Merge tag 'archtopo-cacheinfo-updates-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/sudeep.holla/linux into driver-core-next

Sudeep writes:
"cacheinfo and arch_topology updates for v6.3

The main change is to build the cache topology information for all
the CPUs from the primary CPU. Currently the cacheinfo for secondary CPUs
is created during the early boot on the respective CPU itself. Preemption
and interrupts are disabled at this stage. On PREEMPT_RT kernels, allocating
memory and even parsing the PPTT table for ACPI based systems triggers a:
'BUG: sleeping function called from invalid context'

To prevent this bug, the cacheinfo is now allocated from the primary CPU
when preemption and interrupts are enabled and before booting secondary
CPUs. The cache levels/leaves are computed from DT/ACPI PPTT information
only, without relying on any architecture specific mechanism if done so
early.

The other minor change included here is to handle shared caches at
different levels when not all the CPUs on the system have the same
cache hierarchy."

* tag 'archtopo-cacheinfo-updates-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/sudeep.holla/linux:
cacheinfo: Fix shared_cpu_map to handle shared caches at different levels
arch_topology: Build cacheinfo from primary CPU
ACPI: PPTT: Update acpi_find_last_cache_level() to acpi_get_cache_info()
ACPI: PPTT: Remove acpi_find_cache_levels()
cacheinfo: Check 'cache-unified' property to count cache leaves
cacheinfo: Return error code in init_of_cache_level()
cacheinfo: Use RISC-V's init_cache_level() as generic OF implementation

arch/arm64/kernel/cacheinfo.c

···
 int init_cache_level(unsigned int cpu)
 {
 	unsigned int ctype, level, leaves;
-	int fw_level;
+	int fw_level, ret;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 
 	for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) {
···
 		leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1;
 	}
 
-	if (acpi_disabled)
+	if (acpi_disabled) {
 		fw_level = of_find_last_cache_level(cpu);
-	else
-		fw_level = acpi_find_last_cache_level(cpu);
+	} else {
+		ret = acpi_get_cache_info(cpu, &fw_level, NULL);
+		if (ret < 0)
+			return ret;
+	}
 
 	if (fw_level < 0)
 		return fw_level;

arch/riscv/kernel/cacheinfo.c

···
 	}
 }
 
-int init_cache_level(unsigned int cpu)
-{
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	struct device_node *np = of_cpu_device_node_get(cpu);
-	struct device_node *prev = NULL;
-	int levels = 0, leaves = 0, level;
-
-	if (of_property_read_bool(np, "cache-size"))
-		++leaves;
-	if (of_property_read_bool(np, "i-cache-size"))
-		++leaves;
-	if (of_property_read_bool(np, "d-cache-size"))
-		++leaves;
-	if (leaves > 0)
-		levels = 1;
-
-	prev = np;
-	while ((np = of_find_next_cache_node(np))) {
-		of_node_put(prev);
-		prev = np;
-		if (!of_device_is_compatible(np, "cache"))
-			break;
-		if (of_property_read_u32(np, "cache-level", &level))
-			break;
-		if (level <= levels)
-			break;
-		if (of_property_read_bool(np, "cache-size"))
-			++leaves;
-		if (of_property_read_bool(np, "i-cache-size"))
-			++leaves;
-		if (of_property_read_bool(np, "d-cache-size"))
-			++leaves;
-		levels = level;
-	}
-
-	of_node_put(np);
-	this_cpu_ci->num_levels = levels;
-	this_cpu_ci->num_leaves = leaves;
-
-	return 0;
-}
-
 int populate_cache_leaves(unsigned int cpu)
 {
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);

drivers/acpi/pptt.c

···
  * acpi_pptt_walk_cache() - Attempt to find the requested acpi_pptt_cache
  * @table_hdr: Pointer to the head of the PPTT table
  * @local_level: passed res reflects this cache level
+ * @split_levels: Number of split cache levels (data/instruction).
  * @res: cache resource in the PPTT we want to walk
  * @found: returns a pointer to the requested level if found
  * @level: the requested cache level
···
  */
 static unsigned int acpi_pptt_walk_cache(struct acpi_table_header *table_hdr,
 					 unsigned int local_level,
+					 unsigned int *split_levels,
 					 struct acpi_subtable_header *res,
 					 struct acpi_pptt_cache **found,
 					 unsigned int level, int type)
···
 	while (cache) {
 		local_level++;
 
+		if (!(cache->flags & ACPI_PPTT_CACHE_TYPE_VALID)) {
+			cache = fetch_pptt_cache(table_hdr, cache->next_level_of_cache);
+			continue;
+		}
+
+		if (split_levels &&
+		    (acpi_pptt_match_type(cache->attributes, ACPI_PPTT_CACHE_TYPE_DATA) ||
+		     acpi_pptt_match_type(cache->attributes, ACPI_PPTT_CACHE_TYPE_INSTR)))
+			*split_levels = local_level;
+
 		if (local_level == level &&
-		    cache->flags & ACPI_PPTT_CACHE_TYPE_VALID &&
 		    acpi_pptt_match_type(cache->attributes, type)) {
 			if (*found != NULL && cache != *found)
 				pr_warn("Found duplicate cache level/type unable to determine uniqueness\n");
···
 static struct acpi_pptt_cache *
 acpi_find_cache_level(struct acpi_table_header *table_hdr,
 		      struct acpi_pptt_processor *cpu_node,
-		      unsigned int *starting_level, unsigned int level,
-		      int type)
+		      unsigned int *starting_level, unsigned int *split_levels,
+		      unsigned int level, int type)
 {
 	struct acpi_subtable_header *res;
 	unsigned int number_of_levels = *starting_level;
···
 		resource++;
 
 		local_level = acpi_pptt_walk_cache(table_hdr, *starting_level,
-						   res, &ret, level, type);
+						   split_levels, res, &ret,
+						   level, type);
 		/*
 		 * we are looking for the max depth. Since its potentially
 		 * possible for a given node to have resources with differing
···
 }
 
 /**
- * acpi_count_levels() - Given a PPTT table, and a CPU node, count the caches
+ * acpi_count_levels() - Given a PPTT table, and a CPU node, count the cache
+ * levels and split cache levels (data/instruction).
  * @table_hdr: Pointer to the head of the PPTT table
  * @cpu_node: processor node we wish to count caches for
+ * @levels: Number of levels if success.
+ * @split_levels:	Number of split cache levels (data/instruction) if
+ *			success. Can by NULL.
  *
  * Given a processor node containing a processing unit, walk into it and count
  * how many levels exist solely for it, and then walk up each level until we hit
  * the root node (ignore the package level because it may be possible to have
- * caches that exist across packages). Count the number of cache levels that
- * exist at each level on the way up.
- *
- * Return: Total number of levels found.
+ * caches that exist across packages). Count the number of cache levels and
+ * split cache levels (data/instruction) that exist at each level on the way
+ * up.
  */
-static int acpi_count_levels(struct acpi_table_header *table_hdr,
-			     struct acpi_pptt_processor *cpu_node)
+static void acpi_count_levels(struct acpi_table_header *table_hdr,
+			      struct acpi_pptt_processor *cpu_node,
+			      unsigned int *levels, unsigned int *split_levels)
 {
-	int total_levels = 0;
-
 	do {
-		acpi_find_cache_level(table_hdr, cpu_node, &total_levels, 0, 0);
+		acpi_find_cache_level(table_hdr, cpu_node, levels, split_levels, 0, 0);
 		cpu_node = fetch_pptt_node(table_hdr, cpu_node->parent);
 	} while (cpu_node);
-
-	return total_levels;
 }
 
 /**
···
 	return NULL;
 }
 
-static int acpi_find_cache_levels(struct acpi_table_header *table_hdr,
-				  u32 acpi_cpu_id)
-{
-	int number_of_levels = 0;
-	struct acpi_pptt_processor *cpu;
-
-	cpu = acpi_find_processor_node(table_hdr, acpi_cpu_id);
-	if (cpu)
-		number_of_levels = acpi_count_levels(table_hdr, cpu);
-
-	return number_of_levels;
-}
-
 static u8 acpi_cache_type(enum cache_type type)
 {
 	switch (type) {
···
 
 	while (cpu_node && !found) {
 		found = acpi_find_cache_level(table_hdr, cpu_node,
-					      &total_levels, level, acpi_type);
+					      &total_levels, NULL, level, acpi_type);
 		*node = cpu_node;
 		cpu_node = fetch_pptt_node(table_hdr, cpu_node->parent);
 	}
···
 }
 
 /**
- * acpi_find_last_cache_level() - Determines the number of cache levels for a PE
+ * acpi_get_cache_info() - Determine the number of cache levels and
+ * split cache levels (data/instruction) and for a PE.
  * @cpu: Kernel logical CPU number
+ * @levels: Number of levels if success.
+ * @split_levels:	Number of levels being split (i.e. data/instruction)
+ *			if success. Can by NULL.
  *
  * Given a logical CPU number, returns the number of levels of cache represented
  * in the PPTT. Errors caused by lack of a PPTT table, or otherwise, return 0
  * indicating we didn't find any cache levels.
  *
- * Return: Cache levels visible to this core.
+ * Return: -ENOENT if no PPTT table or no PPTT processor struct found.
+ *	   0 on success.
  */
-int acpi_find_last_cache_level(unsigned int cpu)
+int acpi_get_cache_info(unsigned int cpu, unsigned int *levels,
+			unsigned int *split_levels)
 {
-	u32 acpi_cpu_id;
+	struct acpi_pptt_processor *cpu_node;
 	struct acpi_table_header *table;
-	int number_of_levels = 0;
+	u32 acpi_cpu_id;
+
+	*levels = 0;
+	if (split_levels)
+		*split_levels = 0;
 
 	table = acpi_get_pptt();
 	if (!table)
 		return -ENOENT;
 
-	pr_debug("Cache Setup find last level CPU=%d\n", cpu);
+	pr_debug("Cache Setup: find cache levels for CPU=%d\n", cpu);
 
 	acpi_cpu_id = get_acpi_id_for_cpu(cpu);
-	number_of_levels = acpi_find_cache_levels(table, acpi_cpu_id);
-	pr_debug("Cache Setup find last level level=%d\n", number_of_levels);
+	cpu_node = acpi_find_processor_node(table, acpi_cpu_id);
+	if (!cpu_node)
+		return -ENOENT;
 
-	return number_of_levels;
+	acpi_count_levels(table, cpu_node, levels, split_levels);
+
+	pr_debug("Cache Setup: last_level=%d split_levels=%d\n",
+		 *levels, split_levels ? *split_levels : -1);
+
+	return 0;
 }
 
 /**

drivers/base/arch_topology.c

···
 
 	ret = detect_cache_attributes(cpuid);
 	if (ret && ret != -ENOENT)
-		pr_info("Early cacheinfo failed, ret = %d\n", ret);
+		pr_info("Early cacheinfo allocation failed, ret = %d\n", ret);
 
 	/* update core and thread sibling masks */
 	for_each_online_cpu(cpu) {
···
 #if defined(CONFIG_ARM64) || defined(CONFIG_RISCV)
 void __init init_cpu_topology(void)
 {
-	int ret;
+	int cpu, ret;
 
 	reset_cpu_topology();
 	ret = parse_acpi_topology();
···
 		 */
 		reset_cpu_topology();
 		return;
+	}
+
+	for_each_possible_cpu(cpu) {
+		ret = fetch_cache_info(cpu);
+		if (ret) {
+			pr_err("Early cacheinfo failed, ret = %d\n", ret);
+			break;
+		}
 	}
 }
 

drivers/base/cacheinfo.c

···
 
 	return 0;
 }
+
+static int of_count_cache_leaves(struct device_node *np)
+{
+	unsigned int leaves = 0;
+
+	if (of_property_read_bool(np, "cache-size"))
+		++leaves;
+	if (of_property_read_bool(np, "i-cache-size"))
+		++leaves;
+	if (of_property_read_bool(np, "d-cache-size"))
+		++leaves;
+
+	if (!leaves) {
+		/* The '[i-|d-|]cache-size' property is required, but
+		 * if absent, fallback on the 'cache-unified' property.
+		 */
+		if (of_property_read_bool(np, "cache-unified"))
+			return 1;
+		else
+			return 2;
+	}
+
+	return leaves;
+}
+
+int init_of_cache_level(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct device_node *np = of_cpu_device_node_get(cpu);
+	struct device_node *prev = NULL;
+	unsigned int levels = 0, leaves, level;
+
+	leaves = of_count_cache_leaves(np);
+	if (leaves > 0)
+		levels = 1;
+
+	prev = np;
+	while ((np = of_find_next_cache_node(np))) {
+		of_node_put(prev);
+		prev = np;
+		if (!of_device_is_compatible(np, "cache"))
+			goto err_out;
+		if (of_property_read_u32(np, "cache-level", &level))
+			goto err_out;
+		if (level <= levels)
+			goto err_out;
+
+		leaves += of_count_cache_leaves(np);
+		levels = level;
+	}
+
+	of_node_put(np);
+	this_cpu_ci->num_levels = levels;
+	this_cpu_ci->num_leaves = leaves;
+
+	return 0;
+
+err_out:
+	of_node_put(np);
+	return -EINVAL;
+}
+
 #else
 static inline int cache_setup_of_node(unsigned int cpu) { return 0; }
+int init_of_cache_level(unsigned int cpu) { return 0; }
 #endif
 
 int __weak cache_setup_acpi(unsigned int cpu)
···
 {
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 	struct cacheinfo *this_leaf, *sib_leaf;
-	unsigned int index;
+	unsigned int index, sib_index;
 	int ret = 0;
 
 	if (this_cpu_ci->cpu_map_populated)
···
 
 			if (i == cpu || !sib_cpu_ci->info_list)
 				continue;/* skip if itself or no cacheinfo */
-
-			sib_leaf = per_cpu_cacheinfo_idx(i, index);
-			if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
-				cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
-				cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
+			for (sib_index = 0; sib_index < cache_leaves(i); sib_index++) {
+				sib_leaf = per_cpu_cacheinfo_idx(i, sib_index);
+				if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
+					cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
+					cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
+					break;
+				}
 			}
 		}
 		/* record the maximum cache line size */
···
 static void cache_shared_cpu_map_remove(unsigned int cpu)
 {
 	struct cacheinfo *this_leaf, *sib_leaf;
-	unsigned int sibling, index;
+	unsigned int sibling, index, sib_index;
 
 	for (index = 0; index < cache_leaves(cpu); index++) {
 		this_leaf = per_cpu_cacheinfo_idx(cpu, index);
···
 			if (sibling == cpu || !sib_cpu_ci->info_list)
 				continue;/* skip if itself or no cacheinfo */
 
-			sib_leaf = per_cpu_cacheinfo_idx(sibling, index);
-			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
-			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
+			for (sib_index = 0; sib_index < cache_leaves(sibling); sib_index++) {
+				sib_leaf = per_cpu_cacheinfo_idx(sibling, sib_index);
+				if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
+					cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
+					cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
+					break;
+				}
+			}
 		}
 	}
 }
···
 		return;
 
 	cache_shared_cpu_map_remove(cpu);
-
-	kfree(per_cpu_cacheinfo(cpu));
-	per_cpu_cacheinfo(cpu) = NULL;
-	cache_leaves(cpu) = 0;
 }
 
 int __weak init_cache_level(unsigned int cpu)
···
 	return -ENOENT;
 }
 
-int detect_cache_attributes(unsigned int cpu)
+static inline
+int allocate_cache_info(int cpu)
 {
-	int ret;
-
-	/* Since early detection of the cacheinfo is allowed via this
-	 * function and this also gets called as CPU hotplug callbacks via
-	 * cacheinfo_cpu_online, the initialisation can be skipped and only
-	 * CPU maps can be updated as the CPU online status would be update
-	 * if called via cacheinfo_cpu_online path.
-	 */
-	if (per_cpu_cacheinfo(cpu))
-		goto update_cpu_map;
-
-	if (init_cache_level(cpu) || !cache_leaves(cpu))
-		return -ENOENT;
-
 	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
 					 sizeof(struct cacheinfo), GFP_ATOMIC);
-	if (per_cpu_cacheinfo(cpu) == NULL) {
+	if (!per_cpu_cacheinfo(cpu)) {
 		cache_leaves(cpu) = 0;
 		return -ENOMEM;
 	}
 
+	return 0;
+}
+
+int fetch_cache_info(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci;
+	unsigned int levels, split_levels;
+	int ret;
+
+	if (acpi_disabled) {
+		ret = init_of_cache_level(cpu);
+		if (ret < 0)
+			return ret;
+	} else {
+		ret = acpi_get_cache_info(cpu, &levels, &split_levels);
+		if (ret < 0)
+			return ret;
+
+		this_cpu_ci = get_cpu_cacheinfo(cpu);
+		this_cpu_ci->num_levels = levels;
+		/*
+		 * This assumes that:
+		 * - there cannot be any split caches (data/instruction)
+		 *   above a unified cache
+		 * - data/instruction caches come by pair
+		 */
+		this_cpu_ci->num_leaves = levels + split_levels;
+	}
+	if (!cache_leaves(cpu))
+		return -ENOENT;
+
+	return allocate_cache_info(cpu);
+}
+
+int detect_cache_attributes(unsigned int cpu)
+{
+	int ret;
+
+	/* Since early initialization/allocation of the cacheinfo is allowed
+	 * via fetch_cache_info() and this also gets called as CPU hotplug
+	 * callbacks via cacheinfo_cpu_online, the init/alloc can be skipped
+	 * as it will happen only once (the cacheinfo memory is never freed).
+	 * Just populate the cacheinfo.
+	 */
+	if (per_cpu_cacheinfo(cpu))
+		goto populate_leaves;
+
+	if (init_cache_level(cpu) || !cache_leaves(cpu))
+		return -ENOENT;
+
+	ret = allocate_cache_info(cpu);
+	if (ret)
+		return ret;
+
+populate_leaves:
 	/*
 	 * populate_cache_leaves() may completely setup the cache leaves and
 	 * shared_cpu_map or it may leave it partially setup.
···
 	if (ret)
 		goto free_ci;
 
-update_cpu_map:
 	/*
 	 * For systems using DT for cache hierarchy, fw_token
 	 * and shared_cpu_map will be set up here only if they are

include/linux/cacheinfo.h

···
 
 struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu);
 int init_cache_level(unsigned int cpu);
+int init_of_cache_level(unsigned int cpu);
 int populate_cache_leaves(unsigned int cpu);
 int cache_setup_acpi(unsigned int cpu);
 bool last_level_cache_is_valid(unsigned int cpu);
 bool last_level_cache_is_shared(unsigned int cpu_x, unsigned int cpu_y);
+int fetch_cache_info(unsigned int cpu);
 int detect_cache_attributes(unsigned int cpu);
 #ifndef CONFIG_ACPI_PPTT
 /*
- * acpi_find_last_cache_level is only called on ACPI enabled
+ * acpi_get_cache_info() is only called on ACPI enabled
  * platforms using the PPTT for topology. This means that if
  * the platform supports other firmware configuration methods
  * we need to stub out the call when ACPI is disabled.
  * ACPI enabled platforms not using PPTT won't be making calls
  * to this function so we need not worry about them.
  */
-static inline int acpi_find_last_cache_level(unsigned int cpu)
+static inline
+int acpi_get_cache_info(unsigned int cpu,
+			unsigned int *levels, unsigned int *split_levels)
 {
 	return 0;
 }
 #else
-int acpi_find_last_cache_level(unsigned int cpu);
+int acpi_get_cache_info(unsigned int cpu,
+			unsigned int *levels, unsigned int *split_levels);
 #endif
 
 const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf);