/*
* Function: smp_dump_qct()
*
* Description: gets memory layout from the quad config table. This
* function also updates node_online_map with the nodes (quads) present.
*/
static void __init smp_dump_qct(void)
{
int node;
struct eachquadmem *eq;
struct sys_cfg_data *scd =
(struct sys_cfg_data *)__va(SYS_CFG_DATA_PRIV_ADDR);
nodes_clear(node_online_map);
for_each_node(node) {
if (scd->quads_present31_0 & (1 << node)) {
node_set_online(node);
eq = &scd->eq[node];
/* Convert to pages */
node_start_pfn[node] = MB_TO_PAGES(
eq->hi_shrd_mem_start - eq->priv_mem_size);
node_end_pfn[node] = MB_TO_PAGES(
eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
memory_present(node,
node_start_pfn[node], node_end_pfn[node]);
node_remap_size[node] = node_memmap_size_bytes(node,
node_start_pfn[node],
node_end_pfn[node]);
}
}
}
/**
* init_alloc_remap - Initialize remap allocator for a NUMA node
* @nid: NUMA node to initizlie remap allocator for
*
* NUMA nodes may end up without any lowmem. As allocating pgdat and
* memmap on a different node with lowmem is inefficient, a special
* remap allocator is implemented which can be used by alloc_remap().
*
* For each node, the amount of memory which will be necessary for
* pgdat and memmap is calculated and two memory areas of the size are
* allocated - one in the node and the other in lowmem; then, the area
* in the node is remapped to the lowmem area.
*
* As pgdat and memmap must be allocated in lowmem anyway, this
* doesn't waste lowmem address space; however, the actual lowmem
* which gets remapped over is wasted. The amount shouldn't be
* problematic on machines this feature will be used.
*
* Initialization failure isn't fatal. alloc_remap() is used
* opportunistically and the callers will fall back to other memory
* allocation mechanisms on failure.
*/
void __init init_alloc_remap(int nid, u64 start, u64 end)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long end_pfn = end >> PAGE_SHIFT;
unsigned long size, pfn;
u64 node_pa, remap_pa;
void *remap_va;
/*
* The acpi/srat node info can show hot-add memroy zones where
* memory could be added but not currently present.
*/
printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
nid, start_pfn, end_pfn);
/* calculate the necessary space aligned to large page size */
size = node_memmap_size_bytes(nid, start_pfn, end_pfn);
size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);
size = ALIGN(size, LARGE_PAGE_BYTES);
/* allocate node memory and the lowmem remap area */
node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
if (!node_pa) {
pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
size, nid);
return;
}
memblock_reserve(node_pa, size);
remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
max_low_pfn << PAGE_SHIFT,
size, LARGE_PAGE_BYTES);
if (!remap_pa) {
pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
size, nid);
memblock_free(node_pa, size);
return;
}
memblock_reserve(remap_pa, size);
remap_va = phys_to_virt(remap_pa);
/* perform actual remap */
for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE)
set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT),
(node_pa >> PAGE_SHIFT) + pfn,
PAGE_KERNEL_LARGE);
/* initialize remap allocator parameters */
node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;
node_remap_start_vaddr[nid] = remap_va;
node_remap_end_vaddr[nid] = remap_va + size;
node_remap_alloc_vaddr[nid] = remap_va;
printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n",
nid, node_pa, node_pa + size, remap_va, remap_va + size);
}
static inline void numaq_register_node(int node, struct sys_cfg_data *scd)
{
struct eachquadmem *eq = scd->eq + node;
node_set_online(node);
/* Convert to pages */
node_start_pfn[node] =
MB_TO_PAGES(eq->hi_shrd_mem_start - eq->priv_mem_size);
node_end_pfn[node] =
MB_TO_PAGES(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
e820_register_active_regions(node, node_start_pfn[node],
node_end_pfn[node]);
memory_present(node, node_start_pfn[node], node_end_pfn[node]);
node_remap_size[node] = node_memmap_size_bytes(node,
node_start_pfn[node],
node_end_pfn[node]);
}
int __init get_memcfg_from_srat(void)
{
int i, j, nid;
if (srat_disabled())
goto out_fail;
if (acpi_numa_init() < 0)
goto out_fail;
if (num_memory_chunks == 0) {
printk(KERN_DEBUG
"could not find any ACPI SRAT memory areas.\n");
goto out_fail;
}
/* Calculate total number of nodes in system from PXM bitmap and create
* a set of sequential node IDs starting at zero. (ACPI doesn't seem
* to specify the range of _PXM values.)
*/
/*
* MCD - we no longer HAVE to number nodes sequentially. PXM domain
* numbers could go as high as 256, and MAX_NUMNODES for i386 is typically
* 32, so we will continue numbering them in this manner until MAX_NUMNODES
* approaches MAX_PXM_DOMAINS for i386.
*/
nodes_clear(node_online_map);
for (i = 0; i < MAX_PXM_DOMAINS; i++) {
if (BMAP_TEST(pxm_bitmap, i)) {
int nid = acpi_map_pxm_to_node(i);
node_set_online(nid);
}
}
BUG_ON(num_online_nodes() == 0);
/* set cnode id in memory chunk structure */
for (i = 0; i < num_memory_chunks; i++)
node_memory_chunk[i].nid = pxm_to_node(node_memory_chunk[i].pxm);
printk(KERN_DEBUG "pxm bitmap: ");
for (i = 0; i < sizeof(pxm_bitmap); i++) {
printk(KERN_CONT "%02x ", pxm_bitmap[i]);
}
printk(KERN_CONT "\n");
printk(KERN_DEBUG "Number of logical nodes in system = %d\n",
num_online_nodes());
printk(KERN_DEBUG "Number of memory chunks in system = %d\n",
num_memory_chunks);
for (i = 0; i < MAX_LOCAL_APIC; i++)
set_apicid_to_node(i, pxm_to_node(apicid_to_pxm[i]));
for (j = 0; j < num_memory_chunks; j++){
struct node_memory_chunk_s * chunk = &node_memory_chunk[j];
printk(KERN_DEBUG
"chunk %d nid %d start_pfn %08lx end_pfn %08lx\n",
j, chunk->nid, chunk->start_pfn, chunk->end_pfn);
if (node_read_chunk(chunk->nid, chunk))
continue;
memblock_x86_register_active_regions(chunk->nid, chunk->start_pfn,
min(chunk->end_pfn, max_pfn));
}
/* for out of order entries in SRAT */
sort_node_map();
for_each_online_node(nid) {
unsigned long start = node_start_pfn[nid];
unsigned long end = min(node_end_pfn[nid], max_pfn);
memory_present(nid, start, end);
node_remap_size[nid] = node_memmap_size_bytes(nid, start, end);
}
return 1;
out_fail:
printk(KERN_DEBUG "failed to get NUMA memory information from SRAT"
" table\n");
return 0;
}
/* Parse the ACPI Static Resource Affinity Table */
static int __init acpi20_parse_srat(struct acpi_table_srat *sratp)
{
u8 *start, *end, *p;
int i, j, nid;
start = (u8 *)(&(sratp->reserved) + 1); /* skip header */
p = start;
end = (u8 *)sratp + sratp->header.length;
memset(pxm_bitmap, 0, sizeof(pxm_bitmap)); /* init proximity domain bitmap */
memset(node_memory_chunk, 0, sizeof(node_memory_chunk));
num_memory_chunks = 0;
while (p < end) {
switch (*p) {
case ACPI_SRAT_TYPE_CPU_AFFINITY:
parse_cpu_affinity_structure(p);
break;
case ACPI_SRAT_TYPE_MEMORY_AFFINITY:
parse_memory_affinity_structure(p);
break;
default:
printk("ACPI 2.0 SRAT: unknown entry skipped: type=0x%02X, len=%d\n", p[0], p[1]);
break;
}
p += p[1];
if (p[1] == 0) {
printk("acpi20_parse_srat: Entry length value is zero;"
" can't parse any further!\n");
break;
}
}
if (num_memory_chunks == 0) {
printk("could not finy any ACPI SRAT memory areas.\n");
goto out_fail;
}
/* Calculate total number of nodes in system from PXM bitmap and create
* a set of sequential node IDs starting at zero. (ACPI doesn't seem
* to specify the range of _PXM values.)
*/
/*
* MCD - we no longer HAVE to number nodes sequentially. PXM domain
* numbers could go as high as 256, and MAX_NUMNODES for i386 is typically
* 32, so we will continue numbering them in this manner until MAX_NUMNODES
* approaches MAX_PXM_DOMAINS for i386.
*/
nodes_clear(node_online_map);
for (i = 0; i < MAX_PXM_DOMAINS; i++) {
if (BMAP_TEST(pxm_bitmap, i)) {
int nid = acpi_map_pxm_to_node(i);
node_set_online(nid);
}
}
BUG_ON(num_online_nodes() == 0);
/* set cnode id in memory chunk structure */
for (i = 0; i < num_memory_chunks; i++)
node_memory_chunk[i].nid = pxm_to_node(node_memory_chunk[i].pxm);
printk("pxm bitmap: ");
for (i = 0; i < sizeof(pxm_bitmap); i++) {
printk("%02X ", pxm_bitmap[i]);
}
printk("\n");
printk("Number of logical nodes in system = %d\n", num_online_nodes());
printk("Number of memory chunks in system = %d\n", num_memory_chunks);
for (i = 0; i < MAX_APICID; i++)
apicid_2_node[i] = pxm_to_node(apicid_to_pxm[i]);
for (j = 0; j < num_memory_chunks; j++){
struct node_memory_chunk_s * chunk = &node_memory_chunk[j];
printk("chunk %d nid %d start_pfn %08lx end_pfn %08lx\n",
j, chunk->nid, chunk->start_pfn, chunk->end_pfn);
node_read_chunk(chunk->nid, chunk);
add_active_range(chunk->nid, chunk->start_pfn, chunk->end_pfn);
}
for_each_online_node(nid) {
unsigned long start = node_start_pfn[nid];
unsigned long end = node_end_pfn[nid];
memory_present(nid, start, end);
node_remap_size[nid] = node_memmap_size_bytes(nid, start, end);
}
return 1;
out_fail:
return 0;
}
