[PATCH v5 1/4] arm64, numa: adding numa support for arm64 platforms.

Ganapatrao Kulkarni gpkulkarni at gmail.com
Thu Sep 3 02:52:02 PDT 2015


Hi Catalin/Will,

On Fri, Aug 14, 2015 at 10:09 PM, Ganapatrao Kulkarni
<gkulkarni at caviumnetworks.com> wrote:
> Adding numa support for arm64 based platforms.
> This patch adds by default the dummy numa node and
> maps all memory and cpus to node 0.
> using this patch, numa can be simulated on single node arm64 platforms.
>
> Signed-off-by: Ganapatrao Kulkarni <gkulkarni at caviumnetworks.com>
> ---
>  arch/arm64/Kconfig              |  26 ++
>  arch/arm64/include/asm/mmzone.h |  32 +++
>  arch/arm64/include/asm/numa.h   |  42 +++
>  arch/arm64/kernel/setup.c       |   9 +
>  arch/arm64/kernel/smp.c         |   2 +
>  arch/arm64/mm/Makefile          |   1 +
>  arch/arm64/mm/init.c            |  34 ++-
>  arch/arm64/mm/numa.c            | 550 ++++++++++++++++++++++++++++++++++++++++
>  8 files changed, 690 insertions(+), 6 deletions(-)
>  create mode 100644 arch/arm64/include/asm/mmzone.h
>  create mode 100644 arch/arm64/include/asm/numa.h
>  create mode 100644 arch/arm64/mm/numa.c
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 43a0c26..fa37a5d 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -72,6 +72,7 @@ config ARM64
>         select HAVE_PERF_USER_STACK_DUMP
>         select HAVE_RCU_TABLE_FREE
>         select HAVE_SYSCALL_TRACEPOINTS
> +       select HAVE_MEMBLOCK_NODE_MAP if NUMA
>         select IRQ_DOMAIN
>         select IRQ_FORCED_THREADING
>         select MODULES_USE_ELF_RELA
> @@ -559,6 +560,31 @@ 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 controller 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
>
>  config UP_LATE_INIT
> diff --git a/arch/arm64/include/asm/mmzone.h b/arch/arm64/include/asm/mmzone.h
> new file mode 100644
> index 0000000..d27ee66
> --- /dev/null
> +++ b/arch/arm64/include/asm/mmzone.h
> @@ -0,0 +1,32 @@
> +#ifndef __ASM_ARM64_MMZONE_H_
> +#define __ASM_ARM64_MMZONE_H_
> +
> +#ifdef CONFIG_NUMA
> +
> +#include <linux/mmdebug.h>
> +#include <asm/smp.h>
> +#include <linux/types.h>
> +#include <asm/numa.h>
> +
> +extern struct pglist_data *node_data[];
> +
> +#define NODE_DATA(nid)         (node_data[nid])
> +
> +
> +struct numa_memblk {
> +       u64                     start;
> +       u64                     end;
> +       int                     nid;
> +};
> +
> +struct numa_meminfo {
> +       int                     nr_blks;
> +       struct numa_memblk      blk[NR_NODE_MEMBLKS];
> +};
> +
> +void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi);
> +int __init numa_cleanup_meminfo(struct numa_meminfo *mi);
> +void __init numa_reset_distance(void);
> +
> +#endif /* CONFIG_NUMA */
> +#endif /* __ASM_ARM64_MMZONE_H_ */
> diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
> new file mode 100644
> index 0000000..59b834e
> --- /dev/null
> +++ b/arch/arm64/include/asm/numa.h
> @@ -0,0 +1,42 @@
> +#ifndef _ASM_NUMA_H
> +#define _ASM_NUMA_H
> +
> +#include <linux/nodemask.h>
> +#include <asm/topology.h>
> +
> +#ifdef CONFIG_NUMA
> +
> +#define NR_NODE_MEMBLKS                (MAX_NUMNODES * 2)
> +#define ZONE_ALIGN (1UL << (MAX_ORDER + PAGE_SHIFT))
> +
> +/* currently, arm64 implements flat NUMA topology */
> +#define parent_node(node)      (node)
> +
> +/* dummy definitions for pci functions */
> +#define pcibus_to_node(node)   0
> +#define cpumask_of_pcibus(bus) 0
> +
> +struct __node_cpu_hwid {
> +       u32 node_id;    /* logical node containing this CPU */
> +       u64 cpu_hwid;   /* MPIDR for this CPU */
> +};
> +
> +extern struct __node_cpu_hwid node_cpu_hwid[NR_CPUS];
> +extern nodemask_t numa_nodes_parsed __initdata;
> +
> +const struct cpumask *cpumask_of_node(int node);
> +/* Mappings between node number and cpus on that node. */
> +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
> +
> +void __init arm64_numa_init(void);
> +int __init numa_add_memblk(u32 nodeid, u64 start, u64 end);
> +void numa_store_cpu_info(int cpu);
> +void __init build_cpu_to_node_map(void);
> +void __init numa_set_distance(int from, int to, int distance);
> +#else  /* CONFIG_NUMA */
> +static inline void numa_store_cpu_info(int cpu)                { }
> +static inline void arm64_numa_init(void)               { }
> +static inline void build_cpu_to_node_map(void) { }
> +static inline void numa_set_distance(int from, int to, int distance) { }
> +#endif /* CONFIG_NUMA */
> +#endif /* _ASM_NUMA_H */
> diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
> index 4d4d7ce..6e101eb 100644
> --- a/arch/arm64/kernel/setup.c
> +++ b/arch/arm64/kernel/setup.c
> @@ -65,6 +65,7 @@
>  #include <asm/efi.h>
>  #include <asm/virt.h>
>  #include <asm/xen/hypervisor.h>
> +#include <asm/numa.h>
>
>  unsigned long elf_hwcap __read_mostly;
>  EXPORT_SYMBOL_GPL(elf_hwcap);
> @@ -439,6 +440,9 @@ 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;
> @@ -511,7 +515,12 @@ static int c_show(struct seq_file *m, void *v)
>                  * "processor".  Give glibc what it expects.
>                  */
>  #ifdef CONFIG_SMP
> +       if (IS_ENABLED(CONFIG_NUMA)) {
> +               seq_printf(m, "processor\t: %d", i);
> +               seq_printf(m, " [nid: %d]\n", cpu_to_node(i));
> +       } else {
>                 seq_printf(m, "processor\t: %d\n", i);
> +       }
>  #endif
>
>                 /*
> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
> index 50fb469..ae3e02c 100644
> --- a/arch/arm64/kernel/smp.c
> +++ b/arch/arm64/kernel/smp.c
> @@ -52,6 +52,7 @@
>  #include <asm/sections.h>
>  #include <asm/tlbflush.h>
>  #include <asm/ptrace.h>
> +#include <asm/numa.h>
>
>  #define CREATE_TRACE_POINTS
>  #include <trace/events/ipi.h>
> @@ -124,6 +125,7 @@ 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);
>  }
>
>  /*
> diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
> index 773d37a..bb92d41 100644
> --- a/arch/arm64/mm/Makefile
> +++ b/arch/arm64/mm/Makefile
> @@ -4,3 +4,4 @@ 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
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index 54da32e..cab384b 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -42,6 +42,7 @@
>  #include <asm/sizes.h>
>  #include <asm/tlb.h>
>  #include <asm/alternative.h>
> +#include <asm/numa.h>
>
>  #include "mm.h"
>
> @@ -77,6 +78,20 @@ 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];
> +
> +       memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
> +       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;
> @@ -115,6 +130,7 @@ 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)
> @@ -132,10 +148,15 @@ 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),
> -                              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
>
> @@ -200,6 +221,10 @@ void __init bootmem_init(void)
>         min = PFN_UP(memblock_start_of_DRAM());
>         max = PFN_DOWN(memblock_end_of_DRAM());
>
> +       high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
> +       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.
> @@ -208,9 +233,6 @@ void __init bootmem_init(void)
>
>         sparse_init();
>         zone_sizes_init(min, max);
> -
> -       high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
> -       max_pfn = max_low_pfn = max;
>  }
>
>  #ifndef CONFIG_SPARSEMEM_VMEMMAP
> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
> new file mode 100644
> index 0000000..2be83de
> --- /dev/null
> +++ b/arch/arm64/mm/numa.c
> @@ -0,0 +1,550 @@
> +/*
> + * NUMA support, based on the x86 implementation.
> + *
> + * Copyright (C) 2015 Cavium Inc.
> + * Author: Ganapatrao Kulkarni <gkulkarni at 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/kernel.h>
> +#include <linux/mm.h>
> +#include <linux/string.h>
> +#include <linux/init.h>
> +#include <linux/bootmem.h>
> +#include <linux/memblock.h>
> +#include <linux/ctype.h>
> +#include <linux/module.h>
> +#include <linux/nodemask.h>
> +#include <linux/sched.h>
> +#include <linux/topology.h>
> +#include <linux/mmzone.h>
> +
> +#include <asm/smp_plat.h>
> +
> +int __initdata numa_off;
> +nodemask_t numa_nodes_parsed __initdata;
> +static int numa_distance_cnt;
> +static u8 *numa_distance;
> +static u8 dummy_numa_enabled;
> +
> +struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
> +EXPORT_SYMBOL(node_data);
> +
> +struct __node_cpu_hwid node_cpu_hwid[NR_CPUS];
> +static struct numa_meminfo numa_meminfo;
> +
> +static __init int numa_setup(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_setup);
> +
> +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
> +EXPORT_SYMBOL(node_to_cpumask_map);
> +
> +int cpu_to_node_map[NR_CPUS];
> +EXPORT_SYMBOL(cpu_to_node_map);
> +
> +/*
> + * Returns a pointer to the bitmask of CPUs on Node 'node'.
> + */
> +const struct cpumask *cpumask_of_node(int node)
> +{
> +       if (node >= nr_node_ids) {
> +               pr_warn("cpumask_of_node(%d): node > nr_node_ids(%d)\n",
> +                       node, nr_node_ids);
> +               dump_stack();
> +               return cpu_none_mask;
> +       }
> +       if (node_to_cpumask_map[node] == NULL) {
> +               pr_warn("cpumask_of_node(%d): no node_to_cpumask_map!\n",
> +                       node);
> +               dump_stack();
> +               return cpu_online_mask;
> +       }
> +       return node_to_cpumask_map[node];
> +}
> +EXPORT_SYMBOL(cpumask_of_node);
> +
> +void numa_clear_node(int cpu)
> +{
> +       set_cpu_numa_node(cpu, NUMA_NO_NODE);
> +}
> +
> +void map_cpu_to_node(int cpu, int nid)
> +{
> +       if (nid < 0) { /* just initialize by zero */
> +               cpu_to_node_map[cpu] = 0;
> +               return;
> +       }
> +
> +       cpu_to_node_map[cpu] = nid;
> +       cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
> +       set_numa_node(nid);
> +}
> +
> +/**
> + * build_cpu_to_node_map - setup cpu to node and node to cpumask arrays
> + *
> + * Build cpu to node mapping and initialize the per node cpu masks using
> + * info from the node_cpuid array handed to us by ACPI or DT.
> + */
> +void __init build_cpu_to_node_map(void)
> +{
> +       int cpu, i, node;
> +
> +       for (node = 0; node < MAX_NUMNODES; node++)
> +               cpumask_clear(node_to_cpumask_map[node]);
> +
> +       for_each_possible_cpu(cpu) {
> +               node = NUMA_NO_NODE;
> +               for_each_possible_cpu(i) {
> +                       if (cpu_logical_map(cpu) == node_cpu_hwid[i].cpu_hwid) {
> +                               node = node_cpu_hwid[i].node_id;
> +                               break;
> +                       }
> +               }
> +               map_cpu_to_node(cpu, 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.)
> + */
> +void __init setup_node_to_cpumask_map(void)
> +{
> +       unsigned int node;
> +
> +       /* setup nr_node_ids if not done yet */
> +       if (nr_node_ids == MAX_NUMNODES)
> +               setup_nr_node_ids();
> +
> +       /* allocate the map */
> +       for (node = 0; node < nr_node_ids; node++)
> +               alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
> +
> +       /* cpumask_of_node() will now work */
> +       pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
> +}
> +
> +/*
> + *  Set the cpu to node and mem mapping
> + */
> +void numa_store_cpu_info(int cpu)
> +{
> +       if (dummy_numa_enabled) {
> +               /* set to default */
> +               node_cpu_hwid[cpu].node_id  =  0;
> +               node_cpu_hwid[cpu].cpu_hwid = cpu_logical_map(cpu);
> +       }
> +       map_cpu_to_node(cpu, node_cpu_hwid[cpu].node_id);
> +}
> +
> +/**
> + * numa_add_memblk_to - Add one numa_memblk to a numa_meminfo
> + */
> +
> +static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
> +                                    struct numa_meminfo *mi)
> +{
> +       /* ignore zero length blks */
> +       if (start == end)
> +               return 0;
> +
> +       /* whine about and ignore invalid blks */
> +       if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
> +               pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
> +                               nid, start, end - 1);
> +               return 0;
> +       }
> +
> +       if (mi->nr_blks >= NR_NODE_MEMBLKS) {
> +               pr_err("NUMA: too many memblk ranges\n");
> +               return -EINVAL;
> +       }
> +
> +       pr_info("NUMA: Adding memblock %d [0x%llx - 0x%llx] on node %d\n",
> +                       mi->nr_blks, start, end, nid);
> +       mi->blk[mi->nr_blks].start = start;
> +       mi->blk[mi->nr_blks].end = end;
> +       mi->blk[mi->nr_blks].nid = nid;
> +       mi->nr_blks++;
> +       return 0;
> +}
> +
> +/**
> + * numa_add_memblk - Add one numa_memblk to numa_meminfo
> + * @nid: NUMA node ID of the new memblk
> + * @start: Start address of the new memblk
> + * @end: End address of the new memblk
> + *
> + * Add a new memblk to the default numa_meminfo.
> + *
> + * RETURNS:
> + * 0 on success, -errno on failure.
> + */
> +#define MAX_PHYS_ADDR  ((phys_addr_t)~0)
> +
> +int __init numa_add_memblk(u32 nid, u64 base, u64 end)
> +{
> +       const u64 phys_offset = __pa(PAGE_OFFSET);
> +
> +       base &= PAGE_MASK;
> +       end &= PAGE_MASK;
> +
> +       if (base > MAX_PHYS_ADDR) {
> +               pr_warn("NUMA: Ignoring memory block 0x%llx - 0x%llx\n",
> +                               base, base + end);
> +               return -ENOMEM;
> +       }
> +
> +       if (base + end > MAX_PHYS_ADDR) {
> +               pr_info("NUMA: Ignoring memory range 0x%lx - 0x%llx\n",
> +                               ULONG_MAX, base + end);
> +               end = MAX_PHYS_ADDR - base;
> +       }
> +
> +       if (base + end < phys_offset) {
> +               pr_warn("NUMA: Ignoring memory block 0x%llx - 0x%llx\n",
> +                          base, base + end);
> +               return -ENOMEM;
> +       }
> +       if (base < phys_offset) {
> +               pr_info("NUMA: Ignoring memory range 0x%llx - 0x%llx\n",
> +                          base, phys_offset);
> +               end -= phys_offset - base;
> +               base = phys_offset;
> +       }
> +
> +       return numa_add_memblk_to(nid, base, base + end, &numa_meminfo);
> +}
> +EXPORT_SYMBOL(numa_add_memblk);
> +
> +/* Initialize NODE_DATA for a node on the local memory */
> +static void __init setup_node_data(int nid, u64 start, u64 end)
> +{
> +       const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
> +       u64 nd_pa;
> +       void *nd;
> +       int tnid;
> +
> +       start = roundup(start, ZONE_ALIGN);
> +
> +       pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
> +              nid, start, end - 1);
> +
> +       /*
> +        * Allocate node data.  Try node-local memory and then any node.
> +        */
> +       nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
> +       if (!nd_pa) {
> +               nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES,
> +                                             MEMBLOCK_ALLOC_ACCESSIBLE);
> +               if (!nd_pa) {
> +                       pr_err("Cannot find %zu bytes in node %d\n",
> +                              nd_size, nid);
> +                       return;
> +               }
> +       }
> +       nd = __va(nd_pa);
> +
> +       /* report and initialize */
> +       pr_info("  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("    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 >> PAGE_SHIFT;
> +       NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT;
> +
> +       node_set_online(nid);
> +}
> +
> +/*
> + * Set nodes, which have memory in @mi, in *@nodemask.
> + */
> +static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
> +                                             const struct numa_meminfo *mi)
> +{
> +       int i;
> +
> +       for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
> +               if (mi->blk[i].start != mi->blk[i].end &&
> +                   mi->blk[i].nid != NUMA_NO_NODE)
> +                       node_set(mi->blk[i].nid, *nodemask);
> +}
> +
> +/*
> + * Sanity check to catch more bad NUMA configurations (they are amazingly
> + * common).  Make sure the nodes cover all memory.
> + */
> +static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
> +{
> +       u64 numaram, totalram;
> +       int i;
> +
> +       numaram = 0;
> +       for (i = 0; i < mi->nr_blks; i++) {
> +               u64 s = mi->blk[i].start >> PAGE_SHIFT;
> +               u64 e = mi->blk[i].end >> PAGE_SHIFT;
> +
> +               numaram += e - s;
> +               numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
> +               if ((s64)numaram < 0)
> +                       numaram = 0;
> +       }
> +
> +       totalram = max_pfn - absent_pages_in_range(0, max_pfn);
> +
> +       /* We seem to lose 3 pages somewhere. Allow 1M of slack. */
> +       if ((s64)(totalram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
> +               pr_err("NUMA: nodes only cover %lluMB of your %lluMB Total RAM. Not used.\n",
> +                      (numaram << PAGE_SHIFT) >> 20,
> +                      (totalram << PAGE_SHIFT) >> 20);
> +               return false;
> +       }
> +       return true;
> +}
> +
> +/**
> + * numa_reset_distance - Reset NUMA distance table
> + *
> + * The current table is freed.  The next numa_set_distance() call will
> + * create a new one.
> + */
> +void __init numa_reset_distance(void)
> +{
> +       size_t size = numa_distance_cnt * numa_distance_cnt *
> +               sizeof(numa_distance[0]);
> +
> +       /* numa_distance could be 1LU marking allocation failure, test cnt */
> +       if (numa_distance_cnt)
> +               memblock_free(__pa(numa_distance), size);
> +       numa_distance_cnt = 0;
> +       numa_distance = NULL;   /* enable table creation */
> +}
> +
> +static int __init numa_alloc_distance(void)
> +{
> +       nodemask_t nodes_parsed;
> +       size_t size;
> +       int i, j, cnt = 0;
> +       u64 phys;
> +
> +       /* size the new table and allocate it */
> +       nodes_parsed = numa_nodes_parsed;
> +       numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo);
> +
> +       for_each_node_mask(i, nodes_parsed)
> +               cnt = i;
> +       cnt++;
> +       size = cnt * cnt * sizeof(numa_distance[0]);
> +
> +       phys = memblock_find_in_range(0, PFN_PHYS(max_pfn),
> +                                     size, PAGE_SIZE);
> +       if (!phys) {
> +               pr_warn("NUMA: Warning: can't allocate distance table!\n");
> +               /* don't retry until explicitly reset */
> +               numa_distance = (void *)1LU;
> +               return -ENOMEM;
> +       }
> +       memblock_reserve(phys, size);
> +
> +       numa_distance = __va(phys);
> +       numa_distance_cnt = cnt;
> +
> +       /* fill with the default distances */
> +       for (i = 0; i < cnt; i++)
> +               for (j = 0; j < cnt; j++)
> +                       numa_distance[i * cnt + j] = i == j ?
> +                               LOCAL_DISTANCE : REMOTE_DISTANCE;
> +       pr_debug("NUMA: Initialized distance table, cnt=%d\n", cnt);
> +
> +       return 0;
> +}
> +
> +/**
> + * numa_set_distance - Set NUMA distance from one NUMA to another
> + * @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, one which is large enough to accommodate all the currently
> + * known nodes will be created.
> + *
> + * If such table cannot be allocated, a warning is printed and further
> + * calls are ignored until the distance table is reset with
> + * numa_reset_distance().
> + *
> + * If @from or @to is higher than the highest known node or lower than zero
> + * at the time of table creation or @distance doesn't make sense, the call
> + * is ignored.
> + * This is to allow simplification of specific NUMA config implementations.
> + */
> +void __init numa_set_distance(int from, int to, int distance)
> +{
> +       if (!numa_distance && numa_alloc_distance() < 0)
> +               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;
> +}
> +EXPORT_SYMBOL(numa_set_distance);
> +
> +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_memblks(struct numa_meminfo *mi)
> +{
> +       unsigned long uninitialized_var(pfn_align);
> +       int i, nid;
> +
> +       /* Account for nodes with cpus and no memory */
> +       node_possible_map = numa_nodes_parsed;
> +       numa_nodemask_from_meminfo(&node_possible_map, mi);
> +       if (WARN_ON(nodes_empty(node_possible_map)))
> +               return -EINVAL;
> +
> +       for (i = 0; i < mi->nr_blks; i++) {
> +               struct numa_memblk *mb = &mi->blk[i];
> +
> +               memblock_set_node(mb->start, mb->end - mb->start,
> +                                 &memblock.memory, mb->nid);
> +       }
> +
> +       /*
> +        * If sections array is gonna be used for pfn -> nid mapping, check
> +        * whether its granularity is fine enough.
> +        */
> +#ifdef NODE_NOT_IN_PAGE_FLAGS
> +       pfn_align = node_map_pfn_alignment();
> +       if (pfn_align && pfn_align < PAGES_PER_SECTION) {
> +               pr_warn("Node alignment %lluMB < min %lluMB, rejecting NUMA config\n",
> +                      PFN_PHYS(pfn_align) >> 20,
> +                      PFN_PHYS(PAGES_PER_SECTION) >> 20);
> +               return -EINVAL;
> +       }
> +#endif
> +       if (!numa_meminfo_cover_memory(mi))
> +               return -EINVAL;
> +
> +       /* Finally register nodes. */
> +       for_each_node_mask(nid, node_possible_map) {
> +               u64 start = PFN_PHYS(max_pfn);
> +               u64 end = 0;
> +
> +               for (i = 0; i < mi->nr_blks; i++) {
> +                       if (nid != mi->blk[i].nid)
> +                               continue;
> +                       start = min(mi->blk[i].start, start);
> +                       end = max(mi->blk[i].end, end);
> +               }
> +
> +               if (start < end)
> +                       setup_node_data(nid, start, end);
> +       }
> +
> +       /* Dump memblock with node info and return. */
> +       memblock_dump_all();
> +       return 0;
> +}
> +
> +static int __init numa_init(int (*init_func)(void))
> +{
> +       int ret, i;
> +
> +       nodes_clear(numa_nodes_parsed);
> +       nodes_clear(node_possible_map);
> +       nodes_clear(node_online_map);
> +
> +       ret = init_func();
> +       if (ret < 0)
> +               return ret;
> +
> +       ret = numa_register_memblks(&numa_meminfo);
> +       if (ret < 0)
> +               return ret;
> +
> +       for (i = 0; i < nr_cpu_ids; i++)
> +               numa_clear_node(i);
> +
> +       setup_node_to_cpumask_map();
> +       build_cpu_to_node_map();
> +       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 and add memory blocks that cover all
> + * allowed memory.  This function must not fail.
> + */
> +static int __init dummy_numa_init(void)
> +{
> +       pr_info("%s\n", "No NUMA configuration found");
> +       pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
> +              0LLU, PFN_PHYS(max_pfn) - 1);
> +       node_set(0, numa_nodes_parsed);
> +       numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
> +       dummy_numa_enabled = 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 and
> + * never fails.
> + */
> +void __init arm64_numa_init(void)
> +{
> +       numa_init(dummy_numa_init);
> +}
> --
> 1.8.1.4
>
can you please review this patch.

thanks
Ganapat



More information about the linux-arm-kernel mailing list