/* Allocate NODE_DATA for a node on the local memory */
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;
/*
* Allocate node data. Try node-local memory and then any node.
* Never allocate in DMA zone.
*/
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 */
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);
}
void cpu_node_probe(void)
{
int i, highest = 0;
gda_t *gdap = GDA;
/*
* Initialize the arrays to invalid nodeid (-1)
*/
for (i = 0; i < MAX_COMPACT_NODES; i++)
compact_to_nasid_node[i] = INVALID_NASID;
for (i = 0; i < MAX_NASIDS; i++)
nasid_to_compact_node[i] = INVALID_CNODEID;
for (i = 0; i < MAXCPUS; i++)
cpuid_to_compact_node[i] = INVALID_CNODEID;
/*
* MCD - this whole "compact node" stuff can probably be dropped,
* as we can handle sparse numbering now
*/
nodes_clear(node_online_map);
for (i = 0; i < MAX_COMPACT_NODES; i++) {
nasid_t nasid = gdap->g_nasidtable[i];
if (nasid == INVALID_NASID)
break;
compact_to_nasid_node[i] = nasid;
nasid_to_compact_node[nasid] = i;
node_set_online(num_online_nodes());
highest = do_cpumask(i, nasid, highest);
}
printk("Discovered %d cpus on %d nodes\n", highest + 1, num_online_nodes());
}
/*
* 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]);
}
}
}
void __init setup_arch(char **cmdline_p)
{
ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV);
boot_cpu_data.cpu_clock = M32R_CPUCLK;
boot_cpu_data.bus_clock = M32R_BUSCLK;
boot_cpu_data.timer_divide = M32R_TIMER_DIVIDE;
#ifdef CONFIG_BLK_DEV_RAM
rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK;
rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0);
rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0);
#endif
if (!MOUNT_ROOT_RDONLY)
root_mountflags &= ~MS_RDONLY;
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
conswitchp = &dummy_con;
#endif
#endif
#ifdef CONFIG_DISCONTIGMEM
nodes_clear(node_online_map);
node_set_online(0);
node_set_online(1);
#endif /* CONFIG_DISCONTIGMEM */
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = (unsigned long) _end;
code_resource.start = virt_to_phys(_text);
code_resource.end = virt_to_phys(_etext)-1;
data_resource.start = virt_to_phys(_etext);
data_resource.end = virt_to_phys(_edata)-1;
parse_mem_cmdline(cmdline_p);
setup_memory();
paging_init();
}
/* 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);
bool remapped = false;
u64 nd_pa;
void *nd;
int tnid;
/*
* Don't confuse VM with a node that doesn't have the
* minimum amount of memory:
*/
if (end && (end - start) < NODE_MIN_SIZE)
return;
/* initialize remap allocator before aligning to ZONE_ALIGN */
init_alloc_remap(nid, start, end);
start = roundup(start, ZONE_ALIGN);
printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
nid, start, end - 1);
/*
* Allocate node data. Try remap allocator first, node-local
* memory and then any node. Never allocate in DMA zone.
*/
nd = alloc_remap(nid, nd_size);
if (nd) {
nd_pa = __pa(nd);
remapped = true;
} else {
nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
if (!nd_pa) {
pr_err("Cannot find %zu bytes in node %d\n",
nd_size, nid);
return;
}
nd = __va(nd_pa);
}
/* report and initialize */
printk(KERN_INFO " NODE_DATA [mem %#010Lx-%#010Lx]%s\n",
nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : "");
tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
if (!remapped && 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_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);
}
// start_pfn : 뱅크 0 시작 주소의 물리 small page 번호 (0x20000)
// end_pfn : 뱅크 0의 마지막 주소의 물리 small page 번호 (0x4f800)
static void __init arm_bootmem_init(unsigned long start_pfn,
unsigned long end_pfn)
{
struct memblock_region *reg;
unsigned int boot_pages;
phys_addr_t bitmap;
pg_data_t *pgdat;
// pg_data_t : struct pglist_data
/*
* Allocate the bootmem bitmap page. This must be in a region
* of memory which has already been mapped.
*/
boot_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
// boot_pages : 6
// start_pfn ~ end_pfn 까지를 bitmap으로 바꿨을 때 총 프레임의 갯수가 반환됨.
// boot_pages << PAGE_SHIFT : 0x6000, L1_CACHE_BYTES : 64, _pfn_to_phys(end_pfn) : 0x4F800000
bitmap = memblock_alloc_base(boot_pages << PAGE_SHIFT, L1_CACHE_BYTES,
__pfn_to_phys(end_pfn));
// non-reserved 영역에서 비트맵용 영역을 만들어 가져옴
// 영역의 시작 주소가 반환됨(물리)
/*
* Initialise the bootmem allocator, handing the
* memory banks over to bootmem.
*/
node_set_online(0); // 비어 있는 함수임
pgdat = NODE_DATA(0);
//*pgdat = contig_page_data
//
// .bdata = &bootmem_node_data[0]
// 현재는 0으로 되어 있는 값임
//
init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn);
// bdata_list 에 등록
// bitmap 값을 0xFF로 초기화
/* Free the lowmem regions from memblock into bootmem. */
for_each_memblock(memory, reg) {
// for (reg = memblock.memory.regions; reg < (memblock.memory.regions + memblock.memory.cnt), reg++)
unsigned long start = memblock_region_memory_base_pfn(reg);
unsigned long end = memblock_region_memory_end_pfn(reg);
// start : 0x20000
// end : 0xA0000
if (end >= end_pfn)
end = end_pfn;
if (start >= end)
break;
// start : 0x20000000, (end - start) << PAGE_SHIFT : 0x2F800000
free_bootmem(__pfn_to_phys(start), (end - start) << PAGE_SHIFT);
// start부터 end에 해당하는 bitmap을 전부 0으로 설정
// 일단 전부 FREE로 만듬
}
// ARM10C 20131207
// min: 0x20000, max_low: 0x4f800
static void __init arm_bootmem_init(unsigned long start_pfn,
unsigned long end_pfn)
{
struct memblock_region *reg;
unsigned int boot_pages;
phys_addr_t bitmap;
pg_data_t *pgdat;
/*
* Allocate the bootmem bitmap page. This must be in a region
* of memory which has already been mapped.
*/
// start_pfn: 0x20000, end_pfn: 0x4f800, end_pfn - start_pfn: 0x2f800
// boot_pages: 0x6
boot_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
// boot_pages << PAGE_SHIFT: 0x6000, L1_CACHE_BYTES: 64
// __pfn_to_phys(0x4f800); 0x4f800000
bitmap = memblock_alloc_base(boot_pages << PAGE_SHIFT, L1_CACHE_BYTES,
__pfn_to_phys(end_pfn));
/*
* Initialise the bootmem allocator, handing the
* memory banks over to bootmem.
*/
node_set_online(0);
// pglist_data.bdata 의 bootmem_node_data 주소로 설정
pgdat = NODE_DATA(0);
// pgdat: ?, __phys_to_pfn(bitmap): ?, start_pfn: 0x20000, end_pfn: 0x4f800
init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn);
/* Free the lowmem regions from memblock into bootmem. */
for_each_memblock(memory, reg) {
// start: 0x20000
unsigned long start = memblock_region_memory_base_pfn(reg);
// end: 0xA0000
unsigned long end = memblock_region_memory_end_pfn(reg);
// end: 0xA0000, end_pfn: 0x4f800
if (end >= end_pfn)
// end: 0x4f800
end = end_pfn;
// start: 0x20000, end: 0x4f800
if (start >= end)
break;
// __pfn_to_phys(0x20000): 0x20000000, (end - start) << PAGE_SHIFT: 0x2f800000
free_bootmem(__pfn_to_phys(start), (end - start) << PAGE_SHIFT);
}
/* 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;
/*
* Don't confuse VM with a node that doesn't have the
* minimum amount of memory:
*/
if (end && (end - start) < NODE_MIN_SIZE)
return;
start = roundup(start, ZONE_ALIGN);
printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
nid, start, end - 1);
/*
* Allocate node data. Try node-local memory and then any node.
* Never allocate in DMA zone.
*/
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 */
printk(KERN_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)
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_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);
}
int add_memory(int nid, u64 start, u64 size)
{
pg_data_t *pgdat = NULL;
int new_pgdat = 0;
struct resource *res;
int ret;
res = register_memory_resource(start, size);
if (!res)
return -EEXIST;
if (!node_online(nid)) {
pgdat = hotadd_new_pgdat(nid, start);
if (!pgdat)
return -ENOMEM;
new_pgdat = 1;
}
/* call arch's memory hotadd */
ret = arch_add_memory(nid, start, size);
if (ret < 0)
goto error;
/* we online node here. we can't roll back from here. */
node_set_online(nid);
cpuset_track_online_nodes();
if (new_pgdat) {
ret = register_one_node(nid);
/*
* If sysfs file of new node can't create, cpu on the node
* can't be hot-added. There is no rollback way now.
* So, check by BUG_ON() to catch it reluctantly..
*/
BUG_ON(ret);
}
return ret;
error:
/* rollback pgdat allocation and others */
if (new_pgdat)
rollback_node_hotadd(nid, pgdat);
if (res)
release_memory_resource(res);
return ret;
}
void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
{
unsigned long bootmap_pages;
unsigned long start_pfn, end_pfn;
unsigned long bootmem_paddr;
/* Don't allow bogus node assignment */
BUG_ON(nid > MAX_NUMNODES || nid <= 0);
start_pfn = start >> PAGE_SHIFT;
end_pfn = end >> PAGE_SHIFT;
pmb_bolt_mapping((unsigned long)__va(start), start, end - start,
PAGE_KERNEL);
lmb_add(start, end - start);
__add_active_range(nid, start_pfn, end_pfn);
/* Node-local pgdat */
NODE_DATA(nid) = __va(lmb_alloc_base(sizeof(struct pglist_data),
SMP_CACHE_BYTES, end));
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
NODE_DATA(nid)->node_start_pfn = start_pfn;
NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
/* Node-local bootmap */
bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
bootmem_paddr = lmb_alloc_base(bootmap_pages << PAGE_SHIFT,
PAGE_SIZE, end);
init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
start_pfn, end_pfn);
free_bootmem_with_active_regions(nid, end_pfn);
/* Reserve the pgdat and bootmap space with the bootmem allocator */
reserve_bootmem_node(NODE_DATA(nid), start_pfn << PAGE_SHIFT,
sizeof(struct pglist_data), BOOTMEM_DEFAULT);
reserve_bootmem_node(NODE_DATA(nid), bootmem_paddr,
bootmap_pages << PAGE_SHIFT, BOOTMEM_DEFAULT);
/* It's up */
node_set_online(nid);
/* Kick sparsemem */
sparse_memory_present_with_active_regions(nid);
}
static void __init MP_translation_info(struct mpc_trans *m)
{
printk(KERN_INFO
"Translation: record %d, type %d, quad %d, global %d, local %d\n",
mpc_record, m->trans_type, m->trans_quad, m->trans_global,
m->trans_local);
if (mpc_record >= MAX_MPC_ENTRY)
printk(KERN_ERR "MAX_MPC_ENTRY exceeded!\n");
else
translation_table[mpc_record] = m; /* stash this for later */
if (m->trans_quad < MAX_NUMNODES && !node_online(m->trans_quad))
node_set_online(m->trans_quad);
}
void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
{
unsigned long bootmap_pages, bootmap_start, bootmap_size;
unsigned long start_pfn, free_pfn, end_pfn;
/* Don't allow bogus node assignment */
BUG_ON(nid > MAX_NUMNODES || nid == 0);
/*
* The free pfn starts at the beginning of the range, and is
* advanced as necessary for pgdat and node map allocations.
*/
free_pfn = start_pfn = start >> PAGE_SHIFT;
end_pfn = end >> PAGE_SHIFT;
__add_active_range(nid, start_pfn, end_pfn);
/* Node-local pgdat */
NODE_DATA(nid) = pfn_to_kaddr(free_pfn);
free_pfn += PFN_UP(sizeof(struct pglist_data));
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
NODE_DATA(nid)->node_start_pfn = start_pfn;
NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
/* Node-local bootmap */
bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
bootmap_start = (unsigned long)pfn_to_kaddr(free_pfn);
bootmap_size = init_bootmem_node(NODE_DATA(nid), free_pfn, start_pfn,
end_pfn);
free_bootmem_with_active_regions(nid, end_pfn);
/* Reserve the pgdat and bootmap space with the bootmem allocator */
reserve_bootmem_node(NODE_DATA(nid), start_pfn << PAGE_SHIFT,
sizeof(struct pglist_data), BOOTMEM_DEFAULT);
reserve_bootmem_node(NODE_DATA(nid), free_pfn << PAGE_SHIFT,
bootmap_pages << PAGE_SHIFT, BOOTMEM_DEFAULT);
/* It's up */
node_set_online(nid);
/* Kick sparsemem */
sparse_memory_present_with_active_regions(nid);
}
static void __init arm_bootmem_init(struct meminfo *mi,
unsigned long start_pfn, unsigned long end_pfn)
{
unsigned int boot_pages;
phys_addr_t bitmap;
pg_data_t *pgdat;
int i;
/*
* Allocate the bootmem bitmap page. This must be in a region
* of memory which has already been mapped.
*/
boot_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
bitmap = memblock_alloc_base(boot_pages << PAGE_SHIFT, L1_CACHE_BYTES,
__pfn_to_phys(end_pfn));
/*
* Initialise the bootmem allocator, handing the
* memory banks over to bootmem.
*/
node_set_online(0);
pgdat = NODE_DATA(0);
init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn);
for_each_bank(i, mi) {
struct membank *bank = &mi->bank[i];
if (!bank->highmem)
free_bootmem(bank_phys_start(bank), bank_phys_size(bank));
}
/*
* Reserve the memblock reserved regions in bootmem.
*/
for (i = 0; i < memblock.reserved.cnt; i++) {
phys_addr_t start = memblock_start_pfn(&memblock.reserved, i);
if (start >= start_pfn &&
memblock_end_pfn(&memblock.reserved, i) <= end_pfn)
reserve_bootmem_node(pgdat, __pfn_to_phys(start),
memblock_size_bytes(&memblock.reserved, i),
BOOTMEM_DEFAULT);
}
}
/*
* Function: smp_dump_qct()
*
* Description: gets memory layout from the quad config table. This
* function also increments numnodes with the number of 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);
numnodes = 0;
for(node = 0; node < MAX_NUMNODES; node++) {
if(scd->quads_present31_0 & (1 << node)) {
node_set_online(node);
numnodes++;
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);
}
}
}
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);
}
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]);
}
static void __init arm_bootmem_init(unsigned long start_pfn,
unsigned long end_pfn)
{
struct memblock_region *reg;
unsigned int boot_pages;
phys_addr_t bitmap;
pg_data_t *pgdat;
/*
* Allocate the bootmem bitmap page. This must be in a region
* of memory which has already been mapped.
*/
boot_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
bitmap = memblock_alloc_base(boot_pages << PAGE_SHIFT, L1_CACHE_BYTES,
__pfn_to_phys(end_pfn));
/*
* Initialise the bootmem allocator, handing the
* memory banks over to bootmem.
*/
node_set_online(0);
pgdat = NODE_DATA(0);
init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn);
/* Free the lowmem regions from memblock into bootmem. */
for_each_memblock(memory, reg) {
unsigned long start = memblock_region_memory_base_pfn(reg);
unsigned long end = memblock_region_memory_end_pfn(reg);
if (end >= end_pfn)
end = end_pfn;
if (start >= end)
break;
free_bootmem(__pfn_to_phys(start), (end - start) << PAGE_SHIFT);
}
/*
* First memory setup routine called from setup_arch()
* 1. setup swapper's mm @init_mm
* 2. Count the pages we have and setup bootmem allocator
* 3. zone setup
*/
void __init setup_arch_memory(void)
{
unsigned long zones_size[MAX_NR_ZONES];
unsigned long zones_holes[MAX_NR_ZONES];
init_mm.start_code = (unsigned long)_text;
init_mm.end_code = (unsigned long)_etext;
init_mm.end_data = (unsigned long)_edata;
init_mm.brk = (unsigned long)_end;
/* first page of system - kernel .vector starts here */
min_low_pfn = ARCH_PFN_OFFSET;
/* Last usable page of low mem */
max_low_pfn = max_pfn = PFN_DOWN(low_mem_start + low_mem_sz);
#ifdef CONFIG_FLATMEM
/* pfn_valid() uses this */
max_mapnr = max_low_pfn - min_low_pfn;
#endif
/*------------- bootmem allocator setup -----------------------*/
/*
* seed the bootmem allocator after any DT memory node parsing or
* "mem=xxx" cmdline overrides have potentially updated @arc_mem_sz
*
* Only low mem is added, otherwise we have crashes when allocating
* mem_map[] itself. NO_BOOTMEM allocates mem_map[] at the end of
* avail memory, ending in highmem with a > 32-bit address. However
* it then tries to memset it with a truncaed 32-bit handle, causing
* the crash
*/
memblock_add_node(low_mem_start, low_mem_sz, 0);
memblock_reserve(CONFIG_LINUX_LINK_BASE,
__pa(_end) - CONFIG_LINUX_LINK_BASE);
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start)
memblock_reserve(__pa(initrd_start), initrd_end - initrd_start);
#endif
early_init_fdt_reserve_self();
early_init_fdt_scan_reserved_mem();
memblock_dump_all();
/*----------------- node/zones setup --------------------------*/
memset(zones_size, 0, sizeof(zones_size));
memset(zones_holes, 0, sizeof(zones_holes));
zones_size[ZONE_NORMAL] = max_low_pfn - min_low_pfn;
zones_holes[ZONE_NORMAL] = 0;
/*
* We can't use the helper free_area_init(zones[]) because it uses
* PAGE_OFFSET to compute the @min_low_pfn which would be wrong
* when our kernel doesn't start at PAGE_OFFSET, i.e.
* PAGE_OFFSET != CONFIG_LINUX_RAM_BASE
*/
free_area_init_node(0, /* node-id */
zones_size, /* num pages per zone */
min_low_pfn, /* first pfn of node */
zones_holes); /* holes */
#ifdef CONFIG_HIGHMEM
/*
* Populate a new node with highmem
*
* On ARC (w/o PAE) HIGHMEM addresses are actually smaller (0 based)
* than addresses in normal ala low memory (0x8000_0000 based).
* Even with PAE, the huge peripheral space hole would waste a lot of
* mem with single mem_map[]. This warrants a mem_map per region design.
* Thus HIGHMEM on ARC is imlemented with DISCONTIGMEM.
*
* DISCONTIGMEM in turns requires multiple nodes. node 0 above is
* populated with normal memory zone while node 1 only has highmem
*/
node_set_online(1);
min_high_pfn = PFN_DOWN(high_mem_start);
max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz);
zones_size[ZONE_NORMAL] = 0;
zones_holes[ZONE_NORMAL] = 0;
zones_size[ZONE_HIGHMEM] = max_high_pfn - min_high_pfn;
zones_holes[ZONE_HIGHMEM] = 0;
free_area_init_node(1, /* node-id */
zones_size, /* num pages per zone */
min_high_pfn, /* first pfn of node */
zones_holes); /* holes */
high_memory = (void *)(min_high_pfn << PAGE_SHIFT);
kmap_init();
#endif
}
void __init setup_bootmem_allocator(unsigned long free_pfn)
{
unsigned long bootmap_size;
/*
* Find a proper area for the bootmem bitmap. After this
* bootstrap step all allocations (until the page allocator
* is intact) must be done via bootmem_alloc().
*/
bootmap_size = init_bootmem_node(NODE_DATA(0), free_pfn,
min_low_pfn, max_low_pfn);
add_active_range(0, min_low_pfn, max_low_pfn);
register_bootmem_low_pages();
node_set_online(0);
/*
* Reserve the kernel text and
* Reserve the bootmem bitmap. We do this in two steps (first step
* was init_bootmem()), because this catches the (definitely buggy)
* case of us accidentally initializing the bootmem allocator with
* an invalid RAM area.
*/
reserve_bootmem(__MEMORY_START+PAGE_SIZE,
(PFN_PHYS(free_pfn)+bootmap_size+PAGE_SIZE-1)-__MEMORY_START);
/*
* reserve physical page 0 - it's a special BIOS page on many boxes,
* enabling clean reboots, SMP operation, laptop functions.
*/
reserve_bootmem(__MEMORY_START, PAGE_SIZE);
sparse_memory_present_with_active_regions(0);
#ifdef CONFIG_BLK_DEV_INITRD
ROOT_DEV = MKDEV(RAMDISK_MAJOR, 0);
if (&__rd_start != &__rd_end) {
LOADER_TYPE = 1;
INITRD_START = PHYSADDR((unsigned long)&__rd_start) -
__MEMORY_START;
INITRD_SIZE = (unsigned long)&__rd_end -
(unsigned long)&__rd_start;
}
if (LOADER_TYPE && INITRD_START) {
if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) {
reserve_bootmem(INITRD_START + __MEMORY_START,
INITRD_SIZE);
initrd_start = INITRD_START + PAGE_OFFSET +
__MEMORY_START;
initrd_end = initrd_start + INITRD_SIZE;
} else {
printk("initrd extends beyond end of memory "
"(0x%08lx > 0x%08lx)\ndisabling initrd\n",
INITRD_START + INITRD_SIZE,
max_low_pfn << PAGE_SHIFT);
initrd_start = 0;
}
}
#endif
#ifdef CONFIG_KEXEC
if (crashk_res.start != crashk_res.end)
reserve_bootmem(crashk_res.start,
crashk_res.end - crashk_res.start + 1);
#endif
}
void __init acpi_numa_arch_fixup(void)
{
int i, j, node_from, node_to;
/* If there's no SRAT, fix the phys_id and mark node 0 online */
if (srat_num_cpus == 0) {
node_set_online(0);
node_cpuid[0].phys_id = hard_smp_processor_id();
return;
}
/*
* MCD - This can probably be dropped now. No need for pxm ID to node ID
* mapping with sparse node numbering iff MAX_PXM_DOMAINS <= MAX_NUMNODES.
*/
nodes_clear(node_online_map);
for (i = 0; i < MAX_PXM_DOMAINS; i++) {
if (pxm_bit_test(i)) {
int nid = acpi_map_pxm_to_node(i);
node_set_online(nid);
}
}
/* set logical node id in memory chunk structure */
for (i = 0; i < num_node_memblks; i++)
node_memblk[i].nid = pxm_to_node(node_memblk[i].nid);
/* assign memory bank numbers for each chunk on each node */
for_each_online_node(i) {
int bank;
bank = 0;
for (j = 0; j < num_node_memblks; j++)
if (node_memblk[j].nid == i)
node_memblk[j].bank = bank++;
}
/* set logical node id in cpu structure */
for_each_possible_early_cpu(i)
node_cpuid[i].nid = pxm_to_node(node_cpuid[i].nid);
printk(KERN_INFO "Number of logical nodes in system = %d\n",
num_online_nodes());
printk(KERN_INFO "Number of memory chunks in system = %d\n",
num_node_memblks);
if (!slit_table)
return;
memset(numa_slit, -1, sizeof(numa_slit));
for (i = 0; i < slit_table->locality_count; i++) {
if (!pxm_bit_test(i))
continue;
node_from = pxm_to_node(i);
for (j = 0; j < slit_table->locality_count; j++) {
if (!pxm_bit_test(j))
continue;
node_to = pxm_to_node(j);
node_distance(node_from, node_to) =
slit_table->entry[i * slit_table->locality_count + j];
}
}
#ifdef SLIT_DEBUG
printk("ACPI 2.0 SLIT locality table:\n");
for_each_online_node(i) {
for_each_online_node(j)
printk("%03d ", node_distance(i, j));
printk("\n");
}
#endif
}
void __init
acpi_numa_arch_fixup (void)
{
int i, j, node_from, node_to;
/* If there's no SRAT, fix the phys_id and mark node 0 online */
if (srat_num_cpus == 0) {
node_set_online(0);
node_cpuid[0].phys_id = hard_smp_processor_id();
return;
}
/* calculate total number of nodes in system from PXM bitmap */
numnodes = 0; /* init total nodes in system */
memset(pxm_to_nid_map, -1, sizeof(pxm_to_nid_map));
memset(nid_to_pxm_map, -1, sizeof(nid_to_pxm_map));
for (i = 0; i < MAX_PXM_DOMAINS; i++) {
if (pxm_bit_test(i)) {
pxm_to_nid_map[i] = numnodes;
node_set_online(numnodes);
nid_to_pxm_map[numnodes++] = i;
}
}
/* set logical node id in memory chunk structure */
for (i = 0; i < num_node_memblks; i++)
node_memblk[i].nid = pxm_to_nid_map[node_memblk[i].nid];
/* assign memory bank numbers for each chunk on each node */
for (i = 0; i < numnodes; i++) {
int bank;
bank = 0;
for (j = 0; j < num_node_memblks; j++)
if (node_memblk[j].nid == i)
node_memblk[j].bank = bank++;
}
/* set logical node id in cpu structure */
for (i = 0; i < srat_num_cpus; i++)
node_cpuid[i].nid = pxm_to_nid_map[node_cpuid[i].nid];
printk(KERN_INFO "Number of logical nodes in system = %d\n", numnodes);
printk(KERN_INFO "Number of memory chunks in system = %d\n", num_node_memblks);
if (!slit_table) return;
memset(numa_slit, -1, sizeof(numa_slit));
for (i=0; i<slit_table->localities; i++) {
if (!pxm_bit_test(i))
continue;
node_from = pxm_to_nid_map[i];
for (j=0; j<slit_table->localities; j++) {
if (!pxm_bit_test(j))
continue;
node_to = pxm_to_nid_map[j];
node_distance(node_from, node_to) =
slit_table->entry[i*slit_table->localities + j];
}
}
#ifdef SLIT_DEBUG
printk("ACPI 2.0 SLIT locality table:\n");
for (i = 0; i < numnodes; i++) {
for (j = 0; j < numnodes; j++)
printk("%03d ", node_distance(i,j));
printk("\n");
}
#endif
}
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;
}
static int __init parse_numa_properties(void)
{
struct device_node *cpu = NULL;
struct device_node *memory = NULL;
int depth;
int max_domain = 0;
long entries = lmb_end_of_DRAM() >> MEMORY_INCREMENT_SHIFT;
unsigned long i;
if (strstr(saved_command_line, "numa=off")) {
printk(KERN_WARNING "NUMA disabled by user\n");
return -1;
}
numa_memory_lookup_table =
(char *)abs_to_virt(lmb_alloc(entries * sizeof(char), 1));
for (i = 0; i < entries ; i++)
numa_memory_lookup_table[i] = ARRAY_INITIALISER;
depth = find_min_common_depth();
printk(KERN_INFO "NUMA associativity depth for CPU/Memory: %d\n", depth);
if (depth < 0)
return depth;
for_each_cpu(i) {
int numa_domain;
cpu = find_cpu_node(i);
if (cpu) {
numa_domain = of_node_numa_domain(cpu, depth);
of_node_put(cpu);
if (numa_domain >= MAX_NUMNODES) {
/*
* POWER4 LPAR uses 0xffff as invalid node,
* dont warn in this case.
*/
if (numa_domain != 0xffff)
printk(KERN_ERR "WARNING: cpu %ld "
"maps to invalid NUMA node %d\n",
i, numa_domain);
numa_domain = 0;
}
} else {
printk(KERN_ERR "WARNING: no NUMA information for "
"cpu %ld\n", i);
numa_domain = 0;
}
node_set_online(numa_domain);
if (max_domain < numa_domain)
max_domain = numa_domain;
map_cpu_to_node(i, numa_domain);
}
memory = NULL;
while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
unsigned long start;
unsigned long size;
int numa_domain;
int ranges;
unsigned int *memcell_buf;
unsigned int len;
memcell_buf = (unsigned int *)get_property(memory, "reg", &len);
if (!memcell_buf || len <= 0)
continue;
ranges = memory->n_addrs;
new_range:
/* these are order-sensitive, and modify the buffer pointer */
start = read_cell_ul(memory, &memcell_buf);
size = read_cell_ul(memory, &memcell_buf);
start = _ALIGN_DOWN(start, MEMORY_INCREMENT);
size = _ALIGN_UP(size, MEMORY_INCREMENT);
numa_domain = of_node_numa_domain(memory, depth);
if (numa_domain >= MAX_NUMNODES) {
if (numa_domain != 0xffff)
printk(KERN_ERR "WARNING: memory at %lx maps "
"to invalid NUMA node %d\n", start,
numa_domain);
numa_domain = 0;
}
node_set_online(numa_domain);
if (max_domain < numa_domain)
max_domain = numa_domain;
/*
* For backwards compatibility, OF splits the first node
* into two regions (the first being 0-4GB). Check for
* this simple case and complain if there is a gap in
* memory
*/
if (node_data[numa_domain].node_spanned_pages) {
unsigned long shouldstart =
node_data[numa_domain].node_start_pfn +
node_data[numa_domain].node_spanned_pages;
if (shouldstart != (start / PAGE_SIZE)) {
printk(KERN_ERR "Hole in node, disabling "
"region start %lx length %lx\n",
start, size);
continue;
}
node_data[numa_domain].node_spanned_pages +=
size / PAGE_SIZE;
} else {
node_data[numa_domain].node_start_pfn =
start / PAGE_SIZE;
node_data[numa_domain].node_spanned_pages =
size / PAGE_SIZE;
}
for (i = start ; i < (start+size); i += MEMORY_INCREMENT)
numa_memory_lookup_table[i >> MEMORY_INCREMENT_SHIFT] =
numa_domain;
dbg("memory region %lx to %lx maps to domain %d\n",
start, start+size, numa_domain);
ranges--;
if (ranges)
goto new_range;
}
numnodes = max_domain + 1;
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;
}
void __init acpi_numa_arch_fixup(void)
{
int i, j, node_from, node_to;
if (srat_num_cpus == 0) {
node_set_online(0);
node_cpuid[0].phys_id = hard_smp_processor_id();
return;
}
nodes_clear(node_online_map);
for (i = 0; i < MAX_PXM_DOMAINS; i++) {
if (pxm_bit_test(i)) {
int nid = acpi_map_pxm_to_node(i);
node_set_online(nid);
}
}
for (i = 0; i < num_node_memblks; i++)
node_memblk[i].nid = pxm_to_node(node_memblk[i].nid);
for_each_online_node(i) {
int bank;
bank = 0;
for (j = 0; j < num_node_memblks; j++)
if (node_memblk[j].nid == i)
node_memblk[j].bank = bank++;
}
for_each_possible_early_cpu(i)
node_cpuid[i].nid = pxm_to_node(node_cpuid[i].nid);
printk(KERN_INFO "Number of logical nodes in system = %d\n",
num_online_nodes());
printk(KERN_INFO "Number of memory chunks in system = %d\n",
num_node_memblks);
if (!slit_table) {
for (i = 0; i < MAX_NUMNODES; i++)
for (j = 0; j < MAX_NUMNODES; j++)
node_distance(i, j) = i == j ? LOCAL_DISTANCE :
REMOTE_DISTANCE;
return;
}
memset(numa_slit, -1, sizeof(numa_slit));
for (i = 0; i < slit_table->locality_count; i++) {
if (!pxm_bit_test(i))
continue;
node_from = pxm_to_node(i);
for (j = 0; j < slit_table->locality_count; j++) {
if (!pxm_bit_test(j))
continue;
node_to = pxm_to_node(j);
node_distance(node_from, node_to) =
slit_table->entry[i * slit_table->locality_count + j];
}
}
#ifdef SLIT_DEBUG
printk("ACPI 2.0 SLIT locality table:\n");
for_each_online_node(i) {
for_each_online_node(j)
printk("%03d ", node_distance(i, j));
printk("\n");
}
#endif
}
