perf sched stats: Add schedstat v16 support

The /proc/schedstat file output is standardized with version number.

Add support to record and raw dump v16 version layout.

Version 16 of schedstats changed the order of definitions within 'enum
cpu_idle_type', which changed the order of [CPU_MAX_IDLE_TYPES] columns
in show_schedstat().

In particular the position of CPU_IDLE and __CPU_NOT_IDLE changed
places.

Co-developed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: James Clark <james.clark@linaro.org>
Acked-by: Ian Rogers <irogers@google.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Anubhav Shelat <ashelat@redhat.com>
Cc: Ben Gainey <ben.gainey@arm.com>
Cc: Blake Jones <blakejones@google.com>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: David Vernet <void@manifault.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Gautham Shenoy <gautham.shenoy@amd.com>
Cc: Graham Woodward <graham.woodward@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Santosh Shukla <santosh.shukla@amd.com>
Cc: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Yang Jihong <yangjihong@bytedance.com>
Cc: Yujie Liu <yujie.liu@intel.com>
Cc: Zhongqiu Han <quic_zhonhan@quicinc.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

3 files changed, 161 insertions, 1 deletions

diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index 9fa28e512ca8..965e066fd780 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -179,7 +179,7 @@ install_lib: libs
 		cp -fpR $(LIBPERF_ALL) $(DESTDIR)$(libdir_SQ)
 
 HDRS := bpf_perf.h core.h cpumap.h threadmap.h evlist.h evsel.h event.h mmap.h
-HDRS += schedstat-v15.h
+HDRS += schedstat-v15.h schedstat-v16.h
 INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h rc_check.h threadmap.h xyarray.h
 
 INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/perf
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index ce04fed7cefc..bd4d507ea8ab 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -502,6 +502,12 @@ struct perf_record_schedstat_cpu_v15 {
 #undef CPU_FIELD
 };
 
+struct perf_record_schedstat_cpu_v16 {
+#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver)		_type _name
+#include "schedstat-v16.h"
+#undef CPU_FIELD
+};
+
 struct perf_record_schedstat_cpu {
 	struct perf_event_header header;
 	__u64			 timestamp;
@@ -511,6 +517,7 @@ struct perf_record_schedstat_cpu {
 	char			 __pad[2];
 	union {
 		struct perf_record_schedstat_cpu_v15 v15;
+		struct perf_record_schedstat_cpu_v16 v16;
 	};
 };
 
@@ -520,6 +527,12 @@ struct perf_record_schedstat_domain_v15 {
 #undef DOMAIN_FIELD
 };
 
+struct perf_record_schedstat_domain_v16 {
+#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver)		_type _name
+#include "schedstat-v16.h"
+#undef DOMAIN_FIELD
+};
+
 #define DOMAIN_NAME_LEN		16
 
 struct perf_record_schedstat_domain {
@@ -530,6 +543,7 @@ struct perf_record_schedstat_domain {
 	__u16			 domain;
 	union {
 		struct perf_record_schedstat_domain_v15 v15;
+		struct perf_record_schedstat_domain_v16 v16;
 	};
 };
 
diff --git a/tools/lib/perf/include/perf/schedstat-v16.h b/tools/lib/perf/include/perf/schedstat-v16.h
new file mode 100644
index 000000000000..3462b79c29af
--- /dev/null
+++ b/tools/lib/perf/include/perf/schedstat-v16.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CPU_FIELD
+CPU_FIELD(__u32, yld_count, "sched_yield() count",
+	  "%11u", false, yld_count, v16);
+CPU_FIELD(__u32, array_exp, "Legacy counter can be ignored",
+	  "%11u", false, array_exp, v16);
+CPU_FIELD(__u32, sched_count, "schedule() called",
+	  "%11u", false, sched_count, v16);
+CPU_FIELD(__u32, sched_goidle, "schedule() left the processor idle",
+	  "%11u", true, sched_count, v16);
+CPU_FIELD(__u32, ttwu_count, "try_to_wake_up() was called",
+	  "%11u", false, ttwu_count, v16);
+CPU_FIELD(__u32, ttwu_local, "try_to_wake_up() was called to wake up the local cpu",
+	  "%11u", true, ttwu_count, v16);
+CPU_FIELD(__u64, rq_cpu_time, "total runtime by tasks on this processor (in jiffies)",
+	  "%11llu", false, rq_cpu_time, v16);
+CPU_FIELD(__u64, run_delay, "total waittime by tasks on this processor (in jiffies)",
+	  "%11llu", true, rq_cpu_time, v16);
+CPU_FIELD(__u64, pcount, "total timeslices run on this cpu",
+	  "%11llu", false, pcount, v16);
+#endif /* CPU_FIELD */
+
+#ifdef DOMAIN_FIELD
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category busy> ");
+#endif
+DOMAIN_FIELD(__u32, busy_lb_count,
+	     "load_balance() count on cpu busy", "%11u", true, v16);
+DOMAIN_FIELD(__u32, busy_lb_balanced,
+	     "load_balance() found balanced on cpu busy", "%11u", true, v16);
+DOMAIN_FIELD(__u32, busy_lb_failed,
+	     "load_balance() move task failed on cpu busy", "%11u", true, v16);
+DOMAIN_FIELD(__u32, busy_lb_imbalance,
+	     "imbalance sum on cpu busy", "%11u", false, v16);
+DOMAIN_FIELD(__u32, busy_lb_gained,
+	     "pull_task() count on cpu busy", "%11u", false, v16);
+DOMAIN_FIELD(__u32, busy_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu busy", "%11u", false, v16);
+DOMAIN_FIELD(__u32, busy_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu busy", "%11u", true, v16);
+DOMAIN_FIELD(__u32, busy_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu busy", "%11u", true, v16);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(busy_lb_success_count, "load_balance() success count on cpu busy", "%11u",
+		  busy_lb_count, busy_lb_balanced, busy_lb_failed, v16);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(busy_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu busy)", "%11.2Lf",
+		  busy_lb_count, busy_lb_balanced, busy_lb_failed, busy_lb_gained, v16);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category idle> ");
+#endif
+DOMAIN_FIELD(__u32, idle_lb_count,
+	     "load_balance() count on cpu idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, idle_lb_balanced,
+	     "load_balance() found balanced on cpu idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, idle_lb_failed,
+	     "load_balance() move task failed on cpu idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, idle_lb_imbalance,
+	     "imbalance sum on cpu idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, idle_lb_gained,
+	     "pull_task() count on cpu idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, idle_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, idle_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, idle_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu idle", "%11u", true, v16);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(idle_lb_success_count, "load_balance() success count on cpu idle", "%11u",
+		  idle_lb_count, idle_lb_balanced, idle_lb_failed, v16);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(idle_lb_avg_pulled,
+		  "avg task pulled per successful lb attempt (cpu idle)", "%11.2Lf",
+		  idle_lb_count, idle_lb_balanced, idle_lb_failed, idle_lb_gained, v16);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category newidle> ");
+#endif
+DOMAIN_FIELD(__u32, newidle_lb_count,
+	     "load_balance() count on cpu newly idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, newidle_lb_balanced,
+	     "load_balance() found balanced on cpu newly idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, newidle_lb_failed,
+	     "load_balance() move task failed on cpu newly idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, newidle_lb_imbalance,
+	     "imbalance sum on cpu newly idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, newidle_lb_gained,
+	     "pull_task() count on cpu newly idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, newidle_lb_hot_gained,
+	     "pull_task() when target task was cache-hot on cpu newly idle", "%11u", false, v16);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyq,
+	     "load_balance() failed to find busier queue on cpu newly idle", "%11u", true, v16);
+DOMAIN_FIELD(__u32, newidle_lb_nobusyg,
+	     "load_balance() failed to find busier group on cpu newly idle", "%11u", true, v16);
+#ifdef DERIVED_CNT_FIELD
+DERIVED_CNT_FIELD(newidle_lb_success_count,
+		  "load_balance() success count on cpu newly idle", "%11u",
+		  newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, v16);
+#endif
+#ifdef DERIVED_AVG_FIELD
+DERIVED_AVG_FIELD(newidle_lb_avg_count,
+		  "avg task pulled per successful lb attempt (cpu newly idle)", "%11.2Lf",
+		  newidle_lb_count, newidle_lb_balanced, newidle_lb_failed, newidle_lb_gained, v16);
+#endif
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category active_load_balance()> ");
+#endif
+DOMAIN_FIELD(__u32, alb_count,
+	     "active_load_balance() count", "%11u", false, v16);
+DOMAIN_FIELD(__u32, alb_failed,
+	     "active_load_balance() move task failed", "%11u", false, v16);
+DOMAIN_FIELD(__u32, alb_pushed,
+	     "active_load_balance() successfully moved a task", "%11u", false, v16);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_exec()> ");
+#endif
+DOMAIN_FIELD(__u32, sbe_count,
+	     "sbe_count is not used", "%11u", false, v16);
+DOMAIN_FIELD(__u32, sbe_balanced,
+	     "sbe_balanced is not used", "%11u", false, v16);
+DOMAIN_FIELD(__u32, sbe_pushed,
+	     "sbe_pushed is not used", "%11u", false, v16);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Category sched_balance_fork()> ");
+#endif
+DOMAIN_FIELD(__u32, sbf_count,
+	     "sbf_count is not used", "%11u", false, v16);
+DOMAIN_FIELD(__u32, sbf_balanced,
+	     "sbf_balanced is not used", "%11u", false, v16);
+DOMAIN_FIELD(__u32, sbf_pushed,
+	     "sbf_pushed is not used", "%11u", false, v16);
+#ifdef DOMAIN_CATEGORY
+DOMAIN_CATEGORY(" <Wakeup Info> ");
+#endif
+DOMAIN_FIELD(__u32, ttwu_wake_remote,
+	     "try_to_wake_up() awoke a task that last ran on a diff cpu", "%11u", false, v16);
+DOMAIN_FIELD(__u32, ttwu_move_affine,
+	     "try_to_wake_up() moved task because cache-cold on own cpu", "%11u", false, v16);
+DOMAIN_FIELD(__u32, ttwu_move_balance,
+	     "try_to_wake_up() started passive balancing", "%11u", false, v16);
+#endif /* DOMAIN_FIELD */