arm64, numa: Add NUMA support for arm64 platforms.

Attempt to get the memory and CPU NUMA node via of_numa.  If that
fails, default the dummy NUMA node and map all memory and CPUs to node
0.

Tested-by: Shannon Zhao <shannon.zhao@linaro.org>
Reviewed-by: Robert Richter <rrichter@cavium.com>
Signed-off-by: Ganapatrao Kulkarni <gkulkarni@caviumnetworks.com>
Signed-off-by: David Daney <david.daney@cavium.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

Author: Ganapatrao Kulkarni

arch/arm64/Kconfig

@@ -76,6 +76,7 @@ config ARM64
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP if NUMA
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -98,6 +99,7 @@ config ARM64
 	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_ARM_SMCCC
+	select OF_NUMA if NUMA && OF
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -546,6 +548,30 @@ config HOTPLUG_CPU
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
 
+# Common NUMA Features
+config NUMA
+	bool "Numa Memory Allocation and Scheduler Support"
+	depends on SMP
+	help
+	  Enable NUMA (Non Uniform Memory Access) support.
+
+	  The kernel will try to allocate memory used by a CPU on the
+	  local memory of the CPU and add some more
+	  NUMA awareness to the kernel.
+
+config NODES_SHIFT
+	int "Maximum NUMA Nodes (as a power of 2)"
+	range 1 10
+	default "2"
+	depends on NEED_MULTIPLE_NODES
+	help
+	  Specify the maximum number of NUMA Nodes available on the target
+	  system.  Increases memory reserved to accommodate various tables.
+
+config USE_PERCPU_NUMA_NODE_ID
+	def_bool y
+	depends on NUMA
+
 source kernel/Kconfig.preempt
 source kernel/Kconfig.hz
 

arch/arm64/include/asm/mmzone.h

@@ -0,0 +1,12 @@
+#ifndef __ASM_MMZONE_H
+#define __ASM_MMZONE_H
+
+#ifdef CONFIG_NUMA
+
+#include <asm/numa.h>
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid)		(node_data[(nid)])
+
+#endif /* CONFIG_NUMA */
+#endif /* __ASM_MMZONE_H */

arch/arm64/include/asm/numa.h

@@ -0,0 +1,45 @@
+#ifndef __ASM_NUMA_H
+#define __ASM_NUMA_H
+
+#include <asm/topology.h>
+
+#ifdef CONFIG_NUMA
+
+/* currently, arm64 implements flat NUMA topology */
+#define parent_node(node)	(node)
+
+int __node_distance(int from, int to);
+#define node_distance(a, b) __node_distance(a, b)
+
+extern nodemask_t numa_nodes_parsed __initdata;
+
+/* Mappings between node number and cpus on that node. */
+extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+void numa_clear_node(unsigned int cpu);
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+const struct cpumask *cpumask_of_node(int node);
+#else
+/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const struct cpumask *cpumask_of_node(int node)
+{
+	return node_to_cpumask_map[node];
+}
+#endif
+
+void __init arm64_numa_init(void);
+int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+void __init numa_set_distance(int from, int to, int distance);
+void __init numa_free_distance(void);
+void __init early_map_cpu_to_node(unsigned int cpu, int nid);
+void numa_store_cpu_info(unsigned int cpu);
+
+#else	/* CONFIG_NUMA */
+
+static inline void numa_store_cpu_info(unsigned int cpu) { }
+static inline void arm64_numa_init(void) { }
+static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
+
+#endif	/* CONFIG_NUMA */
+
+#endif	/* __ASM_NUMA_H */

arch/arm64/include/asm/topology.h

@@ -22,6 +22,16 @@ void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
 
+#ifdef CONFIG_NUMA
+
+struct pci_bus;
+int pcibus_to_node(struct pci_bus *bus);
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
+				 cpu_all_mask :				\
+				 cpumask_of_node(pcibus_to_node(bus)))
+
+#endif /* CONFIG_NUMA */
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */

arch/arm64/kernel/pci.c

@@ -74,6 +74,16 @@ int raw_pci_write(unsigned int domain, unsigned int bus,
 	return -ENXIO;
 }
 
+#ifdef CONFIG_NUMA
+
+int pcibus_to_node(struct pci_bus *bus)
+{
+	return dev_to_node(&bus->dev);
+}
+EXPORT_SYMBOL(pcibus_to_node);
+
+#endif
+
 #ifdef CONFIG_ACPI
 /* Root bridge scanning */
 struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)

arch/arm64/kernel/setup.c

@@ -53,6 +53,7 @@
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/kasan.h>
+#include <asm/numa.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -319,6 +320,9 @@ static int __init topology_init(void)
 {
 	int i;
 
+	for_each_online_node(i)
+		register_one_node(i);
+
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
 		cpu->hotpluggable = 1;

arch/arm64/kernel/smp.c

@@ -45,6 +45,7 @@
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
 #include <asm/mmu_context.h>
+#include <asm/numa.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
@@ -203,6 +204,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 static void smp_store_cpu_info(unsigned int cpuid)
 {
 	store_cpu_topology(cpuid);
+	numa_store_cpu_info(cpuid);
 }
 
 /*
@@ -633,6 +635,8 @@ static void __init of_parse_and_init_cpus(void)
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
 		cpu_logical_map(cpu_count) = hwid;
+
+		early_map_cpu_to_node(cpu_count, of_node_to_nid(dn));
 next:
 		cpu_count++;
 	}

arch/arm64/mm/Makefile

@@ -4,6 +4,7 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
+obj-$(CONFIG_NUMA)		+= numa.o
 
 obj-$(CONFIG_KASAN)		+= kasan_init.o
 KASAN_SANITIZE_kasan_init.o	:= n

arch/arm64/mm/init.c

@@ -40,6 +40,7 @@
 #include <asm/kasan.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/memory.h>
+#include <asm/numa.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/sizes.h>
@@ -86,6 +87,21 @@ static phys_addr_t __init max_zone_dma_phys(void)
 	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
 }
 
+#ifdef CONFIG_NUMA
+
+static void __init zone_sizes_init(unsigned long min, unsigned long max)
+{
+	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
+
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		max_zone_pfns[ZONE_DMA] = PFN_DOWN(max_zone_dma_phys());
+	max_zone_pfns[ZONE_NORMAL] = max;
+
+	free_area_init_nodes(max_zone_pfns);
+}
+
+#else
+
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
@@ -126,6 +142,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	free_area_init_node(0, zone_size, min, zhole_size);
 }
 
+#endif /* CONFIG_NUMA */
+
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
@@ -142,10 +160,15 @@ static void __init arm64_memory_present(void)
 static void __init arm64_memory_present(void)
 {
 	struct memblock_region *reg;
+	int nid = 0;
 
-	for_each_memblock(memory, reg)
-		memory_present(0, memblock_region_memory_base_pfn(reg),
-			       memblock_region_memory_end_pfn(reg));
+	for_each_memblock(memory, reg) {
+#ifdef CONFIG_NUMA
+		nid = reg->nid;
+#endif
+		memory_present(nid, memblock_region_memory_base_pfn(reg),
+				memblock_region_memory_end_pfn(reg));
+	}
 }
 #endif
 
@@ -278,7 +301,6 @@ void __init arm64_memblock_init(void)
 	dma_contiguous_reserve(arm64_dma_phys_limit);
 
 	memblock_allow_resize();
-	memblock_dump_all();
 }
 
 void __init bootmem_init(void)
@@ -290,6 +312,9 @@ void __init bootmem_init(void)
 
 	early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
 
+	max_pfn = max_low_pfn = max;
+
+	arm64_numa_init();
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(), so must be
 	 * done after the fixed reservations.
@@ -300,7 +325,7 @@ void __init bootmem_init(void)
 	zone_sizes_init(min, max);
 
 	high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
-	max_pfn = max_low_pfn = max;
+	memblock_dump_all();
 }
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP