cacheinfo: calculate size of per-CPU data cache slice

This can be used to estimate the size of the data cache slice that can be
used by one CPU under ideal circumstances. Both DATA caches and UNIFIED
caches are used in calculation. So, the users need to consider the impact
of the code cache usage.

Because the cache inclusive/non-inclusive information isn't available now,
we just use the size of the per-CPU slice of LLC to make the result more
predictable across architectures. This may be improved when more cache
information is available in the future.

A brute-force algorithm to iterate all online CPUs is used to avoid to
allocate an extra cpumask, especially in offline callback.

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: "Huang, Ying" <[e-mail]>
Acked-by: Mel Gorman <[e-mail]>
Cc: Sudeep Holla <[e-mail]>
Cc: Vlastimil Babka <[e-mail]>
Cc: David Hildenbrand <[e-mail]>
Cc: Johannes Weiner <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Pavel Tatashin <[e-mail]>
Cc: Matthew Wilcox <[e-mail]>
Cc: Christoph Lameter <[e-mail]>
Cc: Arjan van de Ven <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

drivers/base/cacheinfo.c

···
 	return rc;
 }
 
+/*
+ * Calculate the size of the per-CPU data cache slice.  This can be
+ * used to estimate the size of the data cache slice that can be used
+ * by one CPU under ideal circumstances.  UNIFIED caches are counted
+ * in addition to DATA caches.  So, please consider code cache usage
+ * when use the result.
+ *
+ * Because the cache inclusive/non-inclusive information isn't
+ * available, we just use the size of the per-CPU slice of LLC to make
+ * the result more predictable across architectures.
+ */
+static void update_per_cpu_data_slice_size_cpu(unsigned int cpu)
+{
+	struct cpu_cacheinfo *ci;
+	struct cacheinfo *llc;
+	unsigned int nr_shared;
+
+	if (!last_level_cache_is_valid(cpu))
+		return;
+
+	ci = ci_cacheinfo(cpu);
+	llc = per_cpu_cacheinfo_idx(cpu, cache_leaves(cpu) - 1);
+
+	if (llc->type != CACHE_TYPE_DATA && llc->type != CACHE_TYPE_UNIFIED)
+		return;
+
+	nr_shared = cpumask_weight(&llc->shared_cpu_map);
+	if (nr_shared)
+		ci->per_cpu_data_slice_size = llc->size / nr_shared;
+}
+
+static void update_per_cpu_data_slice_size(bool cpu_online, unsigned int cpu)
+{
+	unsigned int icpu;
+
+	for_each_online_cpu(icpu) {
+		if (!cpu_online && icpu == cpu)
+			continue;
+		update_per_cpu_data_slice_size_cpu(icpu);
+	}
+}
+
 static int cacheinfo_cpu_online(unsigned int cpu)
 {
 	int rc = detect_cache_attributes(cpu);
···
 		return rc;
 	rc = cache_add_dev(cpu);
 	if (rc)
-		free_cache_attributes(cpu);
+		goto err;
+	update_per_cpu_data_slice_size(true, cpu);
+	return 0;
+err:
+	free_cache_attributes(cpu);
 	return rc;
 }
 
···
 		cpu_cache_sysfs_exit(cpu);
 
 	free_cache_attributes(cpu);
+	update_per_cpu_data_slice_size(false, cpu);
 	return 0;
 }
 

include/linux/cacheinfo.h

···
 
 struct cpu_cacheinfo {
 	struct cacheinfo *info_list;
+	unsigned int per_cpu_data_slice_size;
 	unsigned int num_levels;
 	unsigned int num_leaves;
 	bool cpu_map_populated;