2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2000, 2003 Silicon Graphics, Inc. All rights reserved.
|
|
|
|
* Copyright (c) 2001 Intel Corp.
|
|
|
|
* Copyright (c) 2001 Tony Luck <tony.luck@intel.com>
|
|
|
|
* Copyright (c) 2002 NEC Corp.
|
|
|
|
* Copyright (c) 2002 Kimio Suganuma <k-suganuma@da.jp.nec.com>
|
|
|
|
* Copyright (c) 2004 Silicon Graphics, Inc
|
|
|
|
* Russ Anderson <rja@sgi.com>
|
|
|
|
* Jesse Barnes <jbarnes@sgi.com>
|
|
|
|
* Jack Steiner <steiner@sgi.com>
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Platform initialization for Discontig Memory
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/swap.h>
|
|
|
|
#include <linux/bootmem.h>
|
|
|
|
#include <linux/acpi.h>
|
|
|
|
#include <linux/efi.h>
|
|
|
|
#include <linux/nodemask.h>
|
|
|
|
#include <asm/pgalloc.h>
|
|
|
|
#include <asm/tlb.h>
|
|
|
|
#include <asm/meminit.h>
|
|
|
|
#include <asm/numa.h>
|
|
|
|
#include <asm/sections.h>
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Track per-node information needed to setup the boot memory allocator, the
|
|
|
|
* per-node areas, and the real VM.
|
|
|
|
*/
|
|
|
|
struct early_node_data {
|
|
|
|
struct ia64_node_data *node_data;
|
|
|
|
pg_data_t *pgdat;
|
|
|
|
unsigned long pernode_addr;
|
|
|
|
unsigned long pernode_size;
|
|
|
|
struct bootmem_data bootmem_data;
|
|
|
|
unsigned long num_physpages;
|
|
|
|
unsigned long num_dma_physpages;
|
|
|
|
unsigned long min_pfn;
|
|
|
|
unsigned long max_pfn;
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct early_node_data mem_data[MAX_NUMNODES] __initdata;
|
2005-07-01 00:52:00 +08:00
|
|
|
static nodemask_t memory_less_mask __initdata;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* To prevent cache aliasing effects, align per-node structures so that they
|
|
|
|
* start at addresses that are strided by node number.
|
|
|
|
*/
|
2005-12-06 03:56:50 +08:00
|
|
|
#define MAX_NODE_ALIGN_OFFSET (32 * 1024 * 1024)
|
2005-04-17 06:20:36 +08:00
|
|
|
#define NODEDATA_ALIGN(addr, node) \
|
2005-12-06 03:56:50 +08:00
|
|
|
((((addr) + 1024*1024-1) & ~(1024*1024-1)) + \
|
|
|
|
(((node)*PERCPU_PAGE_SIZE) & (MAX_NODE_ALIGN_OFFSET - 1)))
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* build_node_maps - callback to setup bootmem structs for each node
|
|
|
|
* @start: physical start of range
|
|
|
|
* @len: length of range
|
|
|
|
* @node: node where this range resides
|
|
|
|
*
|
|
|
|
* We allocate a struct bootmem_data for each piece of memory that we wish to
|
|
|
|
* treat as a virtually contiguous block (i.e. each node). Each such block
|
|
|
|
* must start on an %IA64_GRANULE_SIZE boundary, so we round the address down
|
|
|
|
* if necessary. Any non-existent pages will simply be part of the virtual
|
|
|
|
* memmap. We also update min_low_pfn and max_low_pfn here as we receive
|
|
|
|
* memory ranges from the caller.
|
|
|
|
*/
|
|
|
|
static int __init build_node_maps(unsigned long start, unsigned long len,
|
|
|
|
int node)
|
|
|
|
{
|
|
|
|
unsigned long cstart, epfn, end = start + len;
|
|
|
|
struct bootmem_data *bdp = &mem_data[node].bootmem_data;
|
|
|
|
|
|
|
|
epfn = GRANULEROUNDUP(end) >> PAGE_SHIFT;
|
|
|
|
cstart = GRANULEROUNDDOWN(start);
|
|
|
|
|
|
|
|
if (!bdp->node_low_pfn) {
|
|
|
|
bdp->node_boot_start = cstart;
|
|
|
|
bdp->node_low_pfn = epfn;
|
|
|
|
} else {
|
|
|
|
bdp->node_boot_start = min(cstart, bdp->node_boot_start);
|
|
|
|
bdp->node_low_pfn = max(epfn, bdp->node_low_pfn);
|
|
|
|
}
|
|
|
|
|
|
|
|
min_low_pfn = min(min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT);
|
|
|
|
max_low_pfn = max(max_low_pfn, bdp->node_low_pfn);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2005-07-01 00:52:00 +08:00
|
|
|
* early_nr_cpus_node - return number of cpus on a given node
|
2005-04-17 06:20:36 +08:00
|
|
|
* @node: node to check
|
|
|
|
*
|
2005-07-01 00:52:00 +08:00
|
|
|
* Count the number of cpus on @node. We can't use nr_cpus_node() yet because
|
2005-04-17 06:20:36 +08:00
|
|
|
* acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been
|
2005-07-01 00:52:00 +08:00
|
|
|
* called yet. Note that node 0 will also count all non-existent cpus.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2005-07-01 00:52:00 +08:00
|
|
|
static int __init early_nr_cpus_node(int node)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
int cpu, n = 0;
|
|
|
|
|
|
|
|
for (cpu = 0; cpu < NR_CPUS; cpu++)
|
|
|
|
if (node == node_cpuid[cpu].nid)
|
2005-07-01 00:52:00 +08:00
|
|
|
n++;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
return n;
|
|
|
|
}
|
|
|
|
|
2005-07-01 00:52:00 +08:00
|
|
|
/**
|
|
|
|
* compute_pernodesize - compute size of pernode data
|
|
|
|
* @node: the node id.
|
|
|
|
*/
|
|
|
|
static unsigned long __init compute_pernodesize(int node)
|
|
|
|
{
|
|
|
|
unsigned long pernodesize = 0, cpus;
|
|
|
|
|
|
|
|
cpus = early_nr_cpus_node(node);
|
|
|
|
pernodesize += PERCPU_PAGE_SIZE * cpus;
|
|
|
|
pernodesize += node * L1_CACHE_BYTES;
|
|
|
|
pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t));
|
|
|
|
pernodesize += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));
|
|
|
|
pernodesize = PAGE_ALIGN(pernodesize);
|
|
|
|
return pernodesize;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-07-07 09:18:10 +08:00
|
|
|
/**
|
|
|
|
* per_cpu_node_setup - setup per-cpu areas on each node
|
|
|
|
* @cpu_data: per-cpu area on this node
|
|
|
|
* @node: node to setup
|
|
|
|
*
|
|
|
|
* Copy the static per-cpu data into the region we just set aside and then
|
|
|
|
* setup __per_cpu_offset for each CPU on this node. Return a pointer to
|
|
|
|
* the end of the area.
|
|
|
|
*/
|
|
|
|
static void *per_cpu_node_setup(void *cpu_data, int node)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
for (cpu = 0; cpu < NR_CPUS; cpu++) {
|
|
|
|
if (node == node_cpuid[cpu].nid) {
|
|
|
|
memcpy(__va(cpu_data), __phys_per_cpu_start,
|
|
|
|
__per_cpu_end - __per_cpu_start);
|
|
|
|
__per_cpu_offset[cpu] = (char*)__va(cpu_data) -
|
|
|
|
__per_cpu_start;
|
|
|
|
cpu_data += PERCPU_PAGE_SIZE;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
return cpu_data;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
2005-07-01 00:52:00 +08:00
|
|
|
* fill_pernode - initialize pernode data.
|
|
|
|
* @node: the node id.
|
|
|
|
* @pernode: physical address of pernode data
|
|
|
|
* @pernodesize: size of the pernode data
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2005-07-01 00:52:00 +08:00
|
|
|
static void __init fill_pernode(int node, unsigned long pernode,
|
|
|
|
unsigned long pernodesize)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2005-07-01 00:52:00 +08:00
|
|
|
void *cpu_data;
|
2005-07-07 09:18:10 +08:00
|
|
|
int cpus = early_nr_cpus_node(node);
|
2005-07-01 00:52:00 +08:00
|
|
|
struct bootmem_data *bdp = &mem_data[node].bootmem_data;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-07-01 00:52:00 +08:00
|
|
|
mem_data[node].pernode_addr = pernode;
|
|
|
|
mem_data[node].pernode_size = pernodesize;
|
|
|
|
memset(__va(pernode), 0, pernodesize);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-07-01 00:52:00 +08:00
|
|
|
cpu_data = (void *)pernode;
|
|
|
|
pernode += PERCPU_PAGE_SIZE * cpus;
|
|
|
|
pernode += node * L1_CACHE_BYTES;
|
|
|
|
|
|
|
|
mem_data[node].pgdat = __va(pernode);
|
|
|
|
pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));
|
|
|
|
|
|
|
|
mem_data[node].node_data = __va(pernode);
|
|
|
|
pernode += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));
|
|
|
|
|
|
|
|
mem_data[node].pgdat->bdata = bdp;
|
|
|
|
pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));
|
|
|
|
|
2005-07-07 09:18:10 +08:00
|
|
|
cpu_data = per_cpu_node_setup(cpu_data, node);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-07-01 00:52:00 +08:00
|
|
|
return;
|
|
|
|
}
|
2005-07-07 09:18:10 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
|
|
|
* find_pernode_space - allocate memory for memory map and per-node structures
|
|
|
|
* @start: physical start of range
|
|
|
|
* @len: length of range
|
|
|
|
* @node: node where this range resides
|
|
|
|
*
|
|
|
|
* This routine reserves space for the per-cpu data struct, the list of
|
|
|
|
* pg_data_ts and the per-node data struct. Each node will have something like
|
|
|
|
* the following in the first chunk of addr. space large enough to hold it.
|
|
|
|
*
|
|
|
|
* ________________________
|
|
|
|
* | |
|
|
|
|
* |~~~~~~~~~~~~~~~~~~~~~~~~| <-- NODEDATA_ALIGN(start, node) for the first
|
|
|
|
* | PERCPU_PAGE_SIZE * | start and length big enough
|
|
|
|
* | cpus_on_this_node | Node 0 will also have entries for all non-existent cpus.
|
|
|
|
* |------------------------|
|
|
|
|
* | local pg_data_t * |
|
|
|
|
* |------------------------|
|
|
|
|
* | local ia64_node_data |
|
|
|
|
* |------------------------|
|
|
|
|
* | ??? |
|
|
|
|
* |________________________|
|
|
|
|
*
|
|
|
|
* Once this space has been set aside, the bootmem maps are initialized. We
|
|
|
|
* could probably move the allocation of the per-cpu and ia64_node_data space
|
|
|
|
* outside of this function and use alloc_bootmem_node(), but doing it here
|
|
|
|
* is straightforward and we get the alignments we want so...
|
|
|
|
*/
|
|
|
|
static int __init find_pernode_space(unsigned long start, unsigned long len,
|
|
|
|
int node)
|
|
|
|
{
|
2005-07-01 00:52:00 +08:00
|
|
|
unsigned long epfn;
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned long pernodesize = 0, pernode, pages, mapsize;
|
|
|
|
struct bootmem_data *bdp = &mem_data[node].bootmem_data;
|
|
|
|
|
|
|
|
epfn = (start + len) >> PAGE_SHIFT;
|
|
|
|
|
|
|
|
pages = bdp->node_low_pfn - (bdp->node_boot_start >> PAGE_SHIFT);
|
|
|
|
mapsize = bootmem_bootmap_pages(pages) << PAGE_SHIFT;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Make sure this memory falls within this node's usable memory
|
|
|
|
* since we may have thrown some away in build_maps().
|
|
|
|
*/
|
|
|
|
if (start < bdp->node_boot_start || epfn > bdp->node_low_pfn)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/* Don't setup this node's local space twice... */
|
|
|
|
if (mem_data[node].pernode_addr)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Calculate total size needed, incl. what's necessary
|
|
|
|
* for good alignment and alias prevention.
|
|
|
|
*/
|
2005-07-01 00:52:00 +08:00
|
|
|
pernodesize = compute_pernodesize(node);
|
2005-04-17 06:20:36 +08:00
|
|
|
pernode = NODEDATA_ALIGN(start, node);
|
|
|
|
|
|
|
|
/* Is this range big enough for what we want to store here? */
|
2005-07-01 00:52:00 +08:00
|
|
|
if (start + len > (pernode + pernodesize + mapsize))
|
|
|
|
fill_pernode(node, pernode, pernodesize);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* free_node_bootmem - free bootmem allocator memory for use
|
|
|
|
* @start: physical start of range
|
|
|
|
* @len: length of range
|
|
|
|
* @node: node where this range resides
|
|
|
|
*
|
|
|
|
* Simply calls the bootmem allocator to free the specified ranged from
|
|
|
|
* the given pg_data_t's bdata struct. After this function has been called
|
|
|
|
* for all the entries in the EFI memory map, the bootmem allocator will
|
|
|
|
* be ready to service allocation requests.
|
|
|
|
*/
|
|
|
|
static int __init free_node_bootmem(unsigned long start, unsigned long len,
|
|
|
|
int node)
|
|
|
|
{
|
|
|
|
free_bootmem_node(mem_data[node].pgdat, start, len);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* reserve_pernode_space - reserve memory for per-node space
|
|
|
|
*
|
|
|
|
* Reserve the space used by the bootmem maps & per-node space in the boot
|
|
|
|
* allocator so that when we actually create the real mem maps we don't
|
|
|
|
* use their memory.
|
|
|
|
*/
|
|
|
|
static void __init reserve_pernode_space(void)
|
|
|
|
{
|
|
|
|
unsigned long base, size, pages;
|
|
|
|
struct bootmem_data *bdp;
|
|
|
|
int node;
|
|
|
|
|
|
|
|
for_each_online_node(node) {
|
|
|
|
pg_data_t *pdp = mem_data[node].pgdat;
|
|
|
|
|
2005-07-01 00:52:00 +08:00
|
|
|
if (node_isset(node, memory_less_mask))
|
|
|
|
continue;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
bdp = pdp->bdata;
|
|
|
|
|
|
|
|
/* First the bootmem_map itself */
|
|
|
|
pages = bdp->node_low_pfn - (bdp->node_boot_start>>PAGE_SHIFT);
|
|
|
|
size = bootmem_bootmap_pages(pages) << PAGE_SHIFT;
|
|
|
|
base = __pa(bdp->node_bootmem_map);
|
|
|
|
reserve_bootmem_node(pdp, base, size);
|
|
|
|
|
|
|
|
/* Now the per-node space */
|
|
|
|
size = mem_data[node].pernode_size;
|
|
|
|
base = __pa(mem_data[node].pernode_addr);
|
|
|
|
reserve_bootmem_node(pdp, base, size);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* initialize_pernode_data - fixup per-cpu & per-node pointers
|
|
|
|
*
|
|
|
|
* Each node's per-node area has a copy of the global pg_data_t list, so
|
|
|
|
* we copy that to each node here, as well as setting the per-cpu pointer
|
|
|
|
* to the local node data structure. The active_cpus field of the per-node
|
|
|
|
* structure gets setup by the platform_cpu_init() function later.
|
|
|
|
*/
|
|
|
|
static void __init initialize_pernode_data(void)
|
|
|
|
{
|
|
|
|
pg_data_t *pgdat_list[MAX_NUMNODES];
|
2005-07-07 09:18:10 +08:00
|
|
|
int cpu, node;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
for_each_online_node(node)
|
|
|
|
pgdat_list[node] = mem_data[node].pgdat;
|
|
|
|
|
|
|
|
/* Copy the pg_data_t list to each node and init the node field */
|
|
|
|
for_each_online_node(node) {
|
|
|
|
memcpy(mem_data[node].node_data->pg_data_ptrs, pgdat_list,
|
|
|
|
sizeof(pgdat_list));
|
|
|
|
}
|
2005-07-07 09:18:10 +08:00
|
|
|
#ifdef CONFIG_SMP
|
2005-04-17 06:20:36 +08:00
|
|
|
/* Set the node_data pointer for each per-cpu struct */
|
|
|
|
for (cpu = 0; cpu < NR_CPUS; cpu++) {
|
|
|
|
node = node_cpuid[cpu].nid;
|
|
|
|
per_cpu(cpu_info, cpu).node_data = mem_data[node].node_data;
|
|
|
|
}
|
2005-07-07 09:18:10 +08:00
|
|
|
#else
|
|
|
|
{
|
|
|
|
struct cpuinfo_ia64 *cpu0_cpu_info;
|
|
|
|
cpu = 0;
|
|
|
|
node = node_cpuid[cpu].nid;
|
|
|
|
cpu0_cpu_info = (struct cpuinfo_ia64 *)(__phys_per_cpu_start +
|
|
|
|
((char *)&per_cpu__cpu_info - __per_cpu_start));
|
|
|
|
cpu0_cpu_info->node_data = mem_data[node].node_data;
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_SMP */
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2005-07-01 00:52:00 +08:00
|
|
|
/**
|
|
|
|
* memory_less_node_alloc - * attempt to allocate memory on the best NUMA slit
|
|
|
|
* node but fall back to any other node when __alloc_bootmem_node fails
|
|
|
|
* for best.
|
|
|
|
* @nid: node id
|
|
|
|
* @pernodesize: size of this node's pernode data
|
|
|
|
*/
|
2005-10-30 05:23:05 +08:00
|
|
|
static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
|
2005-07-01 00:52:00 +08:00
|
|
|
{
|
|
|
|
void *ptr = NULL;
|
|
|
|
u8 best = 0xff;
|
2005-10-30 05:23:05 +08:00
|
|
|
int bestnode = -1, node, anynode = 0;
|
2005-07-01 00:52:00 +08:00
|
|
|
|
|
|
|
for_each_online_node(node) {
|
|
|
|
if (node_isset(node, memory_less_mask))
|
|
|
|
continue;
|
|
|
|
else if (node_distance(nid, node) < best) {
|
|
|
|
best = node_distance(nid, node);
|
|
|
|
bestnode = node;
|
|
|
|
}
|
2005-10-30 05:23:05 +08:00
|
|
|
anynode = node;
|
2005-07-01 00:52:00 +08:00
|
|
|
}
|
|
|
|
|
2005-10-30 05:23:05 +08:00
|
|
|
if (bestnode == -1)
|
|
|
|
bestnode = anynode;
|
|
|
|
|
|
|
|
ptr = __alloc_bootmem_node(mem_data[bestnode].pgdat, pernodesize,
|
|
|
|
PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
|
2005-07-01 00:52:00 +08:00
|
|
|
|
|
|
|
return ptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* pgdat_insert - insert the pgdat into global pgdat_list
|
|
|
|
* @pgdat: the pgdat for a node.
|
|
|
|
*/
|
|
|
|
static void __init pgdat_insert(pg_data_t *pgdat)
|
|
|
|
{
|
|
|
|
pg_data_t *prev = NULL, *next;
|
|
|
|
|
|
|
|
for_each_pgdat(next)
|
|
|
|
if (pgdat->node_id < next->node_id)
|
|
|
|
break;
|
|
|
|
else
|
|
|
|
prev = next;
|
|
|
|
|
|
|
|
if (prev) {
|
|
|
|
prev->pgdat_next = pgdat;
|
|
|
|
pgdat->pgdat_next = next;
|
|
|
|
} else {
|
|
|
|
pgdat->pgdat_next = pgdat_list;
|
|
|
|
pgdat_list = pgdat;
|
|
|
|
}
|
|
|
|
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* memory_less_nodes - allocate and initialize CPU only nodes pernode
|
|
|
|
* information.
|
|
|
|
*/
|
|
|
|
static void __init memory_less_nodes(void)
|
|
|
|
{
|
|
|
|
unsigned long pernodesize;
|
|
|
|
void *pernode;
|
|
|
|
int node;
|
|
|
|
|
|
|
|
for_each_node_mask(node, memory_less_mask) {
|
|
|
|
pernodesize = compute_pernodesize(node);
|
2005-10-30 05:23:05 +08:00
|
|
|
pernode = memory_less_node_alloc(node, pernodesize);
|
2005-07-01 00:52:00 +08:00
|
|
|
fill_pernode(node, __pa(pernode), pernodesize);
|
|
|
|
}
|
|
|
|
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2005-10-05 03:13:57 +08:00
|
|
|
#ifdef CONFIG_SPARSEMEM
|
|
|
|
/**
|
|
|
|
* register_sparse_mem - notify SPARSEMEM that this memory range exists.
|
|
|
|
* @start: physical start of range
|
|
|
|
* @end: physical end of range
|
|
|
|
* @arg: unused
|
|
|
|
*
|
|
|
|
* Simply calls SPARSEMEM to register memory section(s).
|
|
|
|
*/
|
|
|
|
static int __init register_sparse_mem(unsigned long start, unsigned long end,
|
|
|
|
void *arg)
|
|
|
|
{
|
|
|
|
int nid;
|
|
|
|
|
|
|
|
start = __pa(start) >> PAGE_SHIFT;
|
|
|
|
end = __pa(end) >> PAGE_SHIFT;
|
|
|
|
nid = early_pfn_to_nid(start);
|
|
|
|
memory_present(nid, start, end);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __init arch_sparse_init(void)
|
|
|
|
{
|
|
|
|
efi_memmap_walk(register_sparse_mem, NULL);
|
|
|
|
sparse_init();
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
#define arch_sparse_init() do {} while (0)
|
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
|
|
|
* find_memory - walk the EFI memory map and setup the bootmem allocator
|
|
|
|
*
|
|
|
|
* Called early in boot to setup the bootmem allocator, and to
|
|
|
|
* allocate the per-cpu and per-node structures.
|
|
|
|
*/
|
|
|
|
void __init find_memory(void)
|
|
|
|
{
|
|
|
|
int node;
|
|
|
|
|
|
|
|
reserve_memory();
|
|
|
|
|
|
|
|
if (num_online_nodes() == 0) {
|
|
|
|
printk(KERN_ERR "node info missing!\n");
|
|
|
|
node_set_online(0);
|
|
|
|
}
|
|
|
|
|
2005-07-01 00:52:00 +08:00
|
|
|
nodes_or(memory_less_mask, memory_less_mask, node_online_map);
|
2005-04-17 06:20:36 +08:00
|
|
|
min_low_pfn = -1;
|
|
|
|
max_low_pfn = 0;
|
|
|
|
|
|
|
|
/* These actually end up getting called by call_pernode_memory() */
|
|
|
|
efi_memmap_walk(filter_rsvd_memory, build_node_maps);
|
|
|
|
efi_memmap_walk(filter_rsvd_memory, find_pernode_space);
|
|
|
|
|
2005-07-01 00:52:00 +08:00
|
|
|
for_each_online_node(node)
|
|
|
|
if (mem_data[node].bootmem_data.node_low_pfn) {
|
|
|
|
node_clear(node, memory_less_mask);
|
|
|
|
mem_data[node].min_pfn = ~0UL;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Initialize the boot memory maps in reverse order since that's
|
|
|
|
* what the bootmem allocator expects
|
|
|
|
*/
|
|
|
|
for (node = MAX_NUMNODES - 1; node >= 0; node--) {
|
|
|
|
unsigned long pernode, pernodesize, map;
|
|
|
|
struct bootmem_data *bdp;
|
|
|
|
|
|
|
|
if (!node_online(node))
|
|
|
|
continue;
|
2005-07-01 00:52:00 +08:00
|
|
|
else if (node_isset(node, memory_less_mask))
|
|
|
|
continue;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
bdp = &mem_data[node].bootmem_data;
|
|
|
|
pernode = mem_data[node].pernode_addr;
|
|
|
|
pernodesize = mem_data[node].pernode_size;
|
|
|
|
map = pernode + pernodesize;
|
|
|
|
|
|
|
|
init_bootmem_node(mem_data[node].pgdat,
|
|
|
|
map>>PAGE_SHIFT,
|
|
|
|
bdp->node_boot_start>>PAGE_SHIFT,
|
|
|
|
bdp->node_low_pfn);
|
|
|
|
}
|
|
|
|
|
|
|
|
efi_memmap_walk(filter_rsvd_memory, free_node_bootmem);
|
|
|
|
|
|
|
|
reserve_pernode_space();
|
2005-07-01 00:52:00 +08:00
|
|
|
memory_less_nodes();
|
2005-04-17 06:20:36 +08:00
|
|
|
initialize_pernode_data();
|
|
|
|
|
|
|
|
max_pfn = max_low_pfn;
|
|
|
|
|
|
|
|
find_initrd();
|
|
|
|
}
|
|
|
|
|
2005-07-07 09:18:10 +08:00
|
|
|
#ifdef CONFIG_SMP
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
|
|
|
* per_cpu_init - setup per-cpu variables
|
|
|
|
*
|
|
|
|
* find_pernode_space() does most of this already, we just need to set
|
|
|
|
* local_per_cpu_offset
|
|
|
|
*/
|
2006-03-13 01:00:13 +08:00
|
|
|
void __cpuinit *per_cpu_init(void)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
int cpu;
|
2005-11-12 06:32:40 +08:00
|
|
|
static int first_time = 1;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-07-07 09:18:10 +08:00
|
|
|
if (smp_processor_id() != 0)
|
|
|
|
return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
|
|
|
|
|
2005-11-12 06:32:40 +08:00
|
|
|
if (first_time) {
|
|
|
|
first_time = 0;
|
|
|
|
for (cpu = 0; cpu < NR_CPUS; cpu++)
|
|
|
|
per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
|
|
|
|
}
|
2005-07-07 09:18:10 +08:00
|
|
|
#endif /* CONFIG_SMP */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* show_mem - give short summary of memory stats
|
|
|
|
*
|
|
|
|
* Shows a simple page count of reserved and used pages in the system.
|
|
|
|
* For discontig machines, it does this on a per-pgdat basis.
|
|
|
|
*/
|
|
|
|
void show_mem(void)
|
|
|
|
{
|
|
|
|
int i, total_reserved = 0;
|
|
|
|
int total_shared = 0, total_cached = 0;
|
|
|
|
unsigned long total_present = 0;
|
|
|
|
pg_data_t *pgdat;
|
|
|
|
|
|
|
|
printk("Mem-info:\n");
|
|
|
|
show_free_areas();
|
|
|
|
printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
|
|
|
|
for_each_pgdat(pgdat) {
|
2005-10-30 09:16:52 +08:00
|
|
|
unsigned long present;
|
|
|
|
unsigned long flags;
|
2005-04-17 06:20:36 +08:00
|
|
|
int shared = 0, cached = 0, reserved = 0;
|
2005-10-30 09:16:52 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
printk("Node ID: %d\n", pgdat->node_id);
|
2005-10-30 09:16:52 +08:00
|
|
|
pgdat_resize_lock(pgdat, &flags);
|
|
|
|
present = pgdat->node_present_pages;
|
2005-04-17 06:20:36 +08:00
|
|
|
for(i = 0; i < pgdat->node_spanned_pages; i++) {
|
2005-10-05 03:13:57 +08:00
|
|
|
struct page *page;
|
|
|
|
if (pfn_valid(pgdat->node_start_pfn + i))
|
|
|
|
page = pfn_to_page(pgdat->node_start_pfn + i);
|
|
|
|
else
|
2005-04-17 06:20:36 +08:00
|
|
|
continue;
|
[PATCH] remove non-DISCONTIG use of pgdat->node_mem_map
This patch effectively eliminates direct use of pgdat->node_mem_map outside
of the DISCONTIG code. On a flat memory system, these fields aren't
currently used, neither are they on a sparsemem system.
There was also a node_mem_map(nid) macro on many architectures. Its use
along with the use of ->node_mem_map itself was not consistent. It has
been removed in favor of two new, more explicit, arch-independent macros:
pgdat_page_nr(pgdat, pagenr)
nid_page_nr(nid, pagenr)
I called them "pgdat" and "nid" because we overload the term "node" to mean
"NUMA node", "DISCONTIG node" or "pg_data_t" in very confusing ways. I
believe the newer names are much clearer.
These macros can be overridden in the sparsemem case with a theoretically
slower operation using node_start_pfn and pfn_to_page(), instead. We could
make this the only behavior if people want, but I don't want to change too
much at once. One thing at a time.
This patch removes more code than it adds.
Compile tested on alpha, alpha discontig, arm, arm-discontig, i386, i386
generic, NUMAQ, Summit, ppc64, ppc64 discontig, and x86_64. Full list
here: http://sr71.net/patches/2.6.12/2.6.12-rc1-mhp2/configs/
Boot tested on NUMAQ, x86 SMP and ppc64 power4/5 LPARs.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin J. Bligh <mbligh@aracnet.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:37 +08:00
|
|
|
if (PageReserved(page))
|
2005-04-17 06:20:36 +08:00
|
|
|
reserved++;
|
[PATCH] remove non-DISCONTIG use of pgdat->node_mem_map
This patch effectively eliminates direct use of pgdat->node_mem_map outside
of the DISCONTIG code. On a flat memory system, these fields aren't
currently used, neither are they on a sparsemem system.
There was also a node_mem_map(nid) macro on many architectures. Its use
along with the use of ->node_mem_map itself was not consistent. It has
been removed in favor of two new, more explicit, arch-independent macros:
pgdat_page_nr(pgdat, pagenr)
nid_page_nr(nid, pagenr)
I called them "pgdat" and "nid" because we overload the term "node" to mean
"NUMA node", "DISCONTIG node" or "pg_data_t" in very confusing ways. I
believe the newer names are much clearer.
These macros can be overridden in the sparsemem case with a theoretically
slower operation using node_start_pfn and pfn_to_page(), instead. We could
make this the only behavior if people want, but I don't want to change too
much at once. One thing at a time.
This patch removes more code than it adds.
Compile tested on alpha, alpha discontig, arm, arm-discontig, i386, i386
generic, NUMAQ, Summit, ppc64, ppc64 discontig, and x86_64. Full list
here: http://sr71.net/patches/2.6.12/2.6.12-rc1-mhp2/configs/
Boot tested on NUMAQ, x86 SMP and ppc64 power4/5 LPARs.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin J. Bligh <mbligh@aracnet.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:37 +08:00
|
|
|
else if (PageSwapCache(page))
|
2005-04-17 06:20:36 +08:00
|
|
|
cached++;
|
[PATCH] remove non-DISCONTIG use of pgdat->node_mem_map
This patch effectively eliminates direct use of pgdat->node_mem_map outside
of the DISCONTIG code. On a flat memory system, these fields aren't
currently used, neither are they on a sparsemem system.
There was also a node_mem_map(nid) macro on many architectures. Its use
along with the use of ->node_mem_map itself was not consistent. It has
been removed in favor of two new, more explicit, arch-independent macros:
pgdat_page_nr(pgdat, pagenr)
nid_page_nr(nid, pagenr)
I called them "pgdat" and "nid" because we overload the term "node" to mean
"NUMA node", "DISCONTIG node" or "pg_data_t" in very confusing ways. I
believe the newer names are much clearer.
These macros can be overridden in the sparsemem case with a theoretically
slower operation using node_start_pfn and pfn_to_page(), instead. We could
make this the only behavior if people want, but I don't want to change too
much at once. One thing at a time.
This patch removes more code than it adds.
Compile tested on alpha, alpha discontig, arm, arm-discontig, i386, i386
generic, NUMAQ, Summit, ppc64, ppc64 discontig, and x86_64. Full list
here: http://sr71.net/patches/2.6.12/2.6.12-rc1-mhp2/configs/
Boot tested on NUMAQ, x86 SMP and ppc64 power4/5 LPARs.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin J. Bligh <mbligh@aracnet.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:37 +08:00
|
|
|
else if (page_count(page))
|
|
|
|
shared += page_count(page)-1;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2005-10-30 09:16:52 +08:00
|
|
|
pgdat_resize_unlock(pgdat, &flags);
|
2005-04-17 06:20:36 +08:00
|
|
|
total_present += present;
|
|
|
|
total_reserved += reserved;
|
|
|
|
total_cached += cached;
|
|
|
|
total_shared += shared;
|
|
|
|
printk("\t%ld pages of RAM\n", present);
|
|
|
|
printk("\t%d reserved pages\n", reserved);
|
|
|
|
printk("\t%d pages shared\n", shared);
|
|
|
|
printk("\t%d pages swap cached\n", cached);
|
|
|
|
}
|
|
|
|
printk("%ld pages of RAM\n", total_present);
|
|
|
|
printk("%d reserved pages\n", total_reserved);
|
|
|
|
printk("%d pages shared\n", total_shared);
|
|
|
|
printk("%d pages swap cached\n", total_cached);
|
2005-04-26 04:13:16 +08:00
|
|
|
printk("Total of %ld pages in page table cache\n",
|
|
|
|
pgtable_quicklist_total_size());
|
2005-04-17 06:20:36 +08:00
|
|
|
printk("%d free buffer pages\n", nr_free_buffer_pages());
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* call_pernode_memory - use SRAT to call callback functions with node info
|
|
|
|
* @start: physical start of range
|
|
|
|
* @len: length of range
|
|
|
|
* @arg: function to call for each range
|
|
|
|
*
|
|
|
|
* efi_memmap_walk() knows nothing about layout of memory across nodes. Find
|
|
|
|
* out to which node a block of memory belongs. Ignore memory that we cannot
|
|
|
|
* identify, and split blocks that run across multiple nodes.
|
|
|
|
*
|
|
|
|
* Take this opportunity to round the start address up and the end address
|
|
|
|
* down to page boundaries.
|
|
|
|
*/
|
|
|
|
void call_pernode_memory(unsigned long start, unsigned long len, void *arg)
|
|
|
|
{
|
|
|
|
unsigned long rs, re, end = start + len;
|
|
|
|
void (*func)(unsigned long, unsigned long, int);
|
|
|
|
int i;
|
|
|
|
|
|
|
|
start = PAGE_ALIGN(start);
|
|
|
|
end &= PAGE_MASK;
|
|
|
|
if (start >= end)
|
|
|
|
return;
|
|
|
|
|
|
|
|
func = arg;
|
|
|
|
|
|
|
|
if (!num_node_memblks) {
|
|
|
|
/* No SRAT table, so assume one node (node 0) */
|
|
|
|
if (start < end)
|
|
|
|
(*func)(start, end - start, 0);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < num_node_memblks; i++) {
|
|
|
|
rs = max(start, node_memblk[i].start_paddr);
|
|
|
|
re = min(end, node_memblk[i].start_paddr +
|
|
|
|
node_memblk[i].size);
|
|
|
|
|
|
|
|
if (rs < re)
|
|
|
|
(*func)(rs, re - rs, node_memblk[i].nid);
|
|
|
|
|
|
|
|
if (re == end)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* count_node_pages - callback to build per-node memory info structures
|
|
|
|
* @start: physical start of range
|
|
|
|
* @len: length of range
|
|
|
|
* @node: node where this range resides
|
|
|
|
*
|
|
|
|
* Each node has it's own number of physical pages, DMAable pages, start, and
|
|
|
|
* end page frame number. This routine will be called by call_pernode_memory()
|
|
|
|
* for each piece of usable memory and will setup these values for each node.
|
|
|
|
* Very similar to build_maps().
|
|
|
|
*/
|
|
|
|
static __init int count_node_pages(unsigned long start, unsigned long len, int node)
|
|
|
|
{
|
|
|
|
unsigned long end = start + len;
|
|
|
|
|
|
|
|
mem_data[node].num_physpages += len >> PAGE_SHIFT;
|
|
|
|
if (start <= __pa(MAX_DMA_ADDRESS))
|
|
|
|
mem_data[node].num_dma_physpages +=
|
|
|
|
(min(end, __pa(MAX_DMA_ADDRESS)) - start) >>PAGE_SHIFT;
|
|
|
|
start = GRANULEROUNDDOWN(start);
|
|
|
|
start = ORDERROUNDDOWN(start);
|
|
|
|
end = GRANULEROUNDUP(end);
|
|
|
|
mem_data[node].max_pfn = max(mem_data[node].max_pfn,
|
|
|
|
end >> PAGE_SHIFT);
|
|
|
|
mem_data[node].min_pfn = min(mem_data[node].min_pfn,
|
|
|
|
start >> PAGE_SHIFT);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* paging_init - setup page tables
|
|
|
|
*
|
|
|
|
* paging_init() sets up the page tables for each node of the system and frees
|
|
|
|
* the bootmem allocator memory for general use.
|
|
|
|
*/
|
|
|
|
void __init paging_init(void)
|
|
|
|
{
|
|
|
|
unsigned long max_dma;
|
|
|
|
unsigned long zones_size[MAX_NR_ZONES];
|
|
|
|
unsigned long zholes_size[MAX_NR_ZONES];
|
|
|
|
unsigned long pfn_offset = 0;
|
|
|
|
int node;
|
|
|
|
|
|
|
|
max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
|
|
|
|
|
2005-10-05 03:13:57 +08:00
|
|
|
arch_sparse_init();
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
efi_memmap_walk(filter_rsvd_memory, count_node_pages);
|
|
|
|
|
2005-10-05 03:13:57 +08:00
|
|
|
#ifdef CONFIG_VIRTUAL_MEM_MAP
|
2005-07-01 00:52:00 +08:00
|
|
|
vmalloc_end -= PAGE_ALIGN(max_low_pfn * sizeof(struct page));
|
|
|
|
vmem_map = (struct page *) vmalloc_end;
|
|
|
|
efi_memmap_walk(create_mem_map_page_table, NULL);
|
|
|
|
printk("Virtual mem_map starts at 0x%p\n", vmem_map);
|
2005-10-05 03:13:57 +08:00
|
|
|
#endif
|
2005-07-01 00:52:00 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
for_each_online_node(node) {
|
|
|
|
memset(zones_size, 0, sizeof(zones_size));
|
|
|
|
memset(zholes_size, 0, sizeof(zholes_size));
|
|
|
|
|
|
|
|
num_physpages += mem_data[node].num_physpages;
|
|
|
|
|
|
|
|
if (mem_data[node].min_pfn >= max_dma) {
|
|
|
|
/* All of this node's memory is above ZONE_DMA */
|
|
|
|
zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
|
|
|
|
mem_data[node].min_pfn;
|
|
|
|
zholes_size[ZONE_NORMAL] = mem_data[node].max_pfn -
|
|
|
|
mem_data[node].min_pfn -
|
|
|
|
mem_data[node].num_physpages;
|
|
|
|
} else if (mem_data[node].max_pfn < max_dma) {
|
|
|
|
/* All of this node's memory is in ZONE_DMA */
|
|
|
|
zones_size[ZONE_DMA] = mem_data[node].max_pfn -
|
|
|
|
mem_data[node].min_pfn;
|
|
|
|
zholes_size[ZONE_DMA] = mem_data[node].max_pfn -
|
|
|
|
mem_data[node].min_pfn -
|
|
|
|
mem_data[node].num_dma_physpages;
|
|
|
|
} else {
|
|
|
|
/* This node has memory in both zones */
|
|
|
|
zones_size[ZONE_DMA] = max_dma -
|
|
|
|
mem_data[node].min_pfn;
|
|
|
|
zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] -
|
|
|
|
mem_data[node].num_dma_physpages;
|
|
|
|
zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
|
|
|
|
max_dma;
|
|
|
|
zholes_size[ZONE_NORMAL] = zones_size[ZONE_NORMAL] -
|
|
|
|
(mem_data[node].num_physpages -
|
|
|
|
mem_data[node].num_dma_physpages);
|
|
|
|
}
|
|
|
|
|
|
|
|
pfn_offset = mem_data[node].min_pfn;
|
|
|
|
|
2005-10-05 03:13:57 +08:00
|
|
|
#ifdef CONFIG_VIRTUAL_MEM_MAP
|
2005-04-17 06:20:36 +08:00
|
|
|
NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
|
2005-10-05 03:13:57 +08:00
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
free_area_init_node(node, NODE_DATA(node), zones_size,
|
|
|
|
pfn_offset, zholes_size);
|
|
|
|
}
|
|
|
|
|
2005-07-01 00:52:00 +08:00
|
|
|
/*
|
|
|
|
* Make memory less nodes become a member of the known nodes.
|
|
|
|
*/
|
|
|
|
for_each_node_mask(node, memory_less_mask)
|
|
|
|
pgdat_insert(mem_data[node].pgdat);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
|
|
|
|
}
|