1 files changed, 170 insertions, 56 deletions

diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index e45e64993c50..53816dfab645 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -14,9 +14,12 @@
 #include <linux/errno.h>
 #include <linux/acpi.h>
 #include <linux/memblock.h>
+#include <linux/memory.h>
 #include <linux/numa.h>
 #include <linux/nodemask.h>
 #include <linux/topology.h>
+#include <linux/numa_memblks.h>
+#include <linux/string_choices.h>
 
 static nodemask_t nodes_found_map = NODE_MASK_NONE;
 
@@ -50,6 +53,7 @@ int node_to_pxm(int node)
 		return PXM_INVAL;
 	return node_to_pxm_map[node];
 }
+EXPORT_SYMBOL_GPL(node_to_pxm);
 
 static void __acpi_map_pxm_to_node(int pxm, int node)
 {
@@ -80,6 +84,101 @@ int acpi_map_pxm_to_node(int pxm)
 }
 EXPORT_SYMBOL(acpi_map_pxm_to_node);
 
+#ifdef CONFIG_NUMA_EMU
+/*
+ * Take max_nid - 1 fake-numa nodes into account in both
+ * pxm_to_node_map()/node_to_pxm_map[] tables.
+ */
+int __init fix_pxm_node_maps(int max_nid)
+{
+	static int pxm_to_node_map_copy[MAX_PXM_DOMAINS] __initdata
+			= { [0 ... MAX_PXM_DOMAINS - 1] = NUMA_NO_NODE };
+	static int node_to_pxm_map_copy[MAX_NUMNODES] __initdata
+			= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
+	int i, j, index = -1, count = 0;
+	nodemask_t nodes_to_enable;
+
+	if (numa_off)
+		return -1;
+
+	/* no or incomplete node/PXM mapping set, nothing to do */
+	if (srat_disabled())
+		return 0;
+
+	/* find fake nodes PXM mapping */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		if (node_to_pxm_map[i] != PXM_INVAL) {
+			for (j = 0; j <= max_nid; j++) {
+				if ((emu_nid_to_phys[j] == i) &&
+				    WARN(node_to_pxm_map_copy[j] != PXM_INVAL,
+					 "Node %d is already binded to PXM %d\n",
+					 j, node_to_pxm_map_copy[j]))
+					return -1;
+				if (emu_nid_to_phys[j] == i) {
+					node_to_pxm_map_copy[j] =
+						node_to_pxm_map[i];
+					if (j > index)
+						index = j;
+					count++;
+				}
+			}
+		}
+	}
+	if (index == -1) {
+		pr_debug("No node/PXM mapping has been set\n");
+		/* nothing more to be done */
+		return 0;
+	}
+	if (WARN(index != max_nid, "%d max nid  when expected %d\n",
+		      index, max_nid))
+		return -1;
+
+	nodes_clear(nodes_to_enable);
+
+	/* map phys nodes not used for fake nodes */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		if (node_to_pxm_map[i] != PXM_INVAL) {
+			for (j = 0; j <= max_nid; j++)
+				if (emu_nid_to_phys[j] == i)
+					break;
+			/* fake nodes PXM mapping has been done */
+			if (j <= max_nid)
+				continue;
+			/* find first hole */
+			for (j = 0;
+			     j < MAX_NUMNODES &&
+				 node_to_pxm_map_copy[j] != PXM_INVAL;
+			     j++)
+			;
+			if (WARN(j == MAX_NUMNODES,
+			    "Number of nodes exceeds MAX_NUMNODES\n"))
+				return -1;
+			node_to_pxm_map_copy[j] = node_to_pxm_map[i];
+			node_set(j, nodes_to_enable);
+			count++;
+		}
+	}
+
+	/* creating reverse mapping in pxm_to_node_map[] */
+	for (i = 0; i < MAX_NUMNODES; i++)
+		if (node_to_pxm_map_copy[i] != PXM_INVAL &&
+		    pxm_to_node_map_copy[node_to_pxm_map_copy[i]] == NUMA_NO_NODE)
+			pxm_to_node_map_copy[node_to_pxm_map_copy[i]] = i;
+
+	/* overwrite with new mapping */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		node_to_pxm_map[i] = node_to_pxm_map_copy[i];
+		pxm_to_node_map[i] = pxm_to_node_map_copy[i];
+	}
+
+	/* enable other nodes found in PXM for hotplug */
+	nodes_or(numa_nodes_parsed, nodes_to_enable, numa_nodes_parsed);
+
+	pr_debug("found %d total number of nodes\n", count);
+	return 0;
+}
+#endif
+
 static void __init
 acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 {
@@ -91,8 +190,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 			pr_debug("SRAT Processor (id[0x%02x] eid[0x%02x]) in proximity domain %d %s\n",
 				 p->apic_id, p->local_sapic_eid,
 				 p->proximity_domain_lo,
-				 (p->flags & ACPI_SRAT_CPU_ENABLED) ?
-				 "enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_SRAT_CPU_ENABLED));
 		}
 		break;
 
@@ -104,8 +202,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 				 (unsigned long long)p->base_address,
 				 (unsigned long long)p->length,
 				 p->proximity_domain,
-				 (p->flags & ACPI_SRAT_MEM_ENABLED) ?
-				 "enabled" : "disabled",
+				 str_enabled_disabled(p->flags & ACPI_SRAT_MEM_ENABLED),
 				 (p->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ?
 				 " hot-pluggable" : "",
 				 (p->flags & ACPI_SRAT_MEM_NON_VOLATILE) ?
@@ -120,8 +217,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 			pr_debug("SRAT Processor (x2apicid[0x%08x]) in proximity domain %d %s\n",
 				 p->apic_id,
 				 p->proximity_domain,
-				 (p->flags & ACPI_SRAT_CPU_ENABLED) ?
-				 "enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_SRAT_CPU_ENABLED));
 		}
 		break;
 
@@ -132,8 +228,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 			pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n",
 				 p->acpi_processor_uid,
 				 p->proximity_domain,
-				 (p->flags & ACPI_SRAT_GICC_ENABLED) ?
-				 "enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_SRAT_GICC_ENABLED));
 		}
 		break;
 
@@ -151,8 +246,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 				 *(u16 *)(&p->device_handle[0]),
 				 *(u16 *)(&p->device_handle[2]),
 				 p->proximity_domain,
-				 (p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED) ?
-				"enabled" : "disabled");
+				 str_enabled_disabled(p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED));
 		} else {
 			/*
 			 * In this case we can rely on the device having a
@@ -162,11 +256,22 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 				(char *)(&p->device_handle[0]),
 				(char *)(&p->device_handle[8]),
 				p->proximity_domain,
-				(p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED) ?
-				"enabled" : "disabled");
+				str_enabled_disabled(p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED));
 		}
 	}
 	break;
+
+	case ACPI_SRAT_TYPE_RINTC_AFFINITY:
+		{
+			struct acpi_srat_rintc_affinity *p =
+			    (struct acpi_srat_rintc_affinity *)header;
+			pr_debug("SRAT Processor (acpi id[0x%04x]) in proximity domain %d %s\n",
+				 p->acpi_processor_uid,
+				 p->proximity_domain,
+				 str_enabled_disabled(p->flags & ACPI_SRAT_RINTC_ENABLED));
+		}
+		break;
+
 	default:
 		pr_warn("Found unsupported SRAT entry (type = 0x%x)\n",
 			header->type);
@@ -208,16 +313,26 @@ int __init srat_disabled(void)
 	return acpi_numa < 0;
 }
 
-#if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH)
+__weak int __init numa_fill_memblks(u64 start, u64 end)
+{
+	return NUMA_NO_MEMBLK;
+}
+
 /*
  * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
  * I/O localities since SRAT does not list them.  I/O localities are
  * not supported at this point.
  */
-void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
+static int __init acpi_parse_slit(struct acpi_table_header *table)
 {
+	struct acpi_table_slit *slit = (struct acpi_table_slit *)table;
 	int i, j;
 
+	if (!slit_valid(slit)) {
+		pr_info("SLIT table looks invalid. Not used.\n");
+		return -EINVAL;
+	}
+
 	for (i = 0; i < slit->locality_count; i++) {
 		const int from_node = pxm_to_node(i);
 
@@ -234,28 +349,34 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 				slit->entry[slit->locality_count * i + j]);
 		}
 	}
+
+	return 0;
 }
 
-/*
- * Default callback for parsing of the Proximity Domain <-> Memory
- * Area mappings
- */
-int __init
-acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
+static int parsed_numa_memblks __initdata;
+
+static int __init
+acpi_parse_memory_affinity(union acpi_subtable_headers *header,
+			   const unsigned long table_end)
 {
+	struct acpi_srat_mem_affinity *ma;
 	u64 start, end;
 	u32 hotpluggable;
 	int node, pxm;
 
+	ma = (struct acpi_srat_mem_affinity *)header;
+
+	acpi_table_print_srat_entry(&header->common);
+
 	if (srat_disabled())
-		goto out_err;
+		return 0;
 	if (ma->header.length < sizeof(struct acpi_srat_mem_affinity)) {
 		pr_err("SRAT: Unexpected header length: %d\n",
 		       ma->header.length);
 		goto out_err_bad_srat;
 	}
 	if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
-		goto out_err;
+		return 0;
 	hotpluggable = IS_ENABLED(CONFIG_MEMORY_HOTPLUG) &&
 		(ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE);
 
@@ -293,11 +414,15 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 
 	max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
 
+	parsed_numa_memblks++;
+
 	return 0;
+
 out_err_bad_srat:
+	/* Just disable SRAT, but do not fail and ignore errors. */
 	bad_srat();
-out_err:
-	return -EINVAL;
+
+	return 0;
 }
 
 static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
@@ -305,13 +430,23 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 {
 	struct acpi_cedt_cfmws *cfmws;
 	int *fake_pxm = arg;
-	u64 start, end;
+	u64 start, end, align;
 	int node;
+	int err;
 
 	cfmws = (struct acpi_cedt_cfmws *)header;
 	start = cfmws->base_hpa;
 	end = cfmws->base_hpa + cfmws->window_size;
 
+	/* Align memblock size to CFMW regions if possible */
+	align = 1UL << __ffs(start | end);
+	if (align >= SZ_256M) {
+		err = memory_block_advise_max_size(align);
+		if (err)
+			pr_warn("CFMWS: memblock size advise failed (%d)\n", err);
+	} else
+		pr_err("CFMWS: [BIOS BUG] base/size alignment violates spec\n");
+
 	/*
 	 * The SRAT may have already described NUMA details for all,
 	 * or a portion of, this CFMWS HPA range. Extend the memblks
@@ -329,7 +464,7 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 		return -EINVAL;
 	}
 
-	if (numa_add_memblk(node, start, end) < 0) {
+	if (numa_add_reserved_memblk(node, start, end) < 0) {
 		/* CXL driver must handle the NUMA_NO_NODE case */
 		pr_warn("ACPI NUMA: Failed to add memblk for CFMWS node %d [mem %#llx-%#llx]\n",
 			node, start, end);
@@ -340,26 +475,6 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
 	(*fake_pxm)++;
 	return 0;
 }
-#else
-static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
-				   void *arg, const unsigned long table_end)
-{
-	return 0;
-}
-#endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
-
-static int __init acpi_parse_slit(struct acpi_table_header *table)
-{
-	struct acpi_table_slit *slit = (struct acpi_table_slit *)table;
-
-	if (!slit_valid(slit)) {
-		pr_info("SLIT table looks invalid. Not used.\n");
-		return -EINVAL;
-	}
-	acpi_numa_slit_init(slit);
-
-	return 0;
-}
 
 void __init __weak
 acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
@@ -450,21 +565,18 @@ acpi_parse_gi_affinity(union acpi_subtable_headers *header,
 }
 #endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
 
-static int __initdata parsed_numa_memblks;
-
 static int __init
-acpi_parse_memory_affinity(union acpi_subtable_headers * header,
-			   const unsigned long end)
+acpi_parse_rintc_affinity(union acpi_subtable_headers *header,
+			  const unsigned long end)
 {
-	struct acpi_srat_mem_affinity *memory_affinity;
-
-	memory_affinity = (struct acpi_srat_mem_affinity *)header;
+	struct acpi_srat_rintc_affinity *rintc_affinity;
 
+	rintc_affinity = (struct acpi_srat_rintc_affinity *)header;
 	acpi_table_print_srat_entry(&header->common);
 
 	/* let architecture-dependent part to do it */
-	if (!acpi_numa_memory_affinity_init(memory_affinity))
-		parsed_numa_memblks++;
+	acpi_numa_rintc_affinity_init(rintc_affinity);
+
 	return 0;
 }
 
@@ -503,7 +615,7 @@ int __init acpi_numa_init(void)
 
 	/* SRAT: System Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
-		struct acpi_subtable_proc srat_proc[4];
+		struct acpi_subtable_proc srat_proc[5];
 
 		memset(srat_proc, 0, sizeof(srat_proc));
 		srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY;
@@ -514,6 +626,8 @@ int __init acpi_numa_init(void)
 		srat_proc[2].handler = acpi_parse_gicc_affinity;
 		srat_proc[3].id = ACPI_SRAT_TYPE_GENERIC_AFFINITY;
 		srat_proc[3].handler = acpi_parse_gi_affinity;
+		srat_proc[4].id = ACPI_SRAT_TYPE_RINTC_AFFINITY;
+		srat_proc[4].handler = acpi_parse_rintc_affinity;
 
 		acpi_table_parse_entries_array(ACPI_SIG_SRAT,
 					sizeof(struct acpi_table_srat),