Merge tag 'powerpc-5.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Convert pseries & powernv to use MSI IRQ domains.

 - Rework the pseries CPU numbering so that CPUs that are removed, and
   later re-added, are given a CPU number on the same node as
   previously, when possible.

 - Add support for a new more flexible device-tree format for specifying
   NUMA distances.

 - Convert powerpc to GENERIC_PTDUMP.

 - Retire sbc8548 and sbc8641d board support.

 - Various other small features and fixes.

Thanks to Alexey Kardashevskiy, Aneesh Kumar K.V, Anton Blanchard,
Cédric Le Goater, Christophe Leroy, Emmanuel Gil Peyrot, Fabiano Rosas,
Fangrui Song, Finn Thain, Gautham R.  Shenoy, Hari Bathini, Joel
Stanley, Jordan Niethe, Kajol Jain, Laurent Dufour, Leonardo Bras, Lukas
Bulwahn, Marc Zyngier, Masahiro Yamada, Michal Suchanek, Nathan
Chancellor, Nicholas Piggin, Parth Shah, Paul Gortmaker, Pratik R.
Sampat, Randy Dunlap, Sebastian Andrzej Siewior, Srikar Dronamraju, Wan
Jiabing, Xiongwei Song, and Zheng Yongjun.

* tag 'powerpc-5.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (154 commits)
  powerpc/bug: Cast to unsigned long before passing to inline asm
  powerpc/ptdump: Fix generic ptdump for 64-bit
  KVM: PPC: Fix clearing never mapped TCEs in realmode
  powerpc/pseries/iommu: Rename "direct window" to "dma window"
  powerpc/pseries/iommu: Make use of DDW for indirect mapping
  powerpc/pseries/iommu: Find existing DDW with given property name
  powerpc/pseries/iommu: Update remove_dma_window() to accept property name
  powerpc/pseries/iommu: Reorganize iommu_table_setparms*() with new helper
  powerpc/pseries/iommu: Add ddw_property_create() and refactor enable_ddw()
  powerpc/pseries/iommu: Allow DDW windows starting at 0x00
  powerpc/pseries/iommu: Add ddw_list_new_entry() helper
  powerpc/pseries/iommu: Add iommu_pseries_alloc_table() helper
  powerpc/kernel/iommu: Add new iommu_table_in_use() helper
  powerpc/pseries/iommu: Replace hard-coded page shift
  powerpc/numa: Update cpu_cpu_map on CPU online/offline
  powerpc/numa: Print debug statements only when required
  powerpc/numa: convert printk to pr_xxx
  powerpc/numa: Drop dbg in favour of pr_debug
  powerpc/smp: Enable CACHE domain for shared processor
  powerpc/smp: Update cpu_core_map on all PowerPc systems
  ...

1 files changed, 62 insertions, 62 deletions

diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 6f903e9aa20b..cf1be75b7833 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -120,6 +120,7 @@ struct cache {
 	struct cpumask shared_cpu_map; /* online CPUs using this cache */
 	int type;                      /* split cache disambiguation */
 	int level;                     /* level not explicit in device tree */
+	int group_id;                  /* id of the group of threads that share this cache */
 	struct list_head list;         /* global list of cache objects */
 	struct cache *next_local;      /* next cache of >= level */
 };
@@ -142,22 +143,24 @@ static const char *cache_type_string(const struct cache *cache)
 }
 
 static void cache_init(struct cache *cache, int type, int level,
-		       struct device_node *ofnode)
+		       struct device_node *ofnode, int group_id)
 {
 	cache->type = type;
 	cache->level = level;
 	cache->ofnode = of_node_get(ofnode);
+	cache->group_id = group_id;
 	INIT_LIST_HEAD(&cache->list);
 	list_add(&cache->list, &cache_list);
 }
 
-static struct cache *new_cache(int type, int level, struct device_node *ofnode)
+static struct cache *new_cache(int type, int level,
+			       struct device_node *ofnode, int group_id)
 {
 	struct cache *cache;
 
 	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
 	if (cache)
-		cache_init(cache, type, level, ofnode);
+		cache_init(cache, type, level, ofnode, group_id);
 
 	return cache;
 }
@@ -309,20 +312,24 @@ static struct cache *cache_find_first_sibling(struct cache *cache)
 		return cache;
 
 	list_for_each_entry(iter, &cache_list, list)
-		if (iter->ofnode == cache->ofnode && iter->next_local == cache)
+		if (iter->ofnode == cache->ofnode &&
+		    iter->group_id == cache->group_id &&
+		    iter->next_local == cache)
 			return iter;
 
 	return cache;
 }
 
-/* return the first cache on a local list matching node */
-static struct cache *cache_lookup_by_node(const struct device_node *node)
+/* return the first cache on a local list matching node and thread-group id */
+static struct cache *cache_lookup_by_node_group(const struct device_node *node,
+						int group_id)
 {
 	struct cache *cache = NULL;
 	struct cache *iter;
 
 	list_for_each_entry(iter, &cache_list, list) {
-		if (iter->ofnode != node)
+		if (iter->ofnode != node ||
+		    iter->group_id != group_id)
 			continue;
 		cache = cache_find_first_sibling(iter);
 		break;
@@ -352,14 +359,15 @@ static int cache_is_unified_d(const struct device_node *np)
 		CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED;
 }
 
-static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode_unified(struct device_node *node, int group_id,
+						  int level)
 {
 	pr_debug("creating L%d ucache for %pOFP\n", level, node);
 
-	return new_cache(cache_is_unified_d(node), level, node);
+	return new_cache(cache_is_unified_d(node), level, node, group_id);
 }
 
-static struct cache *cache_do_one_devnode_split(struct device_node *node,
+static struct cache *cache_do_one_devnode_split(struct device_node *node, int group_id,
 						int level)
 {
 	struct cache *dcache, *icache;
@@ -367,8 +375,8 @@ static struct cache *cache_do_one_devnode_split(struct device_node *node,
 	pr_debug("creating L%d dcache and icache for %pOFP\n", level,
 		 node);
 
-	dcache = new_cache(CACHE_TYPE_DATA, level, node);
-	icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node);
+	dcache = new_cache(CACHE_TYPE_DATA, level, node, group_id);
+	icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node, group_id);
 
 	if (!dcache || !icache)
 		goto err;
@@ -382,31 +390,32 @@ err:
 	return NULL;
 }
 
-static struct cache *cache_do_one_devnode(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode(struct device_node *node, int group_id, int level)
 {
 	struct cache *cache;
 
 	if (cache_node_is_unified(node))
-		cache = cache_do_one_devnode_unified(node, level);
+		cache = cache_do_one_devnode_unified(node, group_id, level);
 	else
-		cache = cache_do_one_devnode_split(node, level);
+		cache = cache_do_one_devnode_split(node, group_id, level);
 
 	return cache;
 }
 
 static struct cache *cache_lookup_or_instantiate(struct device_node *node,
+						 int group_id,
 						 int level)
 {
 	struct cache *cache;
 
-	cache = cache_lookup_by_node(node);
+	cache = cache_lookup_by_node_group(node, group_id);
 
 	WARN_ONCE(cache && cache->level != level,
 		  "cache level mismatch on lookup (got %d, expected %d)\n",
 		  cache->level, level);
 
 	if (!cache)
-		cache = cache_do_one_devnode(node, level);
+		cache = cache_do_one_devnode(node, group_id, level);
 
 	return cache;
 }
@@ -443,7 +452,30 @@ static void do_subsidiary_caches_debugcheck(struct cache *cache)
 		  of_node_get_device_type(cache->ofnode));
 }
 
-static void do_subsidiary_caches(struct cache *cache)
+/*
+ * If sub-groups of threads in a core containing @cpu_id share the
+ * L@level-cache (information obtained via "ibm,thread-groups"
+ * device-tree property), then we identify the group by the first
+ * thread-sibling in the group. We define this to be the group-id.
+ *
+ * In the absence of any thread-group information for L@level-cache,
+ * this function returns -1.
+ */
+static int get_group_id(unsigned int cpu_id, int level)
+{
+	if (has_big_cores && level == 1)
+		return cpumask_first(per_cpu(thread_group_l1_cache_map,
+					     cpu_id));
+	else if (thread_group_shares_l2 && level == 2)
+		return cpumask_first(per_cpu(thread_group_l2_cache_map,
+					     cpu_id));
+	else if (thread_group_shares_l3 && level == 3)
+		return cpumask_first(per_cpu(thread_group_l3_cache_map,
+					     cpu_id));
+	return -1;
+}
+
+static void do_subsidiary_caches(struct cache *cache, unsigned int cpu_id)
 {
 	struct device_node *subcache_node;
 	int level = cache->level;
@@ -452,9 +484,11 @@ static void do_subsidiary_caches(struct cache *cache)
 
 	while ((subcache_node = of_find_next_cache_node(cache->ofnode))) {
 		struct cache *subcache;
+		int group_id;
 
 		level++;
-		subcache = cache_lookup_or_instantiate(subcache_node, level);
+		group_id = get_group_id(cpu_id, level);
+		subcache = cache_lookup_or_instantiate(subcache_node, group_id, level);
 		of_node_put(subcache_node);
 		if (!subcache)
 			break;
@@ -468,6 +502,7 @@ static struct cache *cache_chain_instantiate(unsigned int cpu_id)
 {
 	struct device_node *cpu_node;
 	struct cache *cpu_cache = NULL;
+	int group_id;
 
 	pr_debug("creating cache object(s) for CPU %i\n", cpu_id);
 
@@ -476,11 +511,13 @@ static struct cache *cache_chain_instantiate(unsigned int cpu_id)
 	if (!cpu_node)
 		goto out;
 
-	cpu_cache = cache_lookup_or_instantiate(cpu_node, 1);
+	group_id = get_group_id(cpu_id, 1);
+
+	cpu_cache = cache_lookup_or_instantiate(cpu_node, group_id, 1);
 	if (!cpu_cache)
 		goto out;
 
-	do_subsidiary_caches(cpu_cache);
+	do_subsidiary_caches(cpu_cache, cpu_id);
 
 	cache_cpu_set(cpu_cache, cpu_id);
 out:
@@ -641,45 +678,6 @@ static ssize_t level_show(struct kobject *k, struct kobj_attribute *attr, char *
 static struct kobj_attribute cache_level_attr =
 	__ATTR(level, 0444, level_show, NULL);
 
-static unsigned int index_dir_to_cpu(struct cache_index_dir *index)
-{
-	struct kobject *index_dir_kobj = &index->kobj;
-	struct kobject *cache_dir_kobj = index_dir_kobj->parent;
-	struct kobject *cpu_dev_kobj = cache_dir_kobj->parent;
-	struct device *dev = kobj_to_dev(cpu_dev_kobj);
-
-	return dev->id;
-}
-
-/*
- * On big-core systems, each core has two groups of CPUs each of which
- * has its own L1-cache. The thread-siblings which share l1-cache with
- * @cpu can be obtained via cpu_smallcore_mask().
- *
- * On some big-core systems, the L2 cache is shared only between some
- * groups of siblings. This is already parsed and encoded in
- * cpu_l2_cache_mask().
- *
- * TODO: cache_lookup_or_instantiate() needs to be made aware of the
- *       "ibm,thread-groups" property so that cache->shared_cpu_map
- *       reflects the correct siblings on platforms that have this
- *       device-tree property. This helper function is only a stop-gap
- *       solution so that we report the correct siblings to the
- *       userspace via sysfs.
- */
-static const struct cpumask *get_shared_cpu_map(struct cache_index_dir *index, struct cache *cache)
-{
-	if (has_big_cores) {
-		int cpu = index_dir_to_cpu(index);
-		if (cache->level == 1)
-			return cpu_smallcore_mask(cpu);
-		if (cache->level == 2 && thread_group_shares_l2)
-			return cpu_l2_cache_mask(cpu);
-	}
-
-	return &cache->shared_cpu_map;
-}
-
 static ssize_t
 show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bool list)
 {
@@ -690,7 +688,7 @@ show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bo
 	index = kobj_to_cache_index_dir(k);
 	cache = index->cache;
 
-	mask = get_shared_cpu_map(index, cache);
+	mask = &cache->shared_cpu_map;
 
 	return cpumap_print_to_pagebuf(list, buf, mask);
 }
@@ -848,13 +846,15 @@ static struct cache *cache_lookup_by_cpu(unsigned int cpu_id)
 {
 	struct device_node *cpu_node;
 	struct cache *cache;
+	int group_id;
 
 	cpu_node = of_get_cpu_node(cpu_id, NULL);
 	WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id);
 	if (!cpu_node)
 		return NULL;
 
-	cache = cache_lookup_by_node(cpu_node);
+	group_id = get_group_id(cpu_id, 1);
+	cache = cache_lookup_by_node_group(cpu_node, group_id);
 	of_node_put(cpu_node);
 
 	return cache;