UBUNTU: SAUCE: (noup) arm64, numa: Add NUMA support for arm64 platforms.

BugLink: http://bugs.launchpad.net/bugs/1558765

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>
[ dannf: v15 submittal ]
Reference: http://www.spinics.net/lists/arm-kernel/msg489640.htmlSigned-off-by: dann frazier <dann.frazier@canonical.com>
Signed-off-by: Tim Gardner <tim.gardner@canonical.com>

arch/arm64/Kconfig

@@ -71,6 +71,7 @@ config ARM64
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP if NUMA
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -92,6 +93,7 @@ config ARM64
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_CONTEXT_TRACKING
+	select OF_NUMA if NUMA && OF
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -514,6 +516,30 @@ 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

+#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

+#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

@@ -76,6 +76,16 @@ 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>
@@ -377,6 +378,9 @@ 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>
@@ -126,6 +127,7 @@ 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);
 }
 
 /*
@@ -530,6 +532,8 @@ 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

@@ -37,6 +37,7 @@
 
 #include <asm/fixmap.h>
 #include <asm/memory.h>
+#include <asm/numa.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/sizes.h>
@@ -77,6 +78,21 @@ static phys_addr_t 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;
@@ -117,6 +133,8 @@ 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)
 {
@@ -133,10 +151,15 @@ static void arm64_memory_present(void)
 static void 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),
+	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
 
@@ -181,7 +204,6 @@ void __init arm64_memblock_init(void)
 	dma_contiguous_reserve(arm64_dma_phys_limit);
 
 	memblock_allow_resize();
-	memblock_dump_all();
 }
 
 void __init bootmem_init(void)
@@ -193,6 +215,9 @@ 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.
@@ -203,7 +228,6 @@ void __init bootmem_init(void)
 	zone_sizes_init(min, max);
 
 	high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
-	max_pfn = max_low_pfn = max;
 }
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP

arch/arm64/mm/mmu.c

@@ -458,6 +458,7 @@ void __init paging_init_rest(void)
 	void *zero_page = early_alloc(PAGE_SIZE);
 
 	bootmem_init();
+	memblock_dump_all();
 
 	empty_zero_page = virt_to_page(zero_page);
 

arch/arm64/mm/numa.c

+/*
+ * NUMA support, based on the x86 implementation.
+ *
+ * Copyright (C) 2015 Cavium Inc.
+ * Author: Ganapatrao Kulkarni <gkulkarni@cavium.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/of.h>
+
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_data);
+nodemask_t numa_nodes_parsed __initdata;
+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 __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;
+	}
+	return 0;
+}
+early_param("numa", numa_parse_early_param);
+
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+	if (WARN_ON(node >= nr_node_ids))
+		return cpu_none_mask;
+
+	if (WARN_ON(node_to_cpumask_map[node] == NULL))
+		return cpu_online_mask;
+
+	return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+
+#endif
+
+static void map_cpu_to_node(unsigned int cpu, int nid)
+{
+	set_cpu_numa_node(cpu, nid);
+	if (nid >= 0)
+		cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+}
+
+void numa_clear_node(unsigned int cpu)
+{
+	int nid = cpu_to_node(cpu);
+
+	if (nid >= 0)
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]);
+	set_cpu_numa_node(cpu, NUMA_NO_NODE);
+}
+
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: cpumask_of_node() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+static void __init setup_node_to_cpumask_map(void)
+{
+	unsigned int cpu;
+	int node;
+
+	/* setup nr_node_ids if not done yet */
+	if (nr_node_ids == MAX_NUMNODES)
+		setup_nr_node_ids();
+
+	/* allocate and clear the mapping */
+	for (node = 0; node < nr_node_ids; node++) {
+		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+		cpumask_clear(node_to_cpumask_map[node]);
+	}
+
+	for_each_possible_cpu(cpu)
+		set_cpu_numa_node(cpu, NUMA_NO_NODE);
+
+	/* cpumask_of_node() will now work */
+	pr_debug("NUMA: Node to cpumask map for %d nodes\n", nr_node_ids);
+}
+
+/*
+ *  Set the cpu to node and mem mapping
+ */
+void numa_store_cpu_info(unsigned int cpu)
+{
+	map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]);
+}
+
+void __init early_map_cpu_to_node(unsigned int cpu, int nid)
+{
+	/* fallback to node 0 */
+	if (nid < 0 || nid >= MAX_NUMNODES)
+		nid = 0;
+
+	cpu_to_node_map[cpu] = 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
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_add_memblk(int nid, u64 start, u64 size)
+{
+	int ret;
+
+	ret = memblock_set_node(start, size, &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);
+		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);
+	return ret;
+}
+
+/**
+ * Initialize NODE_DATA for a node on the local memory
+ */
+static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
+{
+	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
+	u64 nd_pa;
+	void *nd;
+	int tnid;
+
+	pr_info("NUMA: Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+			nid, start_pfn << PAGE_SHIFT,
+			(end_pfn << PAGE_SHIFT) - 1);
+
+	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+	nd = __va(nd_pa);
+
+	/* report and initialize */
+	pr_info("NUMA: NODE_DATA [mem %#010Lx-%#010Lx]\n",
+		nd_pa, nd_pa + nd_size - 1);
+	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+	if (tnid != nid)
+		pr_info("NUMA: NODE_DATA(%d) on node %d\n", nid, tnid);
+
+	node_data[nid] = nd;
+	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+	NODE_DATA(nid)->node_id = nid;
+	NODE_DATA(nid)->node_start_pfn = start_pfn;
+	NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
+}
+
+/**
+ * numa_free_distance
+ *
+ * The current table is freed.
+ */
+void __init numa_free_distance(void)
+{
+	size_t size;
+
+	if (!numa_distance)
+		return;
+
+	size = numa_distance_cnt * numa_distance_cnt *
+		sizeof(numa_distance[0]);
+
+	memblock_free(__pa(numa_distance), size);
+	numa_distance_cnt = 0;
+	numa_distance = NULL;
+}
+
+/**
+ *
+ * Create a new NUMA distance table.
+ *
+ */
+static int __init numa_alloc_distance(void)
+{
+	size_t size;
+	u64 phys;
+	int i, j;
+
+	size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
+	phys = memblock_find_in_range(0, PFN_PHYS(max_pfn),
+				      size, PAGE_SIZE);
+	if (WARN_ON(!phys))
+		return -ENOMEM;
+
+	memblock_reserve(phys, size);
+
+	numa_distance = __va(phys);
+	numa_distance_cnt = nr_node_ids;
+
+	/* fill with the default distances */
+	for (i = 0; i < numa_distance_cnt; i++)
+		for (j = 0; j < numa_distance_cnt; j++)
+			numa_distance[i * numa_distance_cnt + j] = i == j ?
+				LOCAL_DISTANCE : REMOTE_DISTANCE;
+
+	pr_debug("NUMA: Initialized distance table, cnt=%d\n",
+			numa_distance_cnt);
+
+	return 0;
+}
+
+/**
+ * numa_set_distance - Set inter node NUMA distance from node to node.
+ * @from: the 'from' node to set distance
+ * @to: the 'to'  node to set distance
+ * @distance: NUMA distance
+ *
+ * Set the distance from node @from to @to to @distance.
+ * If distance table doesn't exist, a warning is printed.
+ *
+ * If @from or @to is higher than the highest known node or lower than zero
+ * or @distance doesn't make sense, the call is ignored.
+ *
+ */
+void __init numa_set_distance(int from, int to, int distance)
+{
+	if (!numa_distance) {
+		pr_warn_once("NUMA: Warning: distance table not allocated yet\n");
+		return;
+	}
+
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
+			from < 0 || to < 0) {
+		pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+			    from, to, distance);
+		return;
+	}
+
+	if ((u8)distance != distance ||
+	    (from == to && distance != LOCAL_DISTANCE)) {
+		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+			     from, to, distance);
+		return;
+	}
+
+	numa_distance[from * numa_distance_cnt + to] = distance;
+}
+
+/**
+ * Return NUMA distance @from to @to
+ */
+int __node_distance(int from, int to)
+{
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt)
+		return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
+	return numa_distance[from * numa_distance_cnt + to];
+}
+EXPORT_SYMBOL(__node_distance);
+
+static int __init numa_register_nodes(void)
+{
+	int nid;
+	struct memblock_region *mblk;
+
+	/* Check that valid nid is set to memblks */
+	for_each_memblock(memory, mblk)
+		if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) {
+			pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+				mblk->nid, mblk->base,
+				mblk->base + mblk->size - 1);
+			return -EINVAL;
+		}
+
+	/* Finally register nodes. */
+	for_each_node_mask(nid, numa_nodes_parsed) {
+		unsigned long start_pfn, end_pfn;
+
+		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+		setup_node_data(nid, start_pfn, end_pfn);
+		node_set_online(nid);
+	}
+
+	/* Setup online nodes to actual nodes*/
+	node_possible_map = numa_nodes_parsed;
+
+	return 0;
+}
+
+static int __init numa_init(int (*init_func)(void))
+{
+	int ret;
+
+	nodes_clear(numa_nodes_parsed);
+	nodes_clear(node_possible_map);
+	nodes_clear(node_online_map);
+	numa_free_distance();
+
+	ret = numa_alloc_distance();
+	if (ret < 0)
+		return ret;
+
+	ret = init_func();
+	if (ret < 0)
+		return ret;
+
+	if (nodes_empty(numa_nodes_parsed))
+		return -EINVAL;
+
+	ret = numa_register_nodes();
+	if (ret < 0)
+		return ret;
+
+	setup_node_to_cpumask_map();
+
+	/* init boot processor */
+	cpu_to_node_map[0] = 0;
+	map_cpu_to_node(0, 0);
+
+	return 0;
+}
+
+/**
+ * dummy_numa_init - Fallback dummy NUMA init
+ *
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
+ *
+ * Must online at least one node (node 0) and add memory blocks that cover all
+ * allowed memory. It is unlikely that this function fails.
+ */
+static int __init dummy_numa_init(void)
+{
+	int ret;
+	struct memblock_region *mblk;
+
+	pr_info("%s\n", "No NUMA configuration found");
+	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);
+		if (!ret)
+			continue;
+
+		pr_err("NUMA init failed\n");
+		return ret;
+	}
+
+	numa_off = 1;
+	return 0;
+}
+
+/**
+ * arm64_numa_init - Initialize NUMA
+ *
+ * Try each configured NUMA initialization method until one succeeds.  The
+ * last fallback is dummy single node config encomapssing whole memory.
+ */
+void __init arm64_numa_init(void)
+{
+	if (!numa_off) {
+		if (!numa_init(of_numa_init))
+			return;
+	}
+
+	numa_init(dummy_numa_init);
+}