int __cpuinit cpu_up(unsigned int cpu)
{
int err = 0;
#ifdef CONFIG_MEMORY_HOTPLUG
int nid;
pg_data_t *pgdat;
#endif
if (!cpu_possible(cpu)) {
printk(KERN_ERR "can't online cpu %d because it is not "
"configured as may-hotadd at boot time\n", cpu);
#if defined(CONFIG_IA64)
printk(KERN_ERR "please check additional_cpus= boot "
"parameter\n");
#endif
return -EINVAL;
}
#ifdef CONFIG_MEMORY_HOTPLUG
nid = cpu_to_node(cpu);
if (!node_online(nid)) {
err = mem_online_node(nid);
if (err)
return err;
}
pgdat = NODE_DATA(nid);
if (!pgdat) {
printk(KERN_ERR
"Can't online cpu %d due to NULL pgdat\n", cpu);
return -ENOMEM;
}
if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
mutex_lock(&zonelists_mutex);
build_all_zonelists(NULL);
mutex_unlock(&zonelists_mutex);
}
#endif
cpu_maps_update_begin();
if (cpu_hotplug_disabled) {
err = -EBUSY;
goto out;
}
err = _cpu_up(cpu, 0);
out:
cpu_maps_update_done();
return err;
}
void arch_unregister_cpu(int num) {
struct node *parent = NULL;
#ifdef CONFIG_NUMA
int node = cpu_to_node(num);
if (node_online(node))
parent = &node_devices[node].node;
#endif /* CONFIG_NUMA */
return unregister_cpu(&cpu_devices[num].cpu, parent);
}
static int __init topology_init(void)
{
int i;
for (i = 0; i < MAX_NUMNODES; i++) {
if (node_online(i))
arch_register_node(i);
}
for (i = 0; i < NR_CPUS; i++)
if (cpu_possible(i)) arch_register_cpu(i);
return 0;
}
static acpi_status __devinit
acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret)
{
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
union acpi_object *obj;
struct acpi_madt_io_sapic *iosapic;
unsigned int gsi_base;
int pxm, node;
/* Only care about objects w/ a method that returns the MADT */
if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
return AE_OK;
if (!buffer.length || !buffer.pointer)
return AE_OK;
obj = buffer.pointer;
if (obj->type != ACPI_TYPE_BUFFER ||
obj->buffer.length < sizeof(*iosapic)) {
kfree(buffer.pointer);
return AE_OK;
}
iosapic = (struct acpi_madt_io_sapic *)obj->buffer.pointer;
if (iosapic->header.type != ACPI_MADT_TYPE_IO_SAPIC) {
kfree(buffer.pointer);
return AE_OK;
}
gsi_base = iosapic->global_irq_base;
kfree(buffer.pointer);
/*
* OK, it's an IOSAPIC MADT entry, look for a _PXM value to tell
* us which node to associate this with.
*/
pxm = acpi_get_pxm(handle);
if (pxm < 0)
return AE_OK;
node = pxm_to_node(pxm);
if (node >= MAX_NUMNODES || !node_online(node) ||
cpus_empty(node_to_cpumask(node)))
return AE_OK;
/* We know a gsi to node mapping! */
map_iosapic_to_node(gsi_base, node);
return AE_OK;
}
/*
* register cpu under node
*/
int register_cpu_under_node(unsigned int cpu, unsigned int nid)
{
if (node_online(nid)) {
struct sys_device *obj = get_cpu_sysdev(cpu);
if (!obj)
return 0;
return sysfs_create_link(&node_devices[nid].sysdev.kobj,
&obj->kobj,
kobject_name(&obj->kobj));
}
return 0;
}
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;
}
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);
}
static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
{
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
unsigned node;
int cpu = smp_processor_id();
int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
node = apicid_to_node[apicid];
if (node == NUMA_NO_NODE || !node_online(node))
node = first_node(node_online_map);
numa_set_node(cpu, node);
#endif
}
static acpi_status __devinit
acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret)
{
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
union acpi_object *obj;
struct acpi_madt_io_sapic *iosapic;
unsigned int gsi_base;
int pxm, node;
if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
return AE_OK;
if (!buffer.length || !buffer.pointer)
return AE_OK;
obj = buffer.pointer;
if (obj->type != ACPI_TYPE_BUFFER ||
obj->buffer.length < sizeof(*iosapic)) {
kfree(buffer.pointer);
return AE_OK;
}
iosapic = (struct acpi_madt_io_sapic *)obj->buffer.pointer;
if (iosapic->header.type != ACPI_MADT_TYPE_IO_SAPIC) {
kfree(buffer.pointer);
return AE_OK;
}
gsi_base = iosapic->global_irq_base;
kfree(buffer.pointer);
pxm = acpi_get_pxm(handle);
if (pxm < 0)
return AE_OK;
node = pxm_to_node(pxm);
if (node >= MAX_NUMNODES || !node_online(node) ||
cpumask_empty(cpumask_of_node(node)))
return AE_OK;
map_iosapic_to_node(gsi_base, node);
return AE_OK;
}
static void register_nodes(void)
{
int i;
for (i = 0; i < MAX_NUMNODES; i++) {
if (node_online(i)) {
int p_node = parent_node(i);
struct node *parent = NULL;
if (p_node != i)
parent = &node_devices[p_node];
register_node(&node_devices[i], i, parent);
}
}
}
static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_NUMA
unsigned node;
int cpu = smp_processor_id();
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE || !node_online(node)) {
/* reuse the value from init_cpu_to_node() */
node = cpu_to_node(cpu);
}
numa_set_node(cpu, node);
#endif
}
static void __cpuinit srat_detect_node(void)
{
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
unsigned node;
int cpu = smp_processor_id();
int apicid = hard_smp_processor_id();
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
node = apicid_to_node[apicid];
if (node == NUMA_NO_NODE || !node_online(node))
node = first_node(node_online_map);
numa_set_node(cpu, node);
printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node);
#endif
}
/*
* Setup early cpu_to_node.
*
* Populate cpu_to_node[] only if x86_cpu_to_apicid[],
* and apicid_to_node[] tables have valid entries for a CPU.
* This means we skip cpu_to_node[] initialisation for NUMA
* emulation and faking node case (when running a kernel compiled
* for NUMA on a non NUMA box), which is OK as cpu_to_node[]
* is already initialized in a round robin manner at numa_init_array,
* prior to this call, and this initialization is good enough
* for the fake NUMA cases.
*
* Called before the per_cpu areas are setup.
*/
void __init init_cpu_to_node(void)
{
int cpu;
u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
BUG_ON(cpu_to_apicid == NULL);
for_each_possible_cpu(cpu) {
int node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE)
continue;
if (!node_online(node))
node = find_near_online_node(node);
numa_set_node(cpu, node);
}
}
/**
* percpu_populate - populate per-cpu data for given cpu
* @__pdata: per-cpu data to populate further
* @size: size of per-cpu object
* @gfp: may sleep or not etc.
* @cpu: populate per-data for this cpu
*
* Populating per-cpu data for a cpu coming online would be a typical
* use case. You need to register a cpu hotplug handler for that purpose.
* Per-cpu object is populated with zeroed buffer.
*/
void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
{
struct percpu_data *pdata = __percpu_disguise(__pdata);
int node = cpu_to_node(cpu);
/*
* We should make sure each CPU gets private memory.
*/
size = roundup(size, cache_line_size());
BUG_ON(pdata->ptrs[cpu]);
if (node_online(node))
pdata->ptrs[cpu] = kmalloc_node(size, gfp|__GFP_ZERO, node);
else
pdata->ptrs[cpu] = kzalloc(size, gfp);
return pdata->ptrs[cpu];
}
/*
* Great future plan:
* Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
* Always point %gs to its beginning
*/
void __init setup_per_cpu_areas(void)
{
ssize_t size = PERCPU_ENOUGH_ROOM;
char *ptr;
int cpu;
/* Setup cpu_pda map */
setup_cpu_pda_map();
/* Copy section for each CPU (we discard the original) */
size = PERCPU_ENOUGH_ROOM;
printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n",
size);
for_each_possible_cpu(cpu) {
#ifndef CONFIG_NEED_MULTIPLE_NODES
ptr = alloc_bootmem_pages(size);
#else
int node = early_cpu_to_node(cpu);
if (!node_online(node) || !NODE_DATA(node)) {
ptr = alloc_bootmem_pages(size);
printk(KERN_INFO
"cpu %d has no node %d or node-local memory\n",
cpu, node);
}
else
ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
#endif
per_cpu_offset(cpu) = ptr - __per_cpu_start;
memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
}
printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d, nr_node_ids %d\n",
NR_CPUS, nr_cpu_ids, nr_node_ids);
/* Setup percpu data maps */
setup_per_cpu_maps();
/* Setup node to cpumask map */
setup_node_to_cpumask_map();
/* Setup cpumask_of_cpu map */
setup_cpumask_of_cpu();
}
/**
* pcpu_need_numa - determine percpu allocation needs to consider NUMA
*
* If NUMA is not configured or there is only one NUMA node available,
* there is no reason to consider NUMA. This function determines
* whether percpu allocation should consider NUMA or not.
*
* RETURNS:
* true if NUMA should be considered; otherwise, false.
*/
static bool __init pcpu_need_numa(void)
{
#ifdef CONFIG_NEED_MULTIPLE_NODES
pg_data_t *last = NULL;
unsigned int cpu;
for_each_possible_cpu(cpu) {
int node = early_cpu_to_node(cpu);
if (node_online(node) && NODE_DATA(node) &&
last && last != NODE_DATA(node))
return true;
last = NODE_DATA(node);
}
#endif
return false;
}
int get_mp_bus_to_node(int busnum)
{
int node = -1;
if (busnum < 0 || busnum > (BUS_NR - 1))
return node;
node = mp_bus_to_node[busnum];
/*
* let numa_node_id to decide it later in dma_alloc_pages
* if there is no ram on that node
*/
if (node != -1 && !node_online(node))
node = -1;
return node;
}
int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
{
struct device *obj;
if (!node_online(nid))
return 0;
obj = get_cpu_device(cpu);
if (!obj)
return 0;
sysfs_remove_link(&node_devices[nid]->dev.kobj,
kobject_name(&obj->kobj));
sysfs_remove_link(&obj->kobj,
kobject_name(&node_devices[nid]->dev.kobj));
return 0;
}
static acpi_status acpi_map_iosapic(acpi_handle handle, u32 depth,
void *context, void **ret)
{
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
union acpi_object *obj;
struct acpi_madt_io_sapic *iosapic;
unsigned int gsi_base;
int node;
/* Only care about objects w/ a method that returns the MADT */
if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
return AE_OK;
if (!buffer.length || !buffer.pointer)
return AE_OK;
obj = buffer.pointer;
if (obj->type != ACPI_TYPE_BUFFER ||
obj->buffer.length < sizeof(*iosapic)) {
kfree(buffer.pointer);
return AE_OK;
}
iosapic = (struct acpi_madt_io_sapic *)obj->buffer.pointer;
if (iosapic->header.type != ACPI_MADT_TYPE_IO_SAPIC) {
kfree(buffer.pointer);
return AE_OK;
}
gsi_base = iosapic->global_irq_base;
kfree(buffer.pointer);
/* OK, it's an IOSAPIC MADT entry; associate it with a node */
node = acpi_get_node(handle);
if (node == NUMA_NO_NODE || !node_online(node) ||
cpumask_empty(cpumask_of_node(node)))
return AE_OK;
/* We know a gsi to node mapping! */
map_iosapic_to_node(gsi_base, node);
return AE_OK;
}
/* register memory section under specified node if it spans that node */
int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
{
int ret;
unsigned long pfn, sect_start_pfn, sect_end_pfn;
if (!mem_blk)
return -EFAULT;
if (!node_online(nid))
return 0;
sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
sect_end_pfn += PAGES_PER_SECTION - 1;
for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
int page_nid;
/*
* memory block could have several absent sections from start.
* skip pfn range from absent section
*/
if (!pfn_present(pfn)) {
pfn = round_down(pfn + PAGES_PER_SECTION,
PAGES_PER_SECTION) - 1;
continue;
}
page_nid = get_nid_for_pfn(pfn);
if (page_nid < 0)
continue;
if (page_nid != nid)
continue;
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
if (ret)
return ret;
return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
&node_devices[nid]->dev.kobj,
kobject_name(&node_devices[nid]->dev.kobj));
}
/* mem section does not span the specified node */
return 0;
}
/**
* fill_mp_bus_to_cpumask()
* fills the mp_bus_to_cpumask array based according to the LDT Bus Number
* Registers found in the K8 northbridge
*/
__init static int
fill_mp_bus_to_cpumask(void)
{
struct pci_dev *nb_dev = NULL;
int i, j;
u32 ldtbus, nid;
static int lbnr[3] = {
LDT_BUS_NUMBER_REGISTER_0,
LDT_BUS_NUMBER_REGISTER_1,
LDT_BUS_NUMBER_REGISTER_2
};
while ((nb_dev = pci_get_device(PCI_VENDOR_ID_AMD,
PCI_DEVICE_ID_K8HTCONFIG, nb_dev))) {
pci_read_config_dword(nb_dev, NODE_ID_REGISTER, &nid);
for (i = 0; i < NR_LDT_BUS_NUMBER_REGISTERS; i++) {
pci_read_config_dword(nb_dev, lbnr[i], &ldtbus);
/*
* if there are no busses hanging off of the current
* ldt link then both the secondary and subordinate
* bus number fields are set to 0.
*
* RED-PEN
* This is slightly broken because it assumes
* HT node IDs == Linux node ids, which is not always
* true. However it is probably mostly true.
*/
if (!(SECONDARY_LDT_BUS_NUMBER(ldtbus) == 0
&& SUBORDINATE_LDT_BUS_NUMBER(ldtbus) == 0)) {
for (j = SECONDARY_LDT_BUS_NUMBER(ldtbus);
j <= SUBORDINATE_LDT_BUS_NUMBER(ldtbus);
j++) {
int node = NODE_ID(nid);
if (!node_online(node))
node = 0;
pci_bus_to_node[j] = node;
}
}
}
}
return 0;
}
/**
* acpi_map_pxm_to_online_node - Map proximity ID to online node
* @pxm: ACPI proximity ID
*
* This is similar to acpi_map_pxm_to_node(), but always returns an online
* node. When the mapped node from a given proximity ID is offline, it
* looks up the node distance table and returns the nearest online node.
*
* ACPI device drivers, which are called after the NUMA initialization has
* completed in the kernel, can call this interface to obtain their device
* NUMA topology from ACPI tables. Such drivers do not have to deal with
* offline nodes. A node may be offline when a device proximity ID is
* unique, SRAT memory entry does not exist, or NUMA is disabled, ex.
* "numa=off" on x86.
*/
int acpi_map_pxm_to_online_node(int pxm)
{
int node, n, dist, min_dist;
node = acpi_map_pxm_to_node(pxm);
if (node == NUMA_NO_NODE)
node = 0;
if (!node_online(node)) {
min_dist = INT_MAX;
for_each_online_node(n) {
dist = node_distance(node, n);
if (dist < min_dist) {
min_dist = dist;
node = n;
}
}
}
void __cpuinit map_cpu_to_node(int cpu, int nid)
{
int oldnid;
if (nid < 0) { /* just initialize by zero */
cpu_to_node_map[cpu] = 0;
return;
}
/* sanity check first */
oldnid = cpu_to_node_map[cpu];
if (cpu_isset(cpu, node_to_cpu_mask[oldnid])) {
return; /* nothing to do */
}
/* we don't have cpu-driven node hot add yet...
In usual case, node is created from SRAT at boot time. */
if (!node_online(nid))
nid = first_online_node;
cpu_to_node_map[cpu] = nid;
cpu_set(cpu, node_to_cpu_mask[nid]);
return;
}
/*
* register cpu under node
*/
int register_cpu_under_node(unsigned int cpu, unsigned int nid)
{
int ret;
struct device *obj;
if (!node_online(nid))
return 0;
obj = get_cpu_device(cpu);
if (!obj)
return 0;
ret = sysfs_create_link(&node_devices[nid]->dev.kobj,
&obj->kobj,
kobject_name(&obj->kobj));
if (ret)
return ret;
return sysfs_create_link(&obj->kobj,
&node_devices[nid]->dev.kobj,
kobject_name(&node_devices[nid]->dev.kobj));
}
/* Set correct numa_node information for AMD NB functions */
static void quirk_amd_nb_node(struct pci_dev *dev)
{
struct pci_dev *nb_ht;
unsigned int devfn;
u32 node;
u32 val;
devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0);
nb_ht = pci_get_slot(dev->bus, devfn);
if (!nb_ht)
return;
pci_read_config_dword(nb_ht, 0x60, &val);
node = pcibus_to_node(dev->bus) | (val & 7);
/*
* Some hardware may return an invalid node ID,
* so check it first:
*/
if (node_online(node))
set_dev_node(&dev->dev, node);
pci_dev_put(nb_ht);
}
/*
* Figure out to which domain a cpu belongs and stick it there.
* Return the id of the domain used.
*/
static int numa_setup_cpu(unsigned long lcpu)
{
int nid = -1;
struct device_node *cpu;
/*
* If a valid cpu-to-node mapping is already available, use it
* directly instead of querying the firmware, since it represents
* the most recent mapping notified to us by the platform (eg: VPHN).
*/
if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) {
map_cpu_to_node(lcpu, nid);
return nid;
}
cpu = of_get_cpu_node(lcpu, NULL);
if (!cpu) {
WARN_ON(1);
if (cpu_present(lcpu))
goto out_present;
else
goto out;
}
nid = of_node_to_nid_single(cpu);
out_present:
if (nid < 0 || !node_online(nid))
nid = first_online_node;
map_cpu_to_node(lcpu, nid);
of_node_put(cpu);
out:
return nid;
}
static void nlm_init_bootmem_node (unsigned long mapstart, unsigned long min_pfn, unsigned long max_pfn)
{
int i;
for (i = 0; i < NLM_MAX_CPU_NODE; i++) {
unsigned long map_pfn, start_pfn, end_pfn, bootmem_size;
int j;
if(!node_online(i))
continue;
start_pfn = NODE_MEM_DATA(i)->low_pfn;
end_pfn = NODE_MEM_DATA(i)->high_pfn;
if (start_pfn && start_pfn < min_pfn)
start_pfn = min_pfn;
if (end_pfn > max_pfn)
end_pfn = max_pfn;
/* in general, never hit the condition */
if (start_pfn && start_pfn >= end_pfn) {
NODE_MEM_DATA(i)->map_pfn = 0; /* indicate a bad map_pfn */
continue;
}
if (start_pfn > mapstart)
map_pfn = start_pfn;
else
map_pfn = mapstart;
if((start_pfn == 0) && (end_pfn == 0)) {
map_pfn =
_low_virt_to_phys(&_node_map_mem[i][0]) >> PAGE_SHIFT;
__node_data[i] = __va(map_pfn << PAGE_SHIFT);
} else {
void __devinit igb_check_options(struct igb_adapter *adapter)
{
int bd = adapter->bd_number;
struct e1000_hw *hw = &adapter->hw;
if (bd >= IGB_MAX_NIC) {
DPRINTK(PROBE, NOTICE,
"Warning: no configuration for board #%d\n", bd);
DPRINTK(PROBE, NOTICE, "Using defaults for all values\n");
#ifndef module_param_array
bd = IGB_MAX_NIC;
#endif
}
{ /* Interrupt Throttling Rate */
struct igb_option opt = {
.type = range_option,
.name = "Interrupt Throttling Rate (ints/sec)",
.err = "using default of " __MODULE_STRING(DEFAULT_ITR),
.def = DEFAULT_ITR,
.arg = { .r = { .min = MIN_ITR,
.max = MAX_ITR } }
};
#ifdef module_param_array
if (num_InterruptThrottleRate > bd) {
#endif
unsigned int itr = InterruptThrottleRate[bd];
switch (itr) {
case 0:
DPRINTK(PROBE, INFO, "%s turned off\n",
opt.name);
if(hw->mac.type >= e1000_i350)
adapter->dmac = IGB_DMAC_DISABLE;
adapter->rx_itr_setting = itr;
break;
case 1:
DPRINTK(PROBE, INFO, "%s set to dynamic mode\n",
opt.name);
adapter->rx_itr_setting = itr;
break;
case 3:
DPRINTK(PROBE, INFO,
"%s set to dynamic conservative mode\n",
opt.name);
adapter->rx_itr_setting = itr;
break;
default:
igb_validate_option(&itr, &opt, adapter);
/* Save the setting, because the dynamic bits
* change itr. In case of invalid user value,
* default to conservative mode, else need to
* clear the lower two bits because they are
* used as control */
if (itr == 3) {
adapter->rx_itr_setting = itr;
} else {
adapter->rx_itr_setting = 1000000000 /
(itr * 256);
adapter->rx_itr_setting &= ~3;
}
break;
}
#ifdef module_param_array
} else {
adapter->rx_itr_setting = opt.def;
}
#endif
adapter->tx_itr_setting = adapter->rx_itr_setting;
}
{ /* Interrupt Mode */
struct igb_option opt = {
.type = range_option,
.name = "Interrupt Mode",
.err = "defaulting to 2 (MSI-X)",
.def = IGB_INT_MODE_MSIX,
.arg = { .r = { .min = MIN_INTMODE,
.max = MAX_INTMODE } }
};
#ifdef module_param_array
if (num_IntMode > bd) {
#endif
unsigned int int_mode = IntMode[bd];
igb_validate_option(&int_mode, &opt, adapter);
adapter->int_mode = int_mode;
#ifdef module_param_array
} else {
adapter->int_mode = opt.def;
}
#endif
}
{ /* Low Latency Interrupt TCP Port */
struct igb_option opt = {
.type = range_option,
.name = "Low Latency Interrupt TCP Port",
.err = "using default of " __MODULE_STRING(DEFAULT_LLIPORT),
.def = DEFAULT_LLIPORT,
.arg = { .r = { .min = MIN_LLIPORT,
.max = MAX_LLIPORT } }
};
#ifdef module_param_array
if (num_LLIPort > bd) {
#endif
adapter->lli_port = LLIPort[bd];
if (adapter->lli_port) {
igb_validate_option(&adapter->lli_port, &opt,
adapter);
} else {
DPRINTK(PROBE, INFO, "%s turned off\n",
opt.name);
}
#ifdef module_param_array
} else {
adapter->lli_port = opt.def;
}
#endif
}
{ /* Low Latency Interrupt on Packet Size */
struct igb_option opt = {
.type = range_option,
.name = "Low Latency Interrupt on Packet Size",
.err = "using default of " __MODULE_STRING(DEFAULT_LLISIZE),
.def = DEFAULT_LLISIZE,
.arg = { .r = { .min = MIN_LLISIZE,
.max = MAX_LLISIZE } }
};
#ifdef module_param_array
if (num_LLISize > bd) {
#endif
adapter->lli_size = LLISize[bd];
if (adapter->lli_size) {
igb_validate_option(&adapter->lli_size, &opt,
adapter);
} else {
DPRINTK(PROBE, INFO, "%s turned off\n",
opt.name);
}
#ifdef module_param_array
} else {
adapter->lli_size = opt.def;
}
#endif
}
{ /* Low Latency Interrupt on TCP Push flag */
struct igb_option opt = {
.type = enable_option,
.name = "Low Latency Interrupt on TCP Push flag",
.err = "defaulting to Disabled",
.def = OPTION_DISABLED
};
#ifdef module_param_array
if (num_LLIPush > bd) {
#endif
unsigned int lli_push = LLIPush[bd];
igb_validate_option(&lli_push, &opt, adapter);
adapter->flags |= lli_push ? IGB_FLAG_LLI_PUSH : 0;
#ifdef module_param_array
} else {
adapter->flags |= opt.def ? IGB_FLAG_LLI_PUSH : 0;
}
#endif
}
{ /* SRIOV - Enable SR-IOV VF devices */
struct igb_option opt = {
.type = range_option,
.name = "max_vfs - SR-IOV VF devices",
.err = "using default of " __MODULE_STRING(DEFAULT_SRIOV),
.def = DEFAULT_SRIOV,
.arg = { .r = { .min = MIN_SRIOV,
.max = MAX_SRIOV } }
};
#ifdef module_param_array
if (num_max_vfs > bd) {
#endif
adapter->vfs_allocated_count = max_vfs[bd];
igb_validate_option(&adapter->vfs_allocated_count, &opt, adapter);
#ifdef module_param_array
} else {
adapter->vfs_allocated_count = opt.def;
}
#endif
if (adapter->vfs_allocated_count) {
switch (hw->mac.type) {
case e1000_82575:
case e1000_82580:
adapter->vfs_allocated_count = 0;
DPRINTK(PROBE, INFO, "SR-IOV option max_vfs not supported.\n");
default:
break;
}
}
}
{ /* VMDQ - Enable VMDq multiqueue receive */
struct igb_option opt = {
.type = range_option,
.name = "VMDQ - VMDq multiqueue queue count",
.err = "using default of " __MODULE_STRING(DEFAULT_VMDQ),
.def = DEFAULT_VMDQ,
.arg = { .r = { .min = MIN_VMDQ,
.max = (MAX_VMDQ - adapter->vfs_allocated_count) } }
};
#ifdef module_param_array
if (num_VMDQ > bd) {
#endif
adapter->vmdq_pools = (VMDQ[bd] == 1 ? 0 : VMDQ[bd]);
if (adapter->vfs_allocated_count && !adapter->vmdq_pools) {
DPRINTK(PROBE, INFO, "Enabling SR-IOV requires VMDq be set to at least 1\n");
adapter->vmdq_pools = 1;
}
igb_validate_option(&adapter->vmdq_pools, &opt, adapter);
#ifdef module_param_array
} else {
if (!adapter->vfs_allocated_count)
adapter->vmdq_pools = (opt.def == 1 ? 0 : opt.def);
else
adapter->vmdq_pools = 1;
}
#endif
#ifdef CONFIG_IGB_VMDQ_NETDEV
if (hw->mac.type == e1000_82575 && adapter->vmdq_pools) {
DPRINTK(PROBE, INFO, "VMDq not supported on this part.\n");
adapter->vmdq_pools = 0;
}
#endif
}
{ /* RSS - Enable RSS multiqueue receives */
struct igb_option opt = {
.type = range_option,
.name = "RSS - RSS multiqueue receive count",
.err = "using default of " __MODULE_STRING(DEFAULT_RSS),
.def = DEFAULT_RSS,
.arg = { .r = { .min = MIN_RSS,
.max = MAX_RSS } }
};
if (adapter->vmdq_pools) {
switch (hw->mac.type) {
#ifndef CONFIG_IGB_VMDQ_NETDEV
case e1000_82576:
opt.arg.r.max = 2;
break;
case e1000_82575:
if (adapter->vmdq_pools == 2)
opt.arg.r.max = 3;
if (adapter->vmdq_pools <= 2)
break;
#endif
default:
opt.arg.r.max = 1;
break;
}
}
#ifdef module_param_array
if (num_RSS > bd) {
#endif
adapter->rss_queues = RSS[bd];
switch (adapter->rss_queues) {
case 1:
break;
default:
igb_validate_option(&adapter->rss_queues, &opt, adapter);
if (adapter->rss_queues)
break;
case 0:
adapter->rss_queues = min_t(u32, opt.arg.r.max, num_online_cpus());
break;
}
#ifdef module_param_array
} else {
adapter->rss_queues = opt.def ?:
min_t(u32, opt.arg.r.max, num_online_cpus());
}
#endif
}
{ /* QueuePairs - Enable TX/RX queue pairs for interrupt handling */
struct igb_option opt = {
.type = enable_option,
.name = "QueuePairs - TX/RX queue pairs for interrupt handling",
.err = "defaulting to Enabled",
.def = OPTION_ENABLED
};
#ifdef module_param_array
if (num_QueuePairs > bd) {
#endif
unsigned int qp = QueuePairs[bd];
/*
* we must enable queue pairs if the number of queues
* exceeds the number of avaialble interrupts. We are
* limited to 10, or 3 per unallocated vf.
*/
if ((adapter->rss_queues > 4) ||
(adapter->vmdq_pools > 4) ||
((adapter->rss_queues > 1) &&
((adapter->vmdq_pools > 3) ||
(adapter->vfs_allocated_count > 6)))) {
if (qp == OPTION_DISABLED) {
qp = OPTION_ENABLED;
DPRINTK(PROBE, INFO,
"Number of queues exceeds available interrupts, %s\n",opt.err);
}
}
igb_validate_option(&qp, &opt, adapter);
adapter->flags |= qp ? IGB_FLAG_QUEUE_PAIRS : 0;
#ifdef module_param_array
} else {
adapter->flags |= opt.def ? IGB_FLAG_QUEUE_PAIRS : 0;
}
#endif
}
{ /* EEE - Enable EEE for capable adapters */
if (hw->mac.type >= e1000_i350) {
struct igb_option opt = {
.type = enable_option,
.name = "EEE Support",
.err = "defaulting to Enabled",
.def = OPTION_ENABLED
};
#ifdef module_param_array
if (num_EEE > bd) {
#endif
unsigned int eee = EEE[bd];
igb_validate_option(&eee, &opt, adapter);
adapter->flags |= eee ? IGB_FLAG_EEE : 0;
if (eee)
hw->dev_spec._82575.eee_disable = false;
else
hw->dev_spec._82575.eee_disable = true;
#ifdef module_param_array
} else {
adapter->flags |= opt.def ? IGB_FLAG_EEE : 0;
if (adapter->flags & IGB_FLAG_EEE)
hw->dev_spec._82575.eee_disable = false;
else
hw->dev_spec._82575.eee_disable = true;
}
#endif
}
}
{ /* DMAC - Enable DMA Coalescing for capable adapters */
if (hw->mac.type >= e1000_i350) {
struct igb_opt_list list [] = {
{ IGB_DMAC_DISABLE, "DMAC Disable"},
{ IGB_DMAC_MIN, "DMAC 250 usec"},
{ IGB_DMAC_500, "DMAC 500 usec"},
{ IGB_DMAC_EN_DEFAULT, "DMAC 1000 usec"},
{ IGB_DMAC_2000, "DMAC 2000 usec"},
{ IGB_DMAC_3000, "DMAC 3000 usec"},
{ IGB_DMAC_4000, "DMAC 4000 usec"},
{ IGB_DMAC_5000, "DMAC 5000 usec"},
{ IGB_DMAC_6000, "DMAC 6000 usec"},
{ IGB_DMAC_7000, "DMAC 7000 usec"},
{ IGB_DMAC_8000, "DMAC 8000 usec"},
{ IGB_DMAC_9000, "DMAC 9000 usec"},
{ IGB_DMAC_MAX, "DMAC 10000 usec"}
};
struct igb_option opt = {
.type = list_option,
.name = "DMA Coalescing",
.err = "using default of "__MODULE_STRING(IGB_DMAC_DISABLE),
.def = IGB_DMAC_DISABLE,
.arg = { .l = { .nr = 13,
.p = list
}
}
};
#ifdef module_param_array
if (num_DMAC > bd) {
#endif
unsigned int dmac = DMAC[bd];
if (adapter->rx_itr_setting == IGB_DMAC_DISABLE)
dmac = IGB_DMAC_DISABLE;
igb_validate_option(&dmac, &opt, adapter);
switch (dmac) {
case IGB_DMAC_DISABLE:
adapter->dmac = dmac;
break;
case IGB_DMAC_MIN:
adapter->dmac = dmac;
break;
case IGB_DMAC_500:
adapter->dmac = dmac;
break;
case IGB_DMAC_EN_DEFAULT:
adapter->dmac = dmac;
break;
case IGB_DMAC_2000:
adapter->dmac = dmac;
break;
case IGB_DMAC_3000:
adapter->dmac = dmac;
break;
case IGB_DMAC_4000:
adapter->dmac = dmac;
break;
case IGB_DMAC_5000:
adapter->dmac = dmac;
break;
case IGB_DMAC_6000:
adapter->dmac = dmac;
break;
case IGB_DMAC_7000:
adapter->dmac = dmac;
break;
case IGB_DMAC_8000:
adapter->dmac = dmac;
break;
case IGB_DMAC_9000:
adapter->dmac = dmac;
break;
case IGB_DMAC_MAX:
adapter->dmac = dmac;
break;
default:
adapter->dmac = opt.def;
DPRINTK(PROBE, INFO,
"Invalid DMAC setting, "
"resetting DMAC to %d\n", opt.def);
}
#ifdef module_param_array
} else
adapter->dmac = opt.def;
#endif
}
}
#ifndef IGB_NO_LRO
{ /* LRO - Enable Large Receive Offload */
struct igb_option opt = {
.type = enable_option,
.name = "LRO - Large Receive Offload",
.err = "defaulting to Disabled",
.def = OPTION_DISABLED
};
struct net_device *netdev = adapter->netdev;
#ifdef module_param_array
if (num_LRO > bd) {
#endif
unsigned int lro = LRO[bd];
igb_validate_option(&lro, &opt, adapter);
netdev->features |= lro ? NETIF_F_LRO : 0;
#ifdef module_param_array
} else if (opt.def == OPTION_ENABLED) {
netdev->features |= NETIF_F_LRO;
}
#endif
}
#endif /* IGB_NO_LRO */
{ /* Node assignment */
static struct igb_option opt = {
.type = range_option,
.name = "Node to start on",
.err = "defaulting to -1",
#ifdef HAVE_EARLY_VMALLOC_NODE
.def = 0,
#else
.def = -1,
#endif
.arg = { .r = { .min = 0,
.max = (MAX_NUMNODES - 1)}}
};
int node_param = opt.def;
/* if the default was zero then we need to set the
* default value to an online node, which is not
* necessarily zero, and the constant initializer
* above can't take first_online_node */
if (node_param == 0)
/* must set opt.def for validate */
opt.def = node_param = first_online_node;
#ifdef module_param_array
if (num_Node > bd) {
#endif
node_param = Node[bd];
igb_validate_option((uint *)&node_param, &opt, adapter);
if (node_param != OPTION_UNSET) {
DPRINTK(PROBE, INFO, "node set to %d\n", node_param);
}
#ifdef module_param_array
}
#endif
/* check sanity of the value */
if (node_param != -1 && !node_online(node_param)) {
DPRINTK(PROBE, INFO,
"ignoring node set to invalid value %d\n",
node_param);
node_param = opt.def;
}
adapter->node = node_param;
}
{ /* MDD - Enable Malicious Driver Detection. Only available when
SR-IOV is enabled. */
struct igb_option opt = {
.type = enable_option,
.name = "Malicious Driver Detection",
.err = "defaulting to 1",
.def = OPTION_ENABLED,
.arg = { .r = { .min = OPTION_DISABLED,
.max = OPTION_ENABLED } }
};
#ifdef module_param_array
if (num_MDD > bd) {
#endif
adapter->mdd = MDD[bd];
igb_validate_option((uint *)&adapter->mdd, &opt,
adapter);
#ifdef module_param_array
} else {
adapter->mdd = opt.def;
}
#endif
}
}
struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
{
struct acpi_device *device = root->device;
struct pci_root_info *info = NULL;
int domain = root->segment;
int busnum = root->secondary.start;
LIST_HEAD(resources);
struct pci_bus *bus = NULL;
struct pci_sysdata *sd;
int node;
#ifdef CONFIG_ACPI_NUMA
int pxm;
#endif
if (pci_ignore_seg)
domain = 0;
if (domain && !pci_domains_supported) {
printk(KERN_WARNING "pci_bus %04x:%02x: "
"ignored (multiple domains not supported)\n",
domain, busnum);
return NULL;
}
node = -1;
#ifdef CONFIG_ACPI_NUMA
pxm = acpi_get_pxm(device->handle);
if (pxm >= 0)
node = pxm_to_node(pxm);
if (node != -1)
set_mp_bus_to_node(busnum, node);
else
#endif
node = get_mp_bus_to_node(busnum);
if (node != -1 && !node_online(node))
node = -1;
info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info) {
printk(KERN_WARNING "pci_bus %04x:%02x: "
"ignored (out of memory)\n", domain, busnum);
return NULL;
}
sd = &info->sd;
sd->domain = domain;
sd->node = node;
sd->companion = device;
/*
* Maybe the desired pci bus has been already scanned. In such case
* it is unnecessary to scan the pci bus with the given domain,busnum.
*/
bus = pci_find_bus(domain, busnum);
if (bus) {
/*
* If the desired bus exits, the content of bus->sysdata will
* be replaced by sd.
*/
memcpy(bus->sysdata, sd, sizeof(*sd));
kfree(info);
} else {
probe_pci_root_info(info, device, busnum, domain);
/* insert busn res at first */
pci_add_resource(&resources, &root->secondary);
/*
* _CRS with no apertures is normal, so only fall back to
* defaults or native bridge info if we're ignoring _CRS.
*/
if (pci_use_crs)
add_resources(info, &resources);
else {
free_pci_root_info_res(info);
x86_pci_root_bus_resources(busnum, &resources);
}
if (!setup_mcfg_map(info, domain, (u8)root->secondary.start,
(u8)root->secondary.end, root->mcfg_addr))
bus = pci_create_root_bus(NULL, busnum, &pci_root_ops,
sd, &resources);
if (bus) {
pci_scan_child_bus(bus);
pci_set_host_bridge_release(
to_pci_host_bridge(bus->bridge),
release_pci_root_info, info);
} else {
pci_free_resource_list(&resources);
__release_pci_root_info(info);
}
}
/* After the PCI-E bus has been walked and all devices discovered,
* configure any settings of the fabric that might be necessary.
*/
if (bus) {
struct pci_bus *child;
list_for_each_entry(child, &bus->children, node)
pcie_bus_configure_settings(child);
}
if (bus && node != -1) {
#ifdef CONFIG_ACPI_NUMA
if (pxm >= 0)
dev_printk(KERN_DEBUG, &bus->dev,
"on NUMA node %d (pxm %d)\n", node, pxm);
#else
dev_printk(KERN_DEBUG, &bus->dev, "on NUMA node %d\n", node);
#endif
}
return bus;
}
struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
{
struct acpi_device *device = root->device;
int domain = root->segment;
int busnum = root->secondary.start;
struct pci_bus *bus;
struct pci_sysdata *sd;
int node;
#ifdef CONFIG_ACPI_NUMA
int pxm;
#endif
if (domain && !pci_domains_supported) {
printk(KERN_WARNING "pci_bus %04x:%02x: "
"ignored (multiple domains not supported)\n",
domain, busnum);
return NULL;
}
node = -1;
#ifdef CONFIG_ACPI_NUMA
pxm = acpi_get_pxm(device->handle);
if (pxm >= 0)
node = pxm_to_node(pxm);
if (node != -1)
set_mp_bus_to_node(busnum, node);
else
#endif
node = get_mp_bus_to_node(busnum);
if (node != -1 && !node_online(node))
node = -1;
/* Allocate per-root-bus (not per bus) arch-specific data.
* TODO: leak; this memory is never freed.
* It's arguable whether it's worth the trouble to care.
*/
sd = kzalloc(sizeof(*sd), GFP_KERNEL);
if (!sd) {
printk(KERN_WARNING "pci_bus %04x:%02x: "
"ignored (out of memory)\n", domain, busnum);
return NULL;
}
sd->domain = domain;
sd->node = node;
/*
* Maybe the desired pci bus has been already scanned. In such case
* it is unnecessary to scan the pci bus with the given domain,busnum.
*/
bus = pci_find_bus(domain, busnum);
if (bus) {
/*
* If the desired bus exits, the content of bus->sysdata will
* be replaced by sd.
*/
memcpy(bus->sysdata, sd, sizeof(*sd));
kfree(sd);
} else {
bus = pci_create_bus(NULL, busnum, &pci_root_ops, sd);
if (bus) {
get_current_resources(device, busnum, domain, bus);
bus->subordinate = pci_scan_child_bus(bus);
}
}
if (!bus)
kfree(sd);
if (bus && node != -1) {
#ifdef CONFIG_ACPI_NUMA
if (pxm >= 0)
dev_printk(KERN_DEBUG, &bus->dev,
"on NUMA node %d (pxm %d)\n", node, pxm);
#else
dev_printk(KERN_DEBUG, &bus->dev, "on NUMA node %d\n", node);
#endif
}
return bus;
}
