_near_call [Speculative and retired direct near calls] br_inst_exec.all_indirect_jump_non_call_ret Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/1473978296-20712-14-git-send-email-sukadev@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-16 05:24:50 +07:00
char *topic;
char *str;
struct list_head terms; /* HEAD struct parse_events_term -> list */
struct list_head list; /* ELEM */
char unit[UNIT_MAX_LEN+1];
double scale;
bool per_pkg;
bool snapshot;
char *metric_expr;
char *metric_name;
};
struct perf_pmu *perf_pmu__find(const char *name);
int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
struct list_head *head_terms,
struct parse_events_error *error);
int perf_pmu__config_terms(struct list_head *formats,
struct perf_event_attr *attr,
struct list_head *head_terms,
bool zero, struct parse_events_error *error);
__u64 perf_pmu__format_bits(struct list_head *formats, const char *name);
tools/perf/stat: Add event unit and scale support This patch adds perf stat support for handling event units and scales as exported by the kernel. The kernel can export PMU events actual unit and scaling factor via sysfs: $ ls -1 /sys/devices/power/events/energy-* /sys/devices/power/events/energy-cores /sys/devices/power/events/energy-cores.scale /sys/devices/power/events/energy-cores.unit /sys/devices/power/events/energy-pkg /sys/devices/power/events/energy-pkg.scale /sys/devices/power/events/energy-pkg.unit $ cat /sys/devices/power/events/energy-cores.scale 2.3283064365386962890625e-10 $ cat cat /sys/devices/power/events/energy-cores.unit Joules This patch modifies the pmu event alias code to check for the presence of the .unit and .scale files to load the corresponding values. They are then used by perf stat transparently: # perf stat -a -e power/energy-pkg/,power/energy-cores/,cycles -I 1000 sleep 1000 # time counts unit events 1.000214717 3.07 Joules power/energy-pkg/ [100.00%] 1.000214717 0.53 Joules power/energy-cores/ 1.000214717 12965028 cycles [100.00%] 2.000749289 3.01 Joules power/energy-pkg/ 2.000749289 0.52 Joules power/energy-cores/ 2.000749289 15817043 cycles When the event does not have an explicit unit exported by the kernel, nothing is printed. In csv output mode, there will be an empty field. Special thanks to Jiri for providing the supporting code in the parser to trigger reading of the scale and unit files. Signed-off-by: Stephane Eranian <eranian@google.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: zheng.z.yan@intel.com Cc: bp@alien8.de Cc: maria.n.dimakopoulou@gmail.com Cc: acme@redhat.com Link: http://lkml.kernel.org/r/1384275531-10892-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-12 23:58:49 +07:00
int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
struct perf_pmu_info *info);
struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
struct list_head *head_terms);
int perf_pmu_wrap(void);
void perf_pmu_error(struct list_head *list, char *name, char const *msg);
int perf_pmu__new_format(struct list_head *list, char *name,
int config, unsigned long *bits);
void perf_pmu__set_format(unsigned long *bits, long from, long to);
int perf_pmu__format_parse(char *dir, struct list_head *head);
struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
void print_pmu_events(const char *event_glob, bool name_only, bool quiet,
bool long_desc, bool details_flag);
bool pmu_have_event(const char *pname, const char *name);
int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
...) __attribute__((format(scanf, 3, 4)));
int perf_pmu__test(void);
struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
#endif /* __PMU_H */