Merge branch 'acpi-numa'

* acpi-numa:
  docs: mm: numaperf.rst Add brief description for access class 1.
  node: Add access1 class to represent CPU to memory characteristics
  ACPI: HMAT: Fix handling of changes from ACPI 6.2 to ACPI 6.3
  ACPI: Let ACPI know we support Generic Initiator Affinity Structures
  x86: Support Generic Initiator only proximity domains
  ACPI: Support Generic Initiator only domains
  ACPI / NUMA: Add stub function for pxm_to_node()
  irq-chip/gic-v3-its: Fix crash if ITS is in a proximity domain without processor or memory
  ACPI: Remove side effect of partly creating a node in acpi_get_node()
  ACPI: Rename acpi_map_pxm_to_online_node() to pxm_to_online_node()
  ACPI: Remove side effect of partly creating a node in acpi_map_pxm_to_online_node()
  ACPI: Do not create new NUMA domains from ACPI static tables that are not SRAT
  ACPI: Add out of bounds and numa_off protections to pxm_to_node()

Author: rafaeljw

Documentation/admin-guide/mm/numaperf.rst

@@ -56,6 +56,11 @@ nodes' access characteristics share the same performance relative to other
 linked initiator nodes. Each target within an initiator's access class,
 though, do not necessarily perform the same as each other.
 
+The access class "1" is used to allow differentiation between initiators
+that are CPUs and hence suitable for generic task scheduling, and
+IO initiators such as GPUs and NICs.  Unlike access class 0, only
+nodes containing CPUs are considered.
+
 ================
 NUMA Performance
 ================
@@ -88,6 +93,9 @@ The latency attributes are provided in nanoseconds.
 The values reported here correspond to the rated latency and bandwidth
 for the platform.
 
+Access class 1 takes the same form but only includes values for CPU to
+memory activity.
+
 ==========
 NUMA Cache
 ==========

arch/x86/include/asm/numa.h

@@ -62,12 +62,14 @@ extern void numa_clear_node(int cpu);
 extern void __init init_cpu_to_node(void);
 extern void numa_add_cpu(int cpu);
 extern void numa_remove_cpu(int cpu);
+extern void init_gi_nodes(void);
 #else	/* CONFIG_NUMA */
 static inline void numa_set_node(int cpu, int node)	{ }
 static inline void numa_clear_node(int cpu)		{ }
 static inline void init_cpu_to_node(void)		{ }
 static inline void numa_add_cpu(int cpu)		{ }
 static inline void numa_remove_cpu(int cpu)		{ }
+static inline void init_gi_nodes(void)			{ }
 #endif	/* CONFIG_NUMA */
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS

arch/x86/kernel/setup.c

@@ -1218,6 +1218,7 @@ void __init setup_arch(char **cmdline_p)
 	prefill_possible_map();
 
 	init_cpu_to_node();
+	init_gi_nodes();
 
 	io_apic_init_mappings();
 

arch/x86/mm/numa.c

@@ -747,6 +747,27 @@ static void __init init_memory_less_node(int nid)
 	 */
 }
 
+/*
+ * A node may exist which has one or more Generic Initiators but no CPUs and no
+ * memory.
+ *
+ * This function must be called after init_cpu_to_node(), to ensure that any
+ * memoryless CPU nodes have already been brought online, and before the
+ * node_data[nid] is needed for zone list setup in build_all_zonelists().
+ *
+ * When this function is called, any nodes containing either memory and/or CPUs
+ * will already be online and there is no need to do anything extra, even if
+ * they also contain one or more Generic Initiators.
+ */
+void __init init_gi_nodes(void)
+{
+	int nid;
+
+	for_each_node_state(nid, N_GENERIC_INITIATOR)
+		if (!node_online(nid))
+			init_memory_less_node(nid);
+}
+
 /*
  * Setup early cpu_to_node.
  *

drivers/acpi/arm64/iort.c

@@ -1335,7 +1335,7 @@ static int  __init arm_smmu_v3_set_proximity(struct device *dev,
 
 	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
 	if (smmu->flags & ACPI_IORT_SMMU_V3_PXM_VALID) {
-		int dev_node = acpi_map_pxm_to_node(smmu->pxm);
+		int dev_node = pxm_to_node(smmu->pxm);
 
 		if (dev_node != NUMA_NO_NODE && !node_online(dev_node))
 			return -EINVAL;

drivers/acpi/bus.c

@@ -303,7 +303,11 @@ static void acpi_bus_osc_support(void)
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT;
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PCLPI_SUPPORT;
 
+#ifdef CONFIG_ARM64
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GENERIC_INITIATOR_SUPPORT;
+#endif
 #ifdef CONFIG_X86
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GENERIC_INITIATOR_SUPPORT;
 	if (boot_cpu_has(X86_FEATURE_HWP)) {
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_SUPPORT;
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPCV2_SUPPORT;

drivers/acpi/nfit/core.c

@@ -3006,10 +3006,8 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 	ndr_desc->provider_data = nfit_spa;
 	ndr_desc->attr_groups = acpi_nfit_region_attribute_groups;
 	if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) {
-		ndr_desc->numa_node = acpi_map_pxm_to_online_node(
-						spa->proximity_domain);
-		ndr_desc->target_node = acpi_map_pxm_to_node(
-				spa->proximity_domain);
+		ndr_desc->numa_node = pxm_to_online_node(spa->proximity_domain);
+		ndr_desc->target_node = pxm_to_node(spa->proximity_domain);
 	} else {
 		ndr_desc->numa_node = NUMA_NO_NODE;
 		ndr_desc->target_node = NUMA_NO_NODE;

drivers/acpi/numa/hmat.c

@@ -56,7 +56,7 @@ struct memory_target {
 	unsigned int memory_pxm;
 	unsigned int processor_pxm;
 	struct resource memregions;
-	struct node_hmem_attrs hmem_attrs;
+	struct node_hmem_attrs hmem_attrs[2];
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
 	bool registered;
@@ -65,6 +65,7 @@ struct memory_target {
 struct memory_initiator {
 	struct list_head node;
 	unsigned int processor_pxm;
+	bool has_cpu;
 };
 
 struct memory_locality {
@@ -108,6 +109,7 @@ static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 		return;
 
 	initiator->processor_pxm = cpu_pxm;
+	initiator->has_cpu = node_state(pxm_to_node(cpu_pxm), N_CPU);
 	list_add_tail(&initiator->node, &initiators);
 }
 
@@ -215,28 +217,28 @@ static u32 hmat_normalize(u16 entry, u64 base, u8 type)
 }
 
 static void hmat_update_target_access(struct memory_target *target,
-					     u8 type, u32 value)
+				      u8 type, u32 value, int access)
 {
 	switch (type) {
 	case ACPI_HMAT_ACCESS_LATENCY:
-		target->hmem_attrs.read_latency = value;
-		target->hmem_attrs.write_latency = value;
+		target->hmem_attrs[access].read_latency = value;
+		target->hmem_attrs[access].write_latency = value;
 		break;
 	case ACPI_HMAT_READ_LATENCY:
-		target->hmem_attrs.read_latency = value;
+		target->hmem_attrs[access].read_latency = value;
 		break;
 	case ACPI_HMAT_WRITE_LATENCY:
-		target->hmem_attrs.write_latency = value;
+		target->hmem_attrs[access].write_latency = value;
 		break;
 	case ACPI_HMAT_ACCESS_BANDWIDTH:
-		target->hmem_attrs.read_bandwidth = value;
-		target->hmem_attrs.write_bandwidth = value;
+		target->hmem_attrs[access].read_bandwidth = value;
+		target->hmem_attrs[access].write_bandwidth = value;
 		break;
 	case ACPI_HMAT_READ_BANDWIDTH:
-		target->hmem_attrs.read_bandwidth = value;
+		target->hmem_attrs[access].read_bandwidth = value;
 		break;
 	case ACPI_HMAT_WRITE_BANDWIDTH:
-		target->hmem_attrs.write_bandwidth = value;
+		target->hmem_attrs[access].write_bandwidth = value;
 		break;
 	default:
 		break;
@@ -329,8 +331,12 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 
 			if (mem_hier == ACPI_HMAT_MEMORY) {
 				target = find_mem_target(targs[targ]);
-				if (target && target->processor_pxm == inits[init])
-					hmat_update_target_access(target, type, value);
+				if (target && target->processor_pxm == inits[init]) {
+					hmat_update_target_access(target, type, value, 0);
+					/* If the node has a CPU, update access 1 */
+					if (node_state(pxm_to_node(inits[init]), N_CPU))
+						hmat_update_target_access(target, type, value, 1);
+				}
 			}
 		}
 	}
@@ -424,7 +430,8 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 		pr_info("HMAT: Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->flags, p->processor_PD, p->memory_PD);
 
-	if (p->flags & ACPI_HMAT_MEMORY_PD_VALID && hmat_revision == 1) {
+	if ((hmat_revision == 1 && p->flags & ACPI_HMAT_MEMORY_PD_VALID) ||
+	    hmat_revision > 1) {
 		target = find_mem_target(p->memory_PD);
 		if (!target) {
 			pr_debug("HMAT: Memory Domain missing from SRAT\n");
@@ -566,6 +573,7 @@ static void hmat_register_target_initiators(struct memory_target *target)
 	unsigned int mem_nid, cpu_nid;
 	struct memory_locality *loc = NULL;
 	u32 best = 0;
+	bool access0done = false;
 	int i;
 
 	mem_nid = pxm_to_node(target->memory_pxm);
@@ -577,7 +585,11 @@ static void hmat_register_target_initiators(struct memory_target *target)
 	if (target->processor_pxm != PXM_INVAL) {
 		cpu_nid = pxm_to_node(target->processor_pxm);
 		register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
-		return;
+		access0done = true;
+		if (node_state(cpu_nid, N_CPU)) {
+			register_memory_node_under_compute_node(mem_nid, cpu_nid, 1);
+			return;
+		}
 	}
 
 	if (list_empty(&localities))
@@ -591,6 +603,41 @@ static void hmat_register_target_initiators(struct memory_target *target)
 	 */
 	bitmap_zero(p_nodes, MAX_NUMNODES);
 	list_sort(p_nodes, &initiators, initiator_cmp);
+	if (!access0done) {
+		for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
+			loc = localities_types[i];
+			if (!loc)
+				continue;
+
+			best = 0;
+			list_for_each_entry(initiator, &initiators, node) {
+				u32 value;
+
+				if (!test_bit(initiator->processor_pxm, p_nodes))
+					continue;
+
+				value = hmat_initiator_perf(target, initiator,
+							    loc->hmat_loc);
+				if (hmat_update_best(loc->hmat_loc->data_type, value, &best))
+					bitmap_clear(p_nodes, 0, initiator->processor_pxm);
+				if (value != best)
+					clear_bit(initiator->processor_pxm, p_nodes);
+			}
+			if (best)
+				hmat_update_target_access(target, loc->hmat_loc->data_type,
+							  best, 0);
+		}
+
+		for_each_set_bit(i, p_nodes, MAX_NUMNODES) {
+			cpu_nid = pxm_to_node(i);
+			register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
+		}
+	}
+
+	/* Access 1 ignores Generic Initiators */
+	bitmap_zero(p_nodes, MAX_NUMNODES);
+	list_sort(p_nodes, &initiators, initiator_cmp);
+	best = 0;
 	for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
 		loc = localities_types[i];
 		if (!loc)
@@ -600,6 +647,10 @@ static void hmat_register_target_initiators(struct memory_target *target)
 		list_for_each_entry(initiator, &initiators, node) {
 			u32 value;
 
+			if (!initiator->has_cpu) {
+				clear_bit(initiator->processor_pxm, p_nodes);
+				continue;
+			}
 			if (!test_bit(initiator->processor_pxm, p_nodes))
 				continue;
 
@@ -610,12 +661,11 @@ static void hmat_register_target_initiators(struct memory_target *target)
 				clear_bit(initiator->processor_pxm, p_nodes);
 		}
 		if (best)
-			hmat_update_target_access(target, loc->hmat_loc->data_type, best);
+			hmat_update_target_access(target, loc->hmat_loc->data_type, best, 1);
 	}
-
 	for_each_set_bit(i, p_nodes, MAX_NUMNODES) {
 		cpu_nid = pxm_to_node(i);
-		register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
+		register_memory_node_under_compute_node(mem_nid, cpu_nid, 1);
 	}
 }
 
@@ -628,10 +678,10 @@ static void hmat_register_target_cache(struct memory_target *target)
 		node_add_cache(mem_nid, &tcache->cache_attrs);
 }
 
-static void hmat_register_target_perf(struct memory_target *target)
+static void hmat_register_target_perf(struct memory_target *target, int access)
 {
 	unsigned mem_nid = pxm_to_node(target->memory_pxm);
-	node_set_perf_attrs(mem_nid, &target->hmem_attrs, 0);
+	node_set_perf_attrs(mem_nid, &target->hmem_attrs[access], access);
 }
 
 static void hmat_register_target_device(struct memory_target *target,
@@ -664,9 +714,9 @@ static void hmat_register_target_device(struct memory_target *target,
 		goto out_pdev;
 	}
 
-	pdev->dev.numa_node = acpi_map_pxm_to_online_node(target->memory_pxm);
+	pdev->dev.numa_node = pxm_to_online_node(target->memory_pxm);
 	info = (struct memregion_info) {
-		.target_node = acpi_map_pxm_to_node(target->memory_pxm),
+		.target_node = pxm_to_node(target->memory_pxm),
 	};
 	rc = platform_device_add_data(pdev, &info, sizeof(info));
 	if (rc < 0) {
@@ -733,7 +783,8 @@ static void hmat_register_target(struct memory_target *target)
 	if (!target->registered) {
 		hmat_register_target_initiators(target);
 		hmat_register_target_cache(target);
-		hmat_register_target_perf(target);
+		hmat_register_target_perf(target, 0);
+		hmat_register_target_perf(target, 1);
 		target->registered = true;
 	}
 	mutex_unlock(&target_lock);