#include <linux/acpi.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/mmzone.h>
#include <linux/ctype.h>
#include <linux/nodemask.h>
#include <linux/sched.h>
#include <linux/topology.h>
#include <asm/e820/api.h>
#include <asm/proto.h>
#include <asm/dma.h>
#include <asm/amd_nb.h>
#include "numa_internal.h"
int numa_off;
nodemask_t numa_nodes_parsed __initdata;
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);
static struct numa_meminfo numa_meminfo __initdata_or_meminfo;
static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo;
static int numa_distance_cnt;
static u8 *numa_distance;
static __init int numa_setup(char *opt)
{
if (!opt)
return -EINVAL;
if (!strncmp(opt, "off", 3))
numa_off = 1;
if (!strncmp(opt, "fake=", 5))
return numa_emu_cmdline(opt + 5);
if (!strncmp(opt, "noacpi", 6))
disable_srat();
if (!strncmp(opt, "nohmat", 6))
disable_hmat();
return 0;
}
early_param("numa", numa_setup);
s16 __apicid_to_node[MAX_LOCAL_APIC] = {
[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};
int numa_cpu_node(int cpu)
{
int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
if (apicid != BAD_APICID)
return __apicid_to_node[apicid];
return NUMA_NO_NODE;
}
cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
EXPORT_SYMBOL(node_to_cpumask_map);
DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
void numa_set_node(int cpu, int node)
{
int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
if (cpu_to_node_map) {
cpu_to_node_map[cpu] = node;
return;
}
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
dump_stack();
return;
}
#endif
per_cpu(x86_cpu_to_node_map, cpu) = node;
set_cpu_numa_node(cpu, node);
}
void numa_clear_node(int cpu)
{
numa_set_node(cpu, NUMA_NO_NODE);
}
void __init setup_node_to_cpumask_map(void)
{
unsigned int node;
if (nr_node_ids == MAX_NUMNODES)
setup_nr_node_ids();
for (node = 0; node < nr_node_ids; node++)
alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
}
static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
struct numa_meminfo *mi)
{
if (start == end)
return 0;
if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
nid, start, end - 1);
return 0;
}
if (mi->nr_blks >= NR_NODE_MEMBLKS) {
pr_err("too many memblk ranges\n");
return -EINVAL;
}
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;
}
void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
{
mi->nr_blks--;
memmove(&mi->blk[idx], &mi->blk[idx + 1],
(mi->nr_blks - idx) * sizeof(mi->blk[0]));
}
static void __init numa_move_tail_memblk(struct numa_meminfo *dst, int idx,
struct numa_meminfo *src)
{
dst->blk[dst->nr_blks++] = src->blk[idx];
numa_remove_memblk_from(idx, src);
}
int __init numa_add_memblk(int nid, u64 start, u64 end)
{
return numa_add_memblk_to(nid, start, end, &numa_meminfo);
}
static void __init alloc_node_data(int nid)
{
const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
u64 nd_pa;
void *nd;
int tnid;
nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
if (!nd_pa) {
pr_err("Cannot find %zu bytes in any node (initial node: %d)\n",
nd_size, nid);
return;
}
nd = __va(nd_pa);
printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid,
nd_pa, nd_pa + nd_size - 1);
tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
if (tnid != nid)
printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid);
node_data[nid] = nd;
memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
node_set_online(nid);
}
int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
{
const u64 low = 0;
const u64 high = PFN_PHYS(max_pfn);
int i, j, k;
for (i = 0; i < mi->nr_blks; i++) {
struct numa_memblk *bi = &mi->blk[i];
if (!memblock_overlaps_region(&memblock.memory,
bi->start, bi->end - bi->start)) {
numa_move_tail_memblk(&numa_reserved_meminfo, i--, mi);
continue;
}
bi->start = max(bi->start, low);
if (bi->end > high) {
numa_add_memblk_to(bi->nid, high, bi->end,
&numa_reserved_meminfo);
bi->end = high;
}
if (bi->start >= bi->end)
numa_remove_memblk_from(i--, mi);
}
for (i = 0; i < mi->nr_blks; i++) {
struct numa_memblk *bi = &mi->blk[i];
for (j = i + 1; j < mi->nr_blks; j++) {
struct numa_memblk *bj = &mi->blk[j];
u64 start, end;
if (bi->end > bj->start && bi->start < bj->end) {
if (bi->nid != bj->nid) {
pr_err("node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n",
bi->nid, bi->start, bi->end - 1,
bj->nid, bj->start, bj->end - 1);
return -EINVAL;
}
pr_warn("Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n",
bi->nid, bi->start, bi->end - 1,
bj->start, bj->end - 1);
}
if (bi->nid != bj->nid)
continue;
start = min(bi->start, bj->start);
end = max(bi->end, bj->end);
for (k = 0; k < mi->nr_blks; k++) {
struct numa_memblk *bk = &mi->blk[k];
if (bi->nid == bk->nid)
continue;
if (start < bk->end && end > bk->start)
break;
}
if (k < mi->nr_blks)
continue;
printk(KERN_INFO "NUMA: Node %d [mem %#010Lx-%#010Lx] + [mem %#010Lx-%#010Lx] -> [mem %#010Lx-%#010Lx]\n",
bi->nid, bi->start, bi->end - 1, bj->start,
bj->end - 1, start, end - 1);
bi->start = start;
bi->end = end;
numa_remove_memblk_from(j--, mi);
}
}
for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) {
mi->blk[i].start = mi->blk[i].end = 0;
mi->blk[i].nid = NUMA_NO_NODE;
}
return 0;
}
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);
}
void __init numa_reset_distance(void)
{
size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);
if (numa_distance_cnt)
memblock_free(numa_distance, size);
numa_distance_cnt = 0;
numa_distance = NULL;
}
static int __init numa_alloc_distance(void)
{
nodemask_t nodes_parsed;
size_t size;
int i, j, cnt = 0;
u64 phys;
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_phys_alloc_range(size, PAGE_SIZE, 0,
PFN_PHYS(max_pfn_mapped));
if (!phys) {
pr_warn("Warning: can't allocate distance table!\n");
numa_distance = (void *)1LU;
return -ENOMEM;
}
numa_distance = __va(phys);
numa_distance_cnt = cnt;
for (i = 0; i < cnt; i++)
for (j = 0; j < cnt; j++)
numa_distance[i * cnt + j] = i == j ?
LOCAL_DISTANCE : REMOTE_DISTANCE;
printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
return 0;
}
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("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("Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
numa_distance[from * numa_distance_cnt + to] = 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 bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
{
u64 numaram, e820ram;
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;
}
e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n",
(numaram << PAGE_SHIFT) >> 20,
(e820ram << PAGE_SHIFT) >> 20);
return false;
}
return true;
}
static void __init numa_clear_kernel_node_hotplug(void)
{
nodemask_t reserved_nodemask = NODE_MASK_NONE;
struct memblock_region *mb_region;
int i;
for (i = 0; i < numa_meminfo.nr_blks; i++) {
struct numa_memblk *mb = numa_meminfo.blk + i;
int ret;
ret = memblock_set_node(mb->start, mb->end - mb->start, &memblock.reserved, mb->nid);
WARN_ON_ONCE(ret);
}
for_each_reserved_mem_region(mb_region) {
int nid = memblock_get_region_node(mb_region);
if (nid != MAX_NUMNODES)
node_set(nid, reserved_nodemask);
}
for (i = 0; i < numa_meminfo.nr_blks; i++) {
struct numa_memblk *mb = numa_meminfo.blk + i;
if (!node_isset(mb->nid, reserved_nodemask))
continue;
memblock_clear_hotplug(mb->start, mb->end - mb->start);
}
}
static int __init numa_register_memblks(struct numa_meminfo *mi)
{
int i, nid;
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);
}
numa_clear_kernel_node_hotplug();
if (IS_ENABLED(NODE_NOT_IN_PAGE_FLAGS)) {
unsigned long pfn_align = node_map_pfn_alignment();
if (pfn_align && pfn_align < PAGES_PER_SECTION) {
pr_warn("Node alignment %LuMB < min %LuMB, rejecting NUMA config\n",
PFN_PHYS(pfn_align) >> 20,
PFN_PHYS(PAGES_PER_SECTION) >> 20);
return -EINVAL;
}
}
if (!numa_meminfo_cover_memory(mi))
return -EINVAL;
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)
continue;
if (end && (end - start) < NODE_MIN_SIZE)
continue;
alloc_node_data(nid);
}
memblock_dump_all();
return 0;
}
static void __init numa_init_array(void)
{
int rr, i;
rr = first_node(node_online_map);
for (i = 0; i < nr_cpu_ids; i++) {
if (early_cpu_to_node(i) != NUMA_NO_NODE)
continue;
numa_set_node(i, rr);
rr = next_node_in(rr, node_online_map);
}
}
static int __init numa_init(int (*init_func)(void))
{
int i;
int ret;
for (i = 0; i < MAX_LOCAL_APIC; i++)
set_apicid_to_node(i, NUMA_NO_NODE);
nodes_clear(numa_nodes_parsed);
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
memset(&numa_meminfo, 0, sizeof(numa_meminfo));
WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
MAX_NUMNODES));
WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
MAX_NUMNODES));
WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
numa_reset_distance();
ret = init_func();
if (ret < 0)
return ret;
memblock_set_bottom_up(false);
ret = numa_cleanup_meminfo(&numa_meminfo);
if (ret < 0)
return ret;
numa_emulation(&numa_meminfo, numa_distance_cnt);
ret = numa_register_memblks(&numa_meminfo);
if (ret < 0)
return ret;
for (i = 0; i < nr_cpu_ids; i++) {
int nid = early_cpu_to_node(i);
if (nid == NUMA_NO_NODE)
continue;
if (!node_online(nid))
numa_clear_node(i);
}
numa_init_array();
return 0;
}
static int __init dummy_numa_init(void)
{
printk(KERN_INFO "%s\n",
numa_off ? "NUMA turned off" : "No NUMA configuration found");
printk(KERN_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));
return 0;
}
void __init x86_numa_init(void)
{
if (!numa_off) {
#ifdef CONFIG_ACPI_NUMA
if (!numa_init(x86_acpi_numa_init))
return;
#endif
#ifdef CONFIG_AMD_NUMA
if (!numa_init(amd_numa_init))
return;
#endif
}
numa_init(dummy_numa_init);
}
void __init init_gi_nodes(void)
{
int nid;
for_each_node_state(nid, N_GENERIC_INITIATOR)
if (!node_online(nid))
node_set_online(nid);
}
void __init init_cpu_to_node(void)
{
int cpu;
u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
BUG_ON(cpu_to_apicid == NULL);
for_each_possible_cpu(cpu) {
int node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE)
continue;
if (!node_online(node))
node_set_online(node);
numa_set_node(cpu, node);
}
}
#ifndef CONFIG_DEBUG_PER_CPU_MAPS
# ifndef CONFIG_NUMA_EMU
void numa_add_cpu(int cpu)
{
cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
}
void numa_remove_cpu(int cpu)
{
cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
}
# endif /* !CONFIG_NUMA_EMU */
#else /* !CONFIG_DEBUG_PER_CPU_MAPS */
int __cpu_to_node(int cpu)
{
if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
printk(KERN_WARNING
"cpu_to_node(%d): usage too early!\n", cpu);
dump_stack();
return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
}
return per_cpu(x86_cpu_to_node_map, cpu);
}
EXPORT_SYMBOL(__cpu_to_node);
int early_cpu_to_node(int cpu)
{
if (early_per_cpu_ptr(x86_cpu_to_node_map))
return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
if (!cpu_possible(cpu)) {
printk(KERN_WARNING
"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
dump_stack();
return NUMA_NO_NODE;
}
return per_cpu(x86_cpu_to_node_map, cpu);
}
void debug_cpumask_set_cpu(int cpu, int node, bool enable)
{
struct cpumask *mask;
if (node == NUMA_NO_NODE) {
return;
}
mask = node_to_cpumask_map[node];
if (!cpumask_available(mask)) {
pr_err("node_to_cpumask_map[%i] NULL\n", node);
dump_stack();
return;
}
if (enable)
cpumask_set_cpu(cpu, mask);
else
cpumask_clear_cpu(cpu, mask);
printk(KERN_DEBUG "%s cpu %d node %d: mask now %*pbl\n",
enable ? "numa_add_cpu" : "numa_remove_cpu",
cpu, node, cpumask_pr_args(mask));
return;
}
# ifndef CONFIG_NUMA_EMU
static void numa_set_cpumask(int cpu, bool enable)
{
debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
}
void numa_add_cpu(int cpu)
{
numa_set_cpumask(cpu, true);
}
void numa_remove_cpu(int cpu)
{
numa_set_cpumask(cpu, false);
}
# endif /* !CONFIG_NUMA_EMU */
const struct cpumask *cpumask_of_node(int node)
{
if ((unsigned)node >= nr_node_ids) {
printk(KERN_WARNING
"cpumask_of_node(%d): (unsigned)node >= nr_node_ids(%u)\n",
node, nr_node_ids);
dump_stack();
return cpu_none_mask;
}
if (!cpumask_available(node_to_cpumask_map[node])) {
printk(KERN_WARNING
"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);
#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
#ifdef CONFIG_NUMA_KEEP_MEMINFO
static int meminfo_to_nid(struct numa_meminfo *mi, u64 start)
{
int i;
for (i = 0; i < mi->nr_blks; i++)
if (mi->blk[i].start <= start && mi->blk[i].end > start)
return mi->blk[i].nid;
return NUMA_NO_NODE;
}
int phys_to_target_node(phys_addr_t start)
{
int nid = meminfo_to_nid(&numa_meminfo, start);
if (nid != NUMA_NO_NODE)
return nid;
return meminfo_to_nid(&numa_reserved_meminfo, start);
}
EXPORT_SYMBOL_GPL(phys_to_target_node);
int memory_add_physaddr_to_nid(u64 start)
{
int nid = meminfo_to_nid(&numa_meminfo, start);
if (nid == NUMA_NO_NODE)
nid = numa_meminfo.blk[0].nid;
return nid;
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif