perf topology: Add core_wide

It is possible to optimize metrics when all SMT threads (CPUs) on a
core are measuring events in system wide mode. For example, TMA
metrics defines CORE_CLKS for Sandybrdige as:

if SMT is disabled:
  CPU_CLK_UNHALTED.THREAD
if SMT is enabled and recording on all SMT threads:
  CPU_CLK_UNHALTED.THREAD_ANY / 2
if SMT is enabled and not recording on all SMT threads:
  (CPU_CLK_UNHALTED.THREAD/2)*
  (1+CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE/CPU_CLK_UNHALTED.REF_XCLK )

That is two more events are necessary when not gathering counts on all
SMT threads. To distinguish all SMT threads on a core vs system wide
(all CPUs) call the new property core wide.  Add a core wide test that
determines the property from user requested CPUs, the topology and
system wide. System wide is required as other processes running on a
SMT thread will change the counts.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Ahmad Yasin <ahmad.yasin@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Florian Fischer <florian.fischer@muhq.space>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.garry@huawei.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kshipra Bopardikar <kshipra.bopardikar@intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Miaoqian Lin <linmq006@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20220831174926.579643-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/cputopo.c

@@ -172,6 +172,52 @@ bool cpu_topology__smt_on(const struct cpu_topology *topology)
 	return false;
 }
 
+bool cpu_topology__core_wide(const struct cpu_topology *topology,
+			     const char *user_requested_cpu_list)
+{
+	struct perf_cpu_map *user_requested_cpus;
+
+	/*
+	 * If user_requested_cpu_list is empty then all CPUs are recorded and so
+	 * core_wide is true.
+	 */
+	if (!user_requested_cpu_list)
+		return true;
+
+	user_requested_cpus = perf_cpu_map__new(user_requested_cpu_list);
+	/* Check that every user requested CPU is the complete set of SMT threads on a core. */
+	for (u32 i = 0; i < topology->core_cpus_lists; i++) {
+		const char *core_cpu_list = topology->core_cpus_list[i];
+		struct perf_cpu_map *core_cpus = perf_cpu_map__new(core_cpu_list);
+		struct perf_cpu cpu;
+		int idx;
+		bool has_first, first = true;
+
+		perf_cpu_map__for_each_cpu(cpu, idx, core_cpus) {
+			if (first) {
+				has_first = perf_cpu_map__has(user_requested_cpus, cpu);
+				first = false;
+			} else {
+				/*
+				 * If the first core CPU is user requested then
+				 * all subsequent CPUs in the core must be user
+				 * requested too. If the first CPU isn't user
+				 * requested then none of the others must be
+				 * too.
+				 */
+				if (perf_cpu_map__has(user_requested_cpus, cpu) != has_first) {
+					perf_cpu_map__put(core_cpus);
+					perf_cpu_map__put(user_requested_cpus);
+					return false;
+				}
+			}
+		}
+		perf_cpu_map__put(core_cpus);
+	}
+	perf_cpu_map__put(user_requested_cpus);
+	return true;
+}
+
 static bool has_die_topology(void)
 {
 	char filename[MAXPATHLEN];

tools/perf/util/cputopo.h

@@ -60,6 +60,9 @@ struct cpu_topology *cpu_topology__new(void);
 void cpu_topology__delete(struct cpu_topology *tp);
 /* Determine from the core list whether SMT was enabled. */
 bool cpu_topology__smt_on(const struct cpu_topology *topology);
+/* Are the sets of SMT siblings all enabled or all disabled in user_requested_cpus. */
+bool cpu_topology__core_wide(const struct cpu_topology *topology,
+			     const char *user_requested_cpu_list);
 
 struct numa_topology *numa_topology__new(void);
 void numa_topology__delete(struct numa_topology *tp);

tools/perf/util/smt.c

@@ -21,3 +21,17 @@ bool smt_on(const struct cpu_topology *topology)
 	cached = true;
 	return cached_result;
 }
+
+bool core_wide(bool system_wide, const char *user_requested_cpu_list,
+	       const struct cpu_topology *topology)
+{
+	/* If not everything running on a core is being recorded then we can't use core_wide. */
+	if (!system_wide)
+		return false;
+
+	/* Cheap case that SMT is disabled and therefore we're inherently core_wide. */
+	if (!smt_on(topology))
+		return true;
+
+	return cpu_topology__core_wide(topology, user_requested_cpu_list);
+}

tools/perf/util/smt.h

@@ -7,4 +7,11 @@ struct cpu_topology;
 /* Returns true if SMT (aka hyperthreading) is enabled. */
 bool smt_on(const struct cpu_topology *topology);
 
+/*
+ * Returns true when system wide and all SMT threads for a core are in the
+ * user_requested_cpus map.
+ */
+bool core_wide(bool system_wide, const char *user_requested_cpu_list,
+	       const struct cpu_topology *topology);
+
 #endif /* __SMT_H */