![Punit Agrawal](/assets/img/avatar_default.png)
When booting linux on a system without CONFIG_NUMA enabled, the following messages are printed during boot - NUMA: Faking a node at [mem 0x0000000000000000-0x00000083ffffffff] NUMA: Adding memblock [0x8000000000 - 0x8000e7ffff] on node 0 NUMA: Adding memblock [0x8000e80000 - 0x83f65cffff] on node 0 NUMA: Adding memblock [0x83f65d0000 - 0x83f665ffff] on node 0 NUMA: Adding memblock [0x83f6660000 - 0x83f676ffff] on node 0 NUMA: Adding memblock [0x83f6770000 - 0x83f678ffff] on node 0 NUMA: Adding memblock [0x83f6790000 - 0x83fb82ffff] on node 0 NUMA: Adding memblock [0x83fb830000 - 0x83fbc0ffff] on node 0 NUMA: Adding memblock [0x83fbc10000 - 0x83fbdfffff] on node 0 NUMA: Adding memblock [0x83fbe00000 - 0x83fbffffff] on node 0 NUMA: Adding memblock [0x83fc000000 - 0x83fffbffff] on node 0 NUMA: Adding memblock [0x83fffc0000 - 0x83fffdffff] on node 0 NUMA: Adding memblock [0x83fffe0000 - 0x83ffffffff] on node 0 NUMA: Initmem setup node 0 [mem 0x8000000000-0x83ffffffff] NUMA: NODE_DATA [mem 0x83fffec500-0x83fffedfff] The information is then duplicated by core kernel messages right after the above output. Early memory node ranges node 0: [mem 0x0000008000000000-0x0000008000e7ffff] node 0: [mem 0x0000008000e80000-0x00000083f65cffff] node 0: [mem 0x00000083f65d0000-0x00000083f665ffff] node 0: [mem 0x00000083f6660000-0x00000083f676ffff] node 0: [mem 0x00000083f6770000-0x00000083f678ffff] node 0: [mem 0x00000083f6790000-0x00000083fb82ffff] node 0: [mem 0x00000083fb830000-0x00000083fbc0ffff] node 0: [mem 0x00000083fbc10000-0x00000083fbdfffff] node 0: [mem 0x00000083fbe00000-0x00000083fbffffff] node 0: [mem 0x00000083fc000000-0x00000083fffbffff] node 0: [mem 0x00000083fffc0000-0x00000083fffdffff] node 0: [mem 0x00000083fffe0000-0x00000083ffffffff] Initmem setup node 0 [mem 0x0000008000000000-0x00000083ffffffff] Remove the duplication of memblock layout information printed during boot by dropping the messages from arm64 numa initialisation. Signed-off-by: Punit Agrawal <punit.agrawal@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
454 lines
11 KiB
C
454 lines
11 KiB
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/>.
|
|
*/
|
|
|
|
#define pr_fmt(fmt) "NUMA: " fmt
|
|
|
|
#include <linux/acpi.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/memblock.h>
|
|
#include <linux/module.h>
|
|
#include <linux/of.h>
|
|
|
|
#include <asm/acpi.h>
|
|
#include <asm/sections.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;
|
|
bool numa_off;
|
|
|
|
static __init int numa_parse_early_param(char *opt)
|
|
{
|
|
if (!opt)
|
|
return -EINVAL;
|
|
if (!strncmp(opt, "off", 3))
|
|
numa_off = true;
|
|
|
|
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)
|
|
{
|
|
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]);
|
|
}
|
|
|
|
/* 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(unsigned int cpu)
|
|
{
|
|
map_cpu_to_node(cpu, 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 || numa_off)
|
|
nid = 0;
|
|
|
|
cpu_to_node_map[cpu] = nid;
|
|
|
|
/*
|
|
* We should set the numa node of cpu0 as soon as possible, because it
|
|
* has already been set up online before. cpu_to_node(0) will soon be
|
|
* called.
|
|
*/
|
|
if (!cpu)
|
|
set_cpu_numa_node(cpu, nid);
|
|
}
|
|
|
|
#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
|
|
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
|
|
EXPORT_SYMBOL(__per_cpu_offset);
|
|
|
|
static int __init early_cpu_to_node(int cpu)
|
|
{
|
|
return cpu_to_node_map[cpu];
|
|
}
|
|
|
|
static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
|
|
{
|
|
return node_distance(early_cpu_to_node(from), early_cpu_to_node(to));
|
|
}
|
|
|
|
static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
|
|
size_t align)
|
|
{
|
|
int nid = early_cpu_to_node(cpu);
|
|
|
|
return memblock_virt_alloc_try_nid(size, align,
|
|
__pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid);
|
|
}
|
|
|
|
static void __init pcpu_fc_free(void *ptr, size_t size)
|
|
{
|
|
memblock_free_early(__pa(ptr), size);
|
|
}
|
|
|
|
void __init setup_per_cpu_areas(void)
|
|
{
|
|
unsigned long delta;
|
|
unsigned int cpu;
|
|
int rc;
|
|
|
|
/*
|
|
* Always reserve area for module percpu variables. That's
|
|
* what the legacy allocator did.
|
|
*/
|
|
rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
|
|
PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
|
|
pcpu_cpu_distance,
|
|
pcpu_fc_alloc, pcpu_fc_free);
|
|
if (rc < 0)
|
|
panic("Failed to initialize percpu areas.");
|
|
|
|
delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
|
|
for_each_possible_cpu(cpu)
|
|
__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
|
|
}
|
|
#endif
|
|
|
|
/**
|
|
* numa_add_memblk - Set node id to memblk
|
|
* @nid: NUMA node ID of the new memblk
|
|
* @start: Start address 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 end)
|
|
{
|
|
int ret;
|
|
|
|
ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
|
|
if (ret < 0) {
|
|
pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n",
|
|
start, (end - 1), nid);
|
|
return ret;
|
|
}
|
|
|
|
node_set(nid, numa_nodes_parsed);
|
|
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;
|
|
|
|
if (start_pfn >= end_pfn)
|
|
pr_info("Initmem setup node %d [<memory-less node>]\n", nid);
|
|
|
|
nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
|
|
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_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("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("Warning: distance table not allocated yet\n");
|
|
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;
|
|
}
|
|
|
|
/**
|
|
* 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("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)) {
|
|
pr_info("No NUMA configuration found\n");
|
|
return -EINVAL;
|
|
}
|
|
|
|
ret = numa_register_nodes();
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
setup_node_to_cpumask_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 (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;
|
|
|
|
if (numa_off)
|
|
pr_info("NUMA disabled\n"); /* Forced off on command line. */
|
|
pr_info("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->base + mblk->size);
|
|
if (!ret)
|
|
continue;
|
|
|
|
pr_err("NUMA init failed\n");
|
|
return ret;
|
|
}
|
|
|
|
numa_off = true;
|
|
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 (!acpi_disabled && !numa_init(arm64_acpi_numa_init))
|
|
return;
|
|
if (acpi_disabled && !numa_init(of_numa_init))
|
|
return;
|
|
}
|
|
|
|
numa_init(dummy_numa_init);
|
|
}
|