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

2 files changed, 144 insertions, 29 deletions

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index e7d6e6657ffa..b1c1dd38ab01 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -736,7 +736,7 @@ void update_siblings_masks(unsigned int cpuid)
 
 	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) {
@@ -825,7 +825,7 @@ __weak int __init parse_acpi_topology(void)
 #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();
@@ -840,6 +840,14 @@ void __init init_cpu_topology(void)
 		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;
+		}
+	}
 }
 
 void store_cpu_topology(unsigned int cpuid)
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index 950b22cdb5f7..418a18acc8f9 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -229,8 +229,71 @@ static int cache_setup_of_node(unsigned int cpu)
 
 	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)
@@ -256,7 +319,7 @@ static int cache_shared_cpu_map_setup(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)
@@ -284,11 +347,13 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
 
 			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 */
@@ -302,7 +367,7 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
 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);
@@ -313,9 +378,14 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 			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;
+				}
+			}
 		}
 	}
 }
@@ -326,10 +396,6 @@ static void free_cache_attributes(unsigned int cpu)
 		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)
@@ -342,29 +408,71 @@ int __weak populate_cache_leaves(unsigned int cpu)
 	return -ENOENT;
 }
 
+static inline
+int allocate_cache_info(int cpu)
+{
+	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
+					 sizeof(struct cacheinfo), GFP_ATOMIC);
+	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 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.
+	/* 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 update_cpu_map;
+		goto populate_leaves;
 
 	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) {
-		cache_leaves(cpu) = 0;
-		return -ENOMEM;
-	}
+	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.
@@ -373,7 +481,6 @@ int detect_cache_attributes(unsigned int cpu)
 	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