static int __init topology_init(void)
{
int i, ret;
#ifdef CONFIG_NEED_MULTIPLE_NODES
for_each_online_node(i)
register_one_node(i);
#endif
for_each_present_cpu(i) {
struct cpu *c = &per_cpu(cpu_devices, i);
c->hotpluggable = 1;
ret = register_cpu(c, i);
if (unlikely(ret))
printk(KERN_WARNING "%s: register_cpu %d failed (%d)\n",
__func__, i, ret);
}
#if defined(CONFIG_NUMA) && !defined(CONFIG_SMP)
for_each_online_node(i)
if (i != numa_node_id())
register_cpu_under_node(raw_smp_processor_id(), i);
#endif
return 0;
}
static int __init topology_init(void)
{
int i, ret;
#ifdef CONFIG_NEED_MULTIPLE_NODES
for_each_online_node(i)
register_one_node(i);
#endif
for_each_present_cpu(i) {
ret = register_cpu(&per_cpu(cpu_devices, i), i);
if (unlikely(ret))
printk(KERN_WARNING "%s: register_cpu %d failed (%d)\n",
__FUNCTION__, i, ret);
}
#if defined(CONFIG_NUMA) && !defined(CONFIG_SMP)
/*
* In the UP case, make sure the CPU association is still
* registered under each node. Without this, sysfs fails
* to make the connection between nodes other than node0
* and cpu0.
*/
for_each_online_node(i)
if (i != numa_node_id())
register_cpu_under_node(raw_smp_processor_id(), i);
#endif
return 0;
}
unsigned long __init numa_free_all_bootmem(void)
{
unsigned long pages = 0;
int i;
for_each_online_node(i)
pages += free_all_bootmem_node(NODE_DATA(i));
<<<<<<< HEAD
/**
* sn_init_pdas - setup node data areas
*
* One time setup for Node Data Area. Called by sn_setup().
*/
static void __init sn_init_pdas(char **cmdline_p)
{
cnodeid_t cnode;
memset(pda->cnodeid_to_nasid_table, -1,
sizeof(pda->cnodeid_to_nasid_table));
for_each_online_node(cnode)
pda->cnodeid_to_nasid_table[cnode] =
pxm_to_nasid(nid_to_pxm_map[cnode]);
numionodes = num_online_nodes();
scan_for_ionodes();
/*
* Allocate & initalize the nodepda for each node.
*/
for_each_online_node(cnode) {
nodepdaindr[cnode] =
alloc_bootmem_node(NODE_DATA(cnode), sizeof(nodepda_t));
memset(nodepdaindr[cnode], 0, sizeof(nodepda_t));
memset(nodepdaindr[cnode]->phys_cpuid, -1,
sizeof(nodepdaindr[cnode]->phys_cpuid));
}
/*
* Allocate & initialize nodepda for TIOs. For now, put them on node 0.
*/
for (cnode = num_online_nodes(); cnode < numionodes; cnode++) {
nodepdaindr[cnode] =
alloc_bootmem_node(NODE_DATA(0), sizeof(nodepda_t));
memset(nodepdaindr[cnode], 0, sizeof(nodepda_t));
}
/*
* Now copy the array of nodepda pointers to each nodepda.
*/
for (cnode = 0; cnode < numionodes; cnode++)
memcpy(nodepdaindr[cnode]->pernode_pdaindr, nodepdaindr,
sizeof(nodepdaindr));
/*
* Set up IO related platform-dependent nodepda fields.
* The following routine actually sets up the hubinfo struct
* in nodepda.
*/
for_each_online_node(cnode) {
bte_init_node(nodepdaindr[cnode], cnode);
}
/*
* Initialize the per node hubdev. This includes IO Nodes and
* headless/memless nodes.
*/
for (cnode = 0; cnode < numionodes; cnode++) {
hubdev_init_node(nodepdaindr[cnode], cnode);
}
}
/*
* The ARC has requested that the filesystem drop entries from the dentry
* and inode caches. This can occur when the ARC needs to free meta data
* blocks but can't because they are all pinned by entries in these caches.
*/
int
zfs_sb_prune(struct super_block *sb, unsigned long nr_to_scan, int *objects)
{
zfs_sb_t *zsb = sb->s_fs_info;
int error = 0;
#if defined(HAVE_SHRINK) || defined(HAVE_SPLIT_SHRINKER_CALLBACK)
struct shrinker *shrinker = &sb->s_shrink;
struct shrink_control sc = {
.nr_to_scan = nr_to_scan,
.gfp_mask = GFP_KERNEL,
};
#endif
ZFS_ENTER(zsb);
#if defined(HAVE_SPLIT_SHRINKER_CALLBACK) && \
defined(SHRINK_CONTROL_HAS_NID) && \
defined(SHRINKER_NUMA_AWARE)
if (sb->s_shrink.flags & SHRINKER_NUMA_AWARE) {
*objects = 0;
for_each_online_node(sc.nid)
*objects += (*shrinker->scan_objects)(shrinker, &sc);
} else {
*objects = (*shrinker->scan_objects)(shrinker, &sc);
}
#elif defined(HAVE_SPLIT_SHRINKER_CALLBACK)
*objects = (*shrinker->scan_objects)(shrinker, &sc);
#elif defined(HAVE_SHRINK)
*objects = (*shrinker->shrink)(shrinker, &sc);
#elif defined(HAVE_D_PRUNE_ALIASES)
#define D_PRUNE_ALIASES_IS_DEFAULT
*objects = zfs_sb_prune_aliases(zsb, nr_to_scan);
#else
#error "No available dentry and inode cache pruning mechanism."
#endif
#if defined(HAVE_D_PRUNE_ALIASES) && !defined(D_PRUNE_ALIASES_IS_DEFAULT)
#undef D_PRUNE_ALIASES_IS_DEFAULT
/*
* Fall back to zfs_sb_prune_aliases if the kernel's per-superblock
* shrinker couldn't free anything, possibly due to the inodes being
* allocated in a different memcg.
*/
if (*objects == 0)
*objects = zfs_sb_prune_aliases(zsb, nr_to_scan);
#endif
ZFS_EXIT(zsb);
dprintf_ds(zsb->z_os->os_dsl_dataset,
"pruning, nr_to_scan=%lu objects=%d error=%d\n",
nr_to_scan, *objects, error);
return (error);
}
static inline unsigned long get_num_physpages(void)
{
int nid;
unsigned long phys_pages = 0;
for_each_online_node(nid)
phys_pages += node_present_pages(nid);
return phys_pages;
}
static int __init topology_init(void)
{
int i;
for_each_online_node(i)
arch_register_node(i);
for_each_cpu(i)
arch_register_cpu(i);
return 0;
}
unsigned long __init numa_free_all_bootmem(void)
{
unsigned long pages = 0;
int i;
for_each_online_node(i)
pages += free_all_bootmem_node(NODE_DATA(i));
pages += free_low_memory_core_early(MAX_NUMNODES);
return pages;
}
static void ip27_machine_halt(void)
{
int i;
#ifdef CONFIG_SMP
smp_send_stop();
#endif
for_each_online_node(i)
REMOTE_HUB_S(COMPACT_TO_NASID_NODEID(i), PROMOP_REG,
PROMOP_RESTART);
LOCAL_HUB_S(NI_PORT_RESET, NPR_PORTRESET | NPR_LOCALRESET);
noreturn;
}
static int __init topology_init(void)
{
int i;
#ifdef CONFIG_NUMA
for_each_online_node(i)
register_one_node(i);
#endif /* CONFIG_NUMA */
for_each_present_cpu(i)
arch_register_cpu(i);
return 0;
}
static ssize_t node_read_distance(struct sys_device * dev, char * buf)
{
int nid = dev->id;
int len = 0;
int i;
/* buf currently PAGE_SIZE, need ~4 chars per node */
BUILD_BUG_ON(MAX_NUMNODES*4 > PAGE_SIZE/2);
for_each_online_node(i)
len += sprintf(buf + len, "%s%d", i ? " " : "", node_distance(nid, i));
len += sprintf(buf + len, "\n");
return len;
}
void __init prom_prepare_cpus(unsigned int max_cpus)
{
cnodeid_t cnode;
for_each_online_node(cnode)
intr_clear_all(COMPACT_TO_NASID_NODEID(cnode));
replicate_kernel_text();
/*
* Assumption to be fixed: we're always booted on logical / physical
* processor 0. While we're always running on logical processor 0
* this still means this is physical processor zero; it might for
* example be disabled in the firwware.
*/
alloc_cpupda(0, 0);
}
static void __init dma32_free_bootmem(void)
{
int node;
if (end_pfn <= MAX_DMA32_PFN)
return;
if (!dma32_bootmem_ptr)
return;
for_each_online_node(node)
free_bootmem_node(NODE_DATA(node), __pa(dma32_bootmem_ptr),
dma32_bootmem_size);
dma32_bootmem_ptr = NULL;
dma32_bootmem_size = 0;
}
static int __init topology_init(void)
{
int i, ret;
#ifdef CONFIG_NUMA
for_each_online_node(i)
register_one_node(i);
#endif /* CONFIG_NUMA */
for_each_present_cpu(i) {
ret = register_cpu(&per_cpu(cpu_devices, i), i);
if (ret)
printk(KERN_WARNING "topology_init: register_cpu %d "
"failed (%d)\n", i, ret);
}
return 0;
}
static ssize_t node_read_distance(struct device *dev,
struct device_attribute *attr, char * buf)
{
int nid = dev->id;
int len = 0;
int i;
/*
* buf is currently PAGE_SIZE in length and each node needs 4 chars
* at the most (distance + space or newline).
*/
BUILD_BUG_ON(MAX_NUMNODES * 4 > PAGE_SIZE);
for_each_online_node(i)
len += sprintf(buf + len, "%s%d", i ? " " : "", node_distance(nid, i));
len += sprintf(buf + len, "\n");
return len;
}
/* XXX How to pass the reboot command to the firmware??? */
static void ip27_machine_restart(char *command)
{
#if 0
int i;
#endif
printk("Reboot started from CPU %d\n", smp_processor_id());
#ifdef CONFIG_SMP
smp_send_stop();
#endif
#if 0
for_each_online_node(i)
REMOTE_HUB_S(COMPACT_TO_NASID_NODEID(i), PROMOP_REG,
PROMOP_REBOOT);
#else
LOCAL_HUB_S(NI_PORT_RESET, NPR_PORTRESET | NPR_LOCALRESET);
#endif
noreturn;
}
/*
* The ARC has requested that the filesystem drop entries from the dentry
* and inode caches. This can occur when the ARC needs to free meta data
* blocks but can't because they are all pinned by entries in these caches.
*/
int
zfs_sb_prune(struct super_block *sb, unsigned long nr_to_scan, int *objects)
{
zfs_sb_t *zsb = sb->s_fs_info;
int error = 0;
#if defined(HAVE_SHRINK) || defined(HAVE_SPLIT_SHRINKER_CALLBACK)
struct shrinker *shrinker = &sb->s_shrink;
struct shrink_control sc = {
.nr_to_scan = nr_to_scan,
.gfp_mask = GFP_KERNEL,
};
#endif
ZFS_ENTER(zsb);
#if defined(HAVE_SPLIT_SHRINKER_CALLBACK) && \
defined(SHRINK_CONTROL_HAS_NID) && \
defined(SHRINKER_NUMA_AWARE)
if (sb->s_shrink.flags & SHRINKER_NUMA_AWARE) {
*objects = 0;
for_each_online_node(sc.nid)
*objects += (*shrinker->scan_objects)(shrinker, &sc);
} else {
*objects = (*shrinker->scan_objects)(shrinker, &sc);
}
#elif defined(HAVE_SPLIT_SHRINKER_CALLBACK)
*objects = (*shrinker->scan_objects)(shrinker, &sc);
#elif defined(HAVE_SHRINK)
*objects = (*shrinker->shrink)(shrinker, &sc);
#elif defined(HAVE_D_PRUNE_ALIASES)
*objects = zfs_sb_prune_aliases(zsb, nr_to_scan);
#else
#error "No available dentry and inode cache pruning mechanism."
#endif
ZFS_EXIT(zsb);
dprintf_ds(zsb->z_os->os_dsl_dataset,
"pruning, nr_to_scan=%lu objects=%d error=%d\n",
nr_to_scan, *objects, error);
return (error);
}
static int __init topology_init(void)
{
int i, ret;
#ifdef CONFIG_NUMA
for_each_online_node(i)
register_one_node(i);
#endif
for_each_present_cpu(i) {
struct cpu *c = &per_cpu(cpu_devices, i);
c->hotpluggable = 1;
ret = register_cpu(c, i);
if (ret)
printk(KERN_WARNING "topology_init: register_cpu %d "
"failed (%d)\n", i, ret);
}
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
}
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
}
