static void unregister_cpu_online(unsigned int cpu)
{
struct cpu *c = &per_cpu(cpu_devices, cpu);
struct device *s = &c->dev;
struct device_attribute *attrs, *pmc_attrs;
int i, nattrs;
BUG_ON(!c->hotpluggable);
#ifdef CONFIG_PPC64
if (!firmware_has_feature(FW_FEATURE_ISERIES) &&
cpu_has_feature(CPU_FTR_SMT))
device_remove_file(s, &dev_attr_smt_snooze_delay);
#endif
/* PMC stuff */
switch (cur_cpu_spec->pmc_type) {
#ifdef HAS_PPC_PMC_IBM
case PPC_PMC_IBM:
attrs = ibm_common_attrs;
nattrs = sizeof(ibm_common_attrs) / sizeof(struct device_attribute);
pmc_attrs = classic_pmc_attrs;
break;
#endif /* HAS_PPC_PMC_IBM */
#ifdef HAS_PPC_PMC_G4
case PPC_PMC_G4:
attrs = g4_common_attrs;
nattrs = sizeof(g4_common_attrs) / sizeof(struct device_attribute);
pmc_attrs = classic_pmc_attrs;
break;
#endif /* HAS_PPC_PMC_G4 */
#ifdef HAS_PPC_PMC_PA6T
case PPC_PMC_PA6T:
/* PA Semi starts counting at PMC0 */
attrs = pa6t_attrs;
nattrs = sizeof(pa6t_attrs) / sizeof(struct device_attribute);
pmc_attrs = NULL;
break;
#endif /* HAS_PPC_PMC_PA6T */
default:
attrs = NULL;
nattrs = 0;
pmc_attrs = NULL;
}
for (i = 0; i < nattrs; i++)
device_remove_file(s, &attrs[i]);
if (pmc_attrs)
for (i = 0; i < cur_cpu_spec->num_pmcs; i++)
device_remove_file(s, &pmc_attrs[i]);
#ifdef CONFIG_PPC64
if (cpu_has_feature(CPU_FTR_MMCRA))
device_remove_file(s, &dev_attr_mmcra);
if (cpu_has_feature(CPU_FTR_PURR))
device_remove_file(s, &dev_attr_purr);
if (cpu_has_feature(CPU_FTR_SPURR))
device_remove_file(s, &dev_attr_spurr);
if (cpu_has_feature(CPU_FTR_DSCR))
device_remove_file(s, &dev_attr_dscr);
if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
device_remove_file(s, &dev_attr_pir);
#endif /* CONFIG_PPC64 */
cacheinfo_cpu_offline(cpu);
}
int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
{
int written = 0;
__be64 olen;
s64 len, rc;
unsigned long flags;
__be64 evt;
if (!opal.entry)
return -ENODEV;
/* We want put_chars to be atomic to avoid mangling of hvsi
* packets. To do that, we first test for room and return
* -EAGAIN if there isn't enough.
*
* Unfortunately, opal_console_write_buffer_space() doesn't
* appear to work on opal v1, so we just assume there is
* enough room and be done with it
*/
spin_lock_irqsave(&opal_write_lock, flags);
if (firmware_has_feature(FW_FEATURE_OPALv2)) {
rc = opal_console_write_buffer_space(vtermno, &olen);
len = be64_to_cpu(olen);
if (rc || len < total_len) {
spin_unlock_irqrestore(&opal_write_lock, flags);
/* Closed -> drop characters */
if (rc)
return total_len;
opal_poll_events(NULL);
return -EAGAIN;
}
}
/* We still try to handle partial completions, though they
* should no longer happen.
*/
rc = OPAL_BUSY;
while(total_len > 0 && (rc == OPAL_BUSY ||
rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
olen = cpu_to_be64(total_len);
rc = opal_console_write(vtermno, &olen, data);
len = be64_to_cpu(olen);
/* Closed or other error drop */
if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
rc != OPAL_BUSY_EVENT) {
written = total_len;
break;
}
if (rc == OPAL_SUCCESS) {
total_len -= len;
data += len;
written += len;
}
/* This is a bit nasty but we need that for the console to
* flush when there aren't any interrupts. We will clean
* things a bit later to limit that to synchronous path
* such as the kernel console and xmon/udbg
*/
do
opal_poll_events(&evt);
while(rc == OPAL_SUCCESS &&
(be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT));
}
spin_unlock_irqrestore(&opal_write_lock, flags);
return written;
}
static int __init opal_init(void)
{
struct device_node *np, *consoles;
const __be32 *irqs;
int rc, i, irqlen;
opal_node = of_find_node_by_path("/ibm,opal");
if (!opal_node) {
pr_warn("opal: Node not found\n");
return -ENODEV;
}
/* Register OPAL consoles if any ports */
if (firmware_has_feature(FW_FEATURE_OPALv2))
consoles = of_find_node_by_path("/ibm,opal/consoles");
else
consoles = of_node_get(opal_node);
if (consoles) {
for_each_child_of_node(consoles, np) {
if (strcmp(np->name, "serial"))
continue;
of_platform_device_create(np, NULL, NULL);
}
of_node_put(consoles);
}
/* Find all OPAL interrupts and request them */
irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
pr_debug("opal: Found %d interrupts reserved for OPAL\n",
irqs ? (irqlen / 4) : 0);
opal_irq_count = irqlen / 4;
opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL);
for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) {
unsigned int hwirq = be32_to_cpup(irqs);
unsigned int irq = irq_create_mapping(NULL, hwirq);
if (irq == NO_IRQ) {
pr_warning("opal: Failed to map irq 0x%x\n", hwirq);
continue;
}
rc = request_irq(irq, opal_interrupt, 0, "opal", NULL);
if (rc)
pr_warning("opal: Error %d requesting irq %d"
" (0x%x)\n", rc, irq, hwirq);
opal_irqs[i] = irq;
}
/* Create "opal" kobject under /sys/firmware */
rc = opal_sysfs_init();
if (rc == 0) {
/* Setup error log interface */
rc = opal_elog_init();
/* Setup code update interface */
opal_flash_init();
/* Setup platform dump extract interface */
opal_platform_dump_init();
/* Setup system parameters interface */
opal_sys_param_init();
/* Setup message log interface. */
opal_msglog_init();
}
return 0;
}
static int pSeries_pci_probe_mode(struct pci_bus *bus)
{
if (firmware_has_feature(FW_FEATURE_LPAR))
return PCI_PROBE_DEVTREE;
return PCI_PROBE_NORMAL;
}
static int opal_xscom_init(void)
{
if (firmware_has_feature(FW_FEATURE_OPAL))
scom_init(&opal_scom_controller);
return 0;
}
static void ps3_ehci_driver_unregister(struct ps3_system_bus_driver *drv)
{
if (firmware_has_feature(FW_FEATURE_PS3_LV1))
ps3_system_bus_driver_unregister(drv);
}
void __init early_setup(unsigned long dt_ptr)
{
/* -------- printk is _NOT_ safe to use here ! ------- */
/* Fill in any unititialised pacas */
initialise_pacas();
/* Identify CPU type */
identify_cpu(0, mfspr(SPRN_PVR));
/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
setup_paca(0);
/* Initialize lockdep early or else spinlocks will blow */
lockdep_init();
/* -------- printk is now safe to use ------- */
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
DBG(" -> early_setup(), dt_ptr: 0x%lx\n", dt_ptr);
/*
* Do early initialization using the flattened device
* tree, such as retrieving the physical memory map or
* calculating/retrieving the hash table size.
*/
early_init_devtree(__va(dt_ptr));
/* Now we know the logical id of our boot cpu, setup the paca. */
setup_paca(boot_cpuid);
/* Fix up paca fields required for the boot cpu */
get_paca()->cpu_start = 1;
get_paca()->stab_real = __pa((u64)&initial_stab);
get_paca()->stab_addr = (u64)&initial_stab;
/* Probe the machine type */
probe_machine();
setup_kdump_trampoline();
DBG("Found, Initializing memory management...\n");
/*
* Initialize the MMU Hash table and create the linear mapping
* of memory. Has to be done before stab/slb initialization as
* this is currently where the page size encoding is obtained
*/
htab_initialize();
/*
* Initialize stab / SLB management except on iSeries
*/
if (cpu_has_feature(CPU_FTR_SLB))
slb_initialize();
else if (!firmware_has_feature(FW_FEATURE_ISERIES))
stab_initialize(get_paca()->stab_real);
DBG(" <- early_setup()\n");
}
static int ps3_ehci_driver_register(struct ps3_system_bus_driver *drv)
{
return firmware_has_feature(FW_FEATURE_PS3_LV1)
? ps3_system_bus_driver_register(drv)
: 0;
}
void vpa_init(int cpu)
{
int hwcpu = get_hard_smp_processor_id(cpu);
unsigned long addr;
long ret;
struct paca_struct *pp;
struct dtl_entry *dtl;
/*
* The spec says it "may be problematic" if CPU x registers the VPA of
* CPU y. We should never do that, but wail if we ever do.
*/
WARN_ON(cpu != smp_processor_id());
if (cpu_has_feature(CPU_FTR_ALTIVEC))
lppaca_of(cpu).vmxregs_in_use = 1;
if (cpu_has_feature(CPU_FTR_ARCH_207S))
lppaca_of(cpu).ebb_regs_in_use = 1;
addr = __pa(&lppaca_of(cpu));
ret = register_vpa(hwcpu, addr);
if (ret) {
pr_err("WARNING: VPA registration for cpu %d (hw %d) of area "
"%lx failed with %ld\n", cpu, hwcpu, addr, ret);
return;
}
/*
* PAPR says this feature is SLB-Buffer but firmware never
* reports that. All SPLPAR support SLB shadow buffer.
*/
addr = __pa(&slb_shadow[cpu]);
if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
ret = register_slb_shadow(hwcpu, addr);
if (ret)
pr_err("WARNING: SLB shadow buffer registration for "
"cpu %d (hw %d) of area %lx failed with %ld\n",
cpu, hwcpu, addr, ret);
}
/*
* Register dispatch trace log, if one has been allocated.
*/
pp = &paca[cpu];
dtl = pp->dispatch_log;
if (dtl) {
pp->dtl_ridx = 0;
pp->dtl_curr = dtl;
lppaca_of(cpu).dtl_idx = 0;
/* hypervisor reads buffer length from this field */
dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
ret = register_dtl(hwcpu, __pa(dtl));
if (ret)
pr_err("WARNING: DTL registration of cpu %d (hw %d) "
"failed with %ld\n", smp_processor_id(),
hwcpu, ret);
lppaca_of(cpu).dtl_enable_mask = 2;
}
}
void htab_initialize_secondary(void)
{
if (!firmware_has_feature(FW_FEATURE_LPAR))
mtspr(SPRN_SDR1, _SDR1);
}
void __init htab_initialize(void)
{
unsigned long table;
unsigned long pteg_count;
unsigned long mode_rw;
unsigned long base = 0, size = 0;
int i;
extern unsigned long tce_alloc_start, tce_alloc_end;
DBG(" -> htab_initialize()\n");
/* Initialize page sizes */
htab_init_page_sizes();
/*
* Calculate the required size of the htab. We want the number of
* PTEGs to equal one half the number of real pages.
*/
htab_size_bytes = htab_get_table_size();
pteg_count = htab_size_bytes >> 7;
htab_hash_mask = pteg_count - 1;
if (firmware_has_feature(FW_FEATURE_LPAR)) {
/* Using a hypervisor which owns the htab */
htab_address = NULL;
_SDR1 = 0;
} else {
/* Find storage for the HPT. Must be contiguous in
* the absolute address space.
*/
table = lmb_alloc(htab_size_bytes, htab_size_bytes);
DBG("Hash table allocated at %lx, size: %lx\n", table,
htab_size_bytes);
htab_address = abs_to_virt(table);
/* htab absolute addr + encoded htabsize */
_SDR1 = table + __ilog2(pteg_count) - 11;
/* Initialize the HPT with no entries */
memset((void *)table, 0, htab_size_bytes);
/* Set SDR1 */
mtspr(SPRN_SDR1, _SDR1);
}
mode_rw = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX;
/* On U3 based machines, we need to reserve the DART area and
* _NOT_ map it to avoid cache paradoxes as it's remapped non
* cacheable later on
*/
/* create bolted the linear mapping in the hash table */
for (i=0; i < lmb.memory.cnt; i++) {
base = (unsigned long)__va(lmb.memory.region[i].base);
size = lmb.memory.region[i].size;
DBG("creating mapping for region: %lx : %lx\n", base, size);
#ifdef CONFIG_U3_DART
/* Do not map the DART space. Fortunately, it will be aligned
* in such a way that it will not cross two lmb regions and
* will fit within a single 16Mb page.
* The DART space is assumed to be a full 16Mb region even if
* we only use 2Mb of that space. We will use more of it later
* for AGP GART. We have to use a full 16Mb large page.
*/
DBG("DART base: %lx\n", dart_tablebase);
if (dart_tablebase != 0 && dart_tablebase >= base
&& dart_tablebase < (base + size)) {
unsigned long dart_table_end = dart_tablebase + 16 * MB;
if (base != dart_tablebase)
BUG_ON(htab_bolt_mapping(base, dart_tablebase,
__pa(base), mode_rw,
mmu_linear_psize));
if ((base + size) > dart_table_end)
BUG_ON(htab_bolt_mapping(dart_tablebase+16*MB,
base + size,
__pa(dart_table_end),
mode_rw,
mmu_linear_psize));
continue;
}
#endif /* CONFIG_U3_DART */
BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
mode_rw, mmu_linear_psize));
}
/*
* If we have a memory_limit and we've allocated TCEs then we need to
* explicitly map the TCE area at the top of RAM. We also cope with the
* case that the TCEs start below memory_limit.
* tce_alloc_start/end are 16MB aligned so the mapping should work
* for either 4K or 16MB pages.
*/
if (tce_alloc_start) {
tce_alloc_start = (unsigned long)__va(tce_alloc_start);
tce_alloc_end = (unsigned long)__va(tce_alloc_end);
if (base + size >= tce_alloc_start)
tce_alloc_start = base + size + 1;
BUG_ON(htab_bolt_mapping(tce_alloc_start, tce_alloc_end,
__pa(tce_alloc_start), mode_rw,
mmu_linear_psize));
}
htab_finish_init();
DBG(" <- htab_initialize()\n");
}
static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
unsigned int desc_flags;
union ibmveth_buf_desc descs[6];
int last, i;
int force_bounce = 0;
/*
* veth handles a maximum of 6 segments including the header, so
* we have to linearize the skb if there are more than this.
*/
if (skb_shinfo(skb)->nr_frags > 5 && __skb_linearize(skb)) {
netdev->stats.tx_dropped++;
goto out;
}
/* veth can't checksum offload UDP */
if (skb->ip_summed == CHECKSUM_PARTIAL &&
((skb->protocol == htons(ETH_P_IP) &&
ip_hdr(skb)->protocol != IPPROTO_TCP) ||
(skb->protocol == htons(ETH_P_IPV6) &&
ipv6_hdr(skb)->nexthdr != IPPROTO_TCP)) &&
skb_checksum_help(skb)) {
netdev_err(netdev, "tx: failed to checksum packet\n");
netdev->stats.tx_dropped++;
goto out;
}
desc_flags = IBMVETH_BUF_VALID;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
unsigned char *buf = skb_transport_header(skb) +
skb->csum_offset;
desc_flags |= (IBMVETH_BUF_NO_CSUM | IBMVETH_BUF_CSUM_GOOD);
/* Need to zero out the checksum */
buf[0] = 0;
buf[1] = 0;
}
retry_bounce:
memset(descs, 0, sizeof(descs));
/*
* If a linear packet is below the rx threshold then
* copy it into the static bounce buffer. This avoids the
* cost of a TCE insert and remove.
*/
if (force_bounce || (!skb_is_nonlinear(skb) &&
(skb->len < tx_copybreak))) {
skb_copy_from_linear_data(skb, adapter->bounce_buffer,
skb->len);
descs[0].fields.flags_len = desc_flags | skb->len;
descs[0].fields.address = adapter->bounce_buffer_dma;
if (ibmveth_send(adapter, descs)) {
adapter->tx_send_failed++;
netdev->stats.tx_dropped++;
} else {
netdev->stats.tx_packets++;
netdev->stats.tx_bytes += skb->len;
}
goto out;
}
/* Map the header */
descs[0].fields.address = dma_map_single(&adapter->vdev->dev, skb->data,
skb_headlen(skb),
DMA_TO_DEVICE);
if (dma_mapping_error(&adapter->vdev->dev, descs[0].fields.address))
goto map_failed;
descs[0].fields.flags_len = desc_flags | skb_headlen(skb);
/* Map the frags */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
unsigned long dma_addr;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
dma_addr = dma_map_page(&adapter->vdev->dev, frag->page,
frag->page_offset, frag->size,
DMA_TO_DEVICE);
if (dma_mapping_error(&adapter->vdev->dev, dma_addr))
goto map_failed_frags;
descs[i+1].fields.flags_len = desc_flags | frag->size;
descs[i+1].fields.address = dma_addr;
}
if (ibmveth_send(adapter, descs)) {
adapter->tx_send_failed++;
netdev->stats.tx_dropped++;
} else {
netdev->stats.tx_packets++;
netdev->stats.tx_bytes += skb->len;
}
dma_unmap_single(&adapter->vdev->dev,
descs[0].fields.address,
descs[0].fields.flags_len & IBMVETH_BUF_LEN_MASK,
DMA_TO_DEVICE);
for (i = 1; i < skb_shinfo(skb)->nr_frags + 1; i++)
dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address,
descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK,
DMA_TO_DEVICE);
out:
dev_kfree_skb(skb);
return NETDEV_TX_OK;
map_failed_frags:
last = i+1;
for (i = 0; i < last; i++)
dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address,
descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK,
DMA_TO_DEVICE);
map_failed:
if (!firmware_has_feature(FW_FEATURE_CMO))
netdev_err(netdev, "tx: unable to map xmit buffer\n");
adapter->tx_map_failed++;
skb_linearize(skb);
force_bounce = 1;
goto retry_bounce;
}