Merge branch 'acpi-numa'

* acpi-numa:
  ACPI / NUMA: Enable ACPI based NUMA on ARM64
  arm64, ACPI, NUMA: NUMA support based on SRAT and SLIT
  ACPI / processor: Add acpi_map_madt_entry()
  ACPI / NUMA: Improve SRAT error detection and add messages
  ACPI / NUMA: Move acpi_numa_memory_affinity_init() to drivers/acpi/numa.c
  ACPI / NUMA: remove unneeded acpi_numa=1
  ACPI / NUMA: move bad_srat() and srat_disabled() to drivers/acpi/numa.c
  x86 / ACPI / NUMA: cleanup acpi_numa_processor_affinity_init()
  arm64, NUMA: Cleanup NUMA disabled messages
  arm64, NUMA: rework numa_add_memblk()
  ACPI / NUMA: move acpi_numa_slit_init() to drivers/acpi/numa.c
  ACPI / NUMA: Move acpi_numa_arch_fixup() to ia64 only
  ACPI / NUMA: remove duplicate NULL check
  ACPI / NUMA: Replace ACPI_DEBUG_PRINT() with pr_debug()
  ACPI / NUMA: Use pr_fmt() instead of printk

arch/arm64/include/asm/acpi.h

@@ -113,4 +113,12 @@ static inline const char *acpi_get_enable_method(int cpu)
 pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
 #endif
 
+#ifdef CONFIG_ACPI_NUMA
+int arm64_acpi_numa_init(void);
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid);
+#else
+static inline int arm64_acpi_numa_init(void) { return -ENOSYS; }
+static inline int acpi_numa_get_nid(unsigned int cpu, u64 hwid) { return NUMA_NO_NODE; }
+#endif /* CONFIG_ACPI_NUMA */
+
 #endif /*_ASM_ACPI_H*/

arch/arm64/include/asm/numa.h

@@ -5,6 +5,8 @@
 
 #ifdef CONFIG_NUMA
 
+#define NR_NODE_MEMBLKS		(MAX_NUMNODES * 2)
+
 /* currently, arm64 implements flat NUMA topology */
 #define parent_node(node)	(node)
 

arch/arm64/kernel/Makefile

@@ -42,6 +42,7 @@ arm64-obj-$(CONFIG_EFI)			+= efi.o efi-entry.stub.o
 arm64-obj-$(CONFIG_PCI)			+= pci.o
 arm64-obj-$(CONFIG_ARMV8_DEPRECATED)	+= armv8_deprecated.o
 arm64-obj-$(CONFIG_ACPI)		+= acpi.o
+arm64-obj-$(CONFIG_ACPI_NUMA)		+= acpi_numa.o
 arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL)	+= acpi_parking_protocol.o
 arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 arm64-obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o

arch/arm64/kernel/acpi_numa.c

@@ -0,0 +1,112 @@
+/*
+ * ACPI 5.1 based NUMA setup for ARM64
+ * Lots of code was borrowed from arch/x86/mm/srat.c
+ *
+ * Copyright 2004 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2013-2016, Linaro Ltd.
+ *		Author: Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs.
+ *
+ * Called from acpi_numa_init while reading the SRAT and SLIT tables.
+ * Assumes all memory regions belonging to a single proximity domain
+ * are in one chunk. Holes between them will be included in the node.
+ */
+
+#define pr_fmt(fmt) "ACPI: NUMA: " fmt
+
+#include <linux/acpi.h>
+#include <linux/bitmap.h>
+#include <linux/bootmem.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/topology.h>
+
+#include <acpi/processor.h>
+#include <asm/numa.h>
+
+static int cpus_in_srat;
+
+struct __node_cpu_hwid {
+	u32 node_id;    /* logical node containing this CPU */
+	u64 cpu_hwid;   /* MPIDR for this CPU */
+};
+
+static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = {
+[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} };
+
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid)
+{
+	int i;
+
+	for (i = 0; i < cpus_in_srat; i++) {
+		if (hwid == early_node_cpu_hwid[i].cpu_hwid)
+			return early_node_cpu_hwid[i].node_id;
+	}
+
+	return NUMA_NO_NODE;
+}
+
+/* Callback for Proximity Domain -> ACPI processor UID mapping */
+void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
+{
+	int pxm, node;
+	phys_cpuid_t mpidr;
+
+	if (srat_disabled())
+		return;
+
+	if (pa->header.length < sizeof(struct acpi_srat_gicc_affinity)) {
+		pr_err("SRAT: Invalid SRAT header length: %d\n",
+			pa->header.length);
+		bad_srat();
+		return;
+	}
+
+	if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
+		return;
+
+	if (cpus_in_srat >= NR_CPUS) {
+		pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n",
+			     NR_CPUS);
+		return;
+	}
+
+	pxm = pa->proximity_domain;
+	node = acpi_map_pxm_to_node(pxm);
+
+	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+		pr_err("SRAT: Too many proximity domains %d\n", pxm);
+		bad_srat();
+		return;
+	}
+
+	mpidr = acpi_map_madt_entry(pa->acpi_processor_uid);
+	if (mpidr == PHYS_CPUID_INVALID) {
+		pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n",
+			pxm, pa->acpi_processor_uid);
+		bad_srat();
+		return;
+	}
+
+	early_node_cpu_hwid[cpus_in_srat].node_id = node;
+	early_node_cpu_hwid[cpus_in_srat].cpu_hwid =  mpidr;
+	node_set(node, numa_nodes_parsed);
+	cpus_in_srat++;
+	pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n",
+		pxm, mpidr, node);
+}
+
+int __init arm64_acpi_numa_init(void)
+{
+	int ret;
+
+	ret = acpi_numa_init();
+	if (ret)
+		return ret;
+
+	return srat_disabled() ? -EINVAL : 0;
+}

arch/arm64/kernel/smp.c

@@ -560,6 +560,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 	 */
 	acpi_set_mailbox_entry(cpu_count, processor);
 
+	early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid));
+
 	cpu_count++;
 }
 

arch/arm64/mm/numa.c

@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/module.h>
@@ -29,15 +30,15 @@ static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
 
 static int numa_distance_cnt;
 static u8 *numa_distance;
-static int numa_off;
+static bool numa_off;
 
 static __init int numa_parse_early_param(char *opt)
 {
 	if (!opt)
 		return -EINVAL;
 	if (!strncmp(opt, "off", 3)) {
 		pr_info("%s\n", "NUMA turned off");
-		numa_off = 1;
+		numa_off = true;
 	}
 	return 0;
 }
@@ -131,25 +132,25 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
  * numa_add_memblk - Set node id to memblk
  * @nid: NUMA node ID of the new memblk
  * @start: Start address of the new memblk
- * @size:  Size of the new memblk
+ * @end:  End address of the new memblk
  *
  * RETURNS:
  * 0 on success, -errno on failure.
  */
-int __init numa_add_memblk(int nid, u64 start, u64 size)
+int __init numa_add_memblk(int nid, u64 start, u64 end)
 {
 	int ret;
 
-	ret = memblock_set_node(start, size, &memblock.memory, nid);
+	ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
 	if (ret < 0) {
 		pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
-			start, (start + size - 1), nid);
+			start, (end - 1), nid);
 		return ret;
 	}
 
 	node_set(nid, numa_nodes_parsed);
 	pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
-			start, (start + size - 1), nid);
+			start, (end - 1), nid);
 	return ret;
 }
 
@@ -362,20 +363,23 @@ static int __init dummy_numa_init(void)
 	int ret;
 	struct memblock_region *mblk;
 
-	pr_info("%s\n", "No NUMA configuration found");
+	if (numa_off)
+		pr_info("NUMA disabled\n"); /* Forced off on command line. */
+	else
+		pr_info("No NUMA configuration found\n");
 	pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
 	       0LLU, PFN_PHYS(max_pfn) - 1);
 
 	for_each_memblock(memory, mblk) {
-		ret = numa_add_memblk(0, mblk->base, mblk->size);
+		ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
 		if (!ret)
 			continue;
 
 		pr_err("NUMA init failed\n");
 		return ret;
 	}
 
-	numa_off = 1;
+	numa_off = true;
 	return 0;
 }
 
@@ -388,7 +392,9 @@ static int __init dummy_numa_init(void)
 void __init arm64_numa_init(void)
 {
 	if (!numa_off) {
-		if (!numa_init(of_numa_init))
+		if (!acpi_disabled && !numa_init(arm64_acpi_numa_init))
+			return;
+		if (acpi_disabled && !numa_init(of_numa_init))
 			return;
 	}
 

arch/ia64/include/asm/acpi.h

@@ -140,6 +140,9 @@ static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus)
 		}
 	}
 }
+
+extern void acpi_numa_fixup(void);
+
 #endif /* CONFIG_ACPI_NUMA */
 
 #endif /*__KERNEL__*/

arch/ia64/kernel/acpi.c

@@ -524,7 +524,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 	return 0;
 }
 
-void __init acpi_numa_arch_fixup(void)
+void __init acpi_numa_fixup(void)
 {
 	int i, j, node_from, node_to;
 

arch/ia64/kernel/setup.c

@@ -552,6 +552,7 @@ setup_arch (char **cmdline_p)
 	early_acpi_boot_init();
 # ifdef CONFIG_ACPI_NUMA
 	acpi_numa_init();
+	acpi_numa_fixup();
 #  ifdef CONFIG_ACPI_HOTPLUG_CPU
 	prefill_possible_map();
 #  endif

arch/x86/include/asm/acpi.h

@@ -145,7 +145,6 @@ static inline void disable_acpi(void) { }
 #define ARCH_HAS_POWER_INIT	1
 
 #ifdef CONFIG_ACPI_NUMA
-extern int acpi_numa;
 extern int x86_acpi_numa_init(void);
 #endif /* CONFIG_ACPI_NUMA */
 

arch/x86/mm/numa.c

@@ -1,4 +1,5 @@
 /* Common code for 32 and 64-bit NUMA */
+#include <linux/acpi.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/string.h>
@@ -15,7 +16,6 @@
 #include <asm/e820.h>
 #include <asm/proto.h>
 #include <asm/dma.h>
-#include <asm/acpi.h>
 #include <asm/amd_nb.h>
 
 #include "numa_internal.h"