diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries')
-rw-r--r-- | arch/powerpc/platforms/pseries/Kconfig | 2 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/cmm.c | 33 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh.c | 44 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh_driver.c | 2 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/hotplug-cpu.c | 2 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/hotplug-memory.c | 8 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/iommu.c | 6 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/pci_dlpar.c | 162 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/phyp_dump.c | 5 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/reconfig.c | 6 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/rtasd.c | 30 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/smp.c | 45 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/xics.c | 575 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/xics.h | 12 |
14 files changed, 503 insertions, 429 deletions
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 97619fd51e3..ddc2a307cd5 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -54,7 +54,7 @@ config PPC_SMLPAR config CMM tristate "Collaborative memory management" - depends on PPC_SMLPAR + depends on PPC_SMLPAR && !CRASH_DUMP default y help Select this option, if you want to enable the kernel interface diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 38fe32a7cc7..6567439fe78 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -28,6 +28,7 @@ #include <linux/kthread.h> #include <linux/module.h> #include <linux/oom.h> +#include <linux/reboot.h> #include <linux/sched.h> #include <linux/stringify.h> #include <linux/swap.h> @@ -121,7 +122,7 @@ static long cmm_alloc_pages(long nr) npa = (struct cmm_page_array *)__get_free_page(GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC); if (!npa) { - pr_info("%s: Can not allocate new page list\n", __FUNCTION__); + pr_info("%s: Can not allocate new page list\n", __func__); free_page(addr); break; } @@ -138,7 +139,7 @@ static long cmm_alloc_pages(long nr) } if ((rc = plpar_page_set_loaned(__pa(addr)))) { - pr_err("%s: Can not set page to loaned. rc=%ld\n", __FUNCTION__, rc); + pr_err("%s: Can not set page to loaned. rc=%ld\n", __func__, rc); spin_unlock(&cmm_lock); free_page(addr); break; @@ -384,6 +385,26 @@ static void cmm_unregister_sysfs(struct sys_device *sysdev) } /** + * cmm_reboot_notifier - Make sure pages are not still marked as "loaned" + * + **/ +static int cmm_reboot_notifier(struct notifier_block *nb, + unsigned long action, void *unused) +{ + if (action == SYS_RESTART) { + if (cmm_thread_ptr) + kthread_stop(cmm_thread_ptr); + cmm_thread_ptr = NULL; + cmm_free_pages(loaned_pages); + } + return NOTIFY_DONE; +} + +static struct notifier_block cmm_reboot_nb = { + .notifier_call = cmm_reboot_notifier, +}; + +/** * cmm_init - Module initialization * * Return value: @@ -399,9 +420,12 @@ static int cmm_init(void) if ((rc = register_oom_notifier(&cmm_oom_nb)) < 0) return rc; - if ((rc = cmm_sysfs_register(&cmm_sysdev))) + if ((rc = register_reboot_notifier(&cmm_reboot_nb))) goto out_oom_notifier; + if ((rc = cmm_sysfs_register(&cmm_sysdev))) + goto out_reboot_notifier; + if (cmm_disabled) return rc; @@ -415,6 +439,8 @@ static int cmm_init(void) out_unregister_sysfs: cmm_unregister_sysfs(&cmm_sysdev); +out_reboot_notifier: + unregister_reboot_notifier(&cmm_reboot_nb); out_oom_notifier: unregister_oom_notifier(&cmm_oom_nb); return rc; @@ -431,6 +457,7 @@ static void cmm_exit(void) if (cmm_thread_ptr) kthread_stop(cmm_thread_ptr); unregister_oom_notifier(&cmm_oom_nb); + unregister_reboot_notifier(&cmm_reboot_nb); cmm_free_pages(loaned_pages); cmm_unregister_sysfs(&cmm_sysdev); } diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 54816d75b57..989d6462c15 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -21,6 +21,8 @@ * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com> */ +#undef DEBUG + #include <linux/delay.h> #include <linux/init.h> #include <linux/list.h> @@ -488,10 +490,8 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) || pdn->eeh_mode & EEH_MODE_NOCHECK) { ignored_check++; -#ifdef DEBUG - printk ("EEH:ignored check (%x) for %s %s\n", - pdn->eeh_mode, pci_name (dev), dn->full_name); -#endif + pr_debug("EEH: Ignored check (%x) for %s %s\n", + pdn->eeh_mode, pci_name (dev), dn->full_name); return 0; } @@ -1014,10 +1014,9 @@ static void *early_enable_eeh(struct device_node *dn, void *data) eeh_subsystem_enabled = 1; pdn->eeh_mode |= EEH_MODE_SUPPORTED; -#ifdef DEBUG - printk(KERN_DEBUG "EEH: %s: eeh enabled, config=%x pe_config=%x\n", - dn->full_name, pdn->eeh_config_addr, pdn->eeh_pe_config_addr); -#endif + pr_debug("EEH: %s: eeh enabled, config=%x pe_config=%x\n", + dn->full_name, pdn->eeh_config_addr, + pdn->eeh_pe_config_addr); } else { /* This device doesn't support EEH, but it may have an @@ -1161,13 +1160,17 @@ static void eeh_add_device_late(struct pci_dev *dev) if (!dev || !eeh_subsystem_enabled) return; -#ifdef DEBUG - printk(KERN_DEBUG "EEH: adding device %s\n", pci_name(dev)); -#endif + pr_debug("EEH: Adding device %s\n", pci_name(dev)); - pci_dev_get (dev); dn = pci_device_to_OF_node(dev); pdn = PCI_DN(dn); + if (pdn->pcidev == dev) { + pr_debug("EEH: Already referenced !\n"); + return; + } + WARN_ON(pdn->pcidev); + + pci_dev_get (dev); pdn->pcidev = dev; pci_addr_cache_insert_device(dev); @@ -1206,17 +1209,18 @@ static void eeh_remove_device(struct pci_dev *dev) return; /* Unregister the device with the EEH/PCI address search system */ -#ifdef DEBUG - printk(KERN_DEBUG "EEH: remove device %s\n", pci_name(dev)); -#endif - pci_addr_cache_remove_device(dev); - eeh_sysfs_remove_device(dev); + pr_debug("EEH: Removing device %s\n", pci_name(dev)); dn = pci_device_to_OF_node(dev); - if (PCI_DN(dn)->pcidev) { - PCI_DN(dn)->pcidev = NULL; - pci_dev_put (dev); + if (PCI_DN(dn)->pcidev == NULL) { + pr_debug("EEH: Not referenced !\n"); + return; } + PCI_DN(dn)->pcidev = NULL; + pci_dev_put (dev); + + pci_addr_cache_remove_device(dev); + eeh_sysfs_remove_device(dev); } void eeh_remove_bus_device(struct pci_dev *dev) diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c index 8c1ca477c52..0ad56ff7b4a 100644 --- a/arch/powerpc/platforms/pseries/eeh_driver.c +++ b/arch/powerpc/platforms/pseries/eeh_driver.c @@ -41,7 +41,7 @@ static inline const char * pcid_name (struct pci_dev *pdev) return ""; } -#ifdef DEBUG +#if 0 static void print_device_node_tree(struct pci_dn *pdn, int dent) { int i; diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 1f032483c02..a20ead87153 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -116,7 +116,7 @@ static void pseries_cpu_die(unsigned int cpu) cpu_status = query_cpu_stopped(pcpu); if (cpu_status == 0 || cpu_status == -1) break; - msleep(200); + cpu_relax(); } if (cpu_status != 0) { printk("Querying DEAD? cpu %i (%i) shows %i\n", diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index a1a368dd2d9..a623ad256e9 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -21,7 +21,13 @@ static int pseries_remove_lmb(unsigned long base, unsigned int lmb_size) struct zone *zone; int ret; - start_pfn = base >> PFN_SECTION_SHIFT; + start_pfn = base >> PAGE_SHIFT; + + if (!pfn_valid(start_pfn)) { + lmb_remove(base, lmb_size); + return 0; + } + zone = page_zone(pfn_to_page(start_pfn)); /* diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index a8c446697f9..c90817acb47 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -32,6 +32,7 @@ #include <linux/string.h> #include <linux/pci.h> #include <linux/dma-mapping.h> +#include <linux/crash_dump.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -291,9 +292,8 @@ static void iommu_table_setparms(struct pci_controller *phb, tbl->it_base = (unsigned long)__va(*basep); -#ifndef CONFIG_CRASH_DUMP - memset((void *)tbl->it_base, 0, *sizep); -#endif + if (!is_kdump_kernel()) + memset((void *)tbl->it_base, 0, *sizep); tbl->it_busno = phb->bus->number; diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 21a6d55418f..5e1ed3d60ee 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -25,6 +25,8 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#undef DEBUG + #include <linux/pci.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> @@ -69,74 +71,25 @@ EXPORT_SYMBOL_GPL(pcibios_find_pci_bus); * Remove all of the PCI devices under this bus both from the * linux pci device tree, and from the powerpc EEH address cache. */ -void -pcibios_remove_pci_devices(struct pci_bus *bus) +void pcibios_remove_pci_devices(struct pci_bus *bus) { - struct pci_dev *dev, *tmp; + struct pci_dev *dev, *tmp; + struct pci_bus *child_bus; + + /* First go down child busses */ + list_for_each_entry(child_bus, &bus->children, node) + pcibios_remove_pci_devices(child_bus); + pr_debug("PCI: Removing devices on bus %04x:%02x\n", + pci_domain_nr(bus), bus->number); list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) { + pr_debug(" * Removing %s...\n", pci_name(dev)); eeh_remove_bus_device(dev); - pci_remove_bus_device(dev); - } + pci_remove_bus_device(dev); + } } EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices); -/* Must be called before pci_bus_add_devices */ -void -pcibios_fixup_new_pci_devices(struct pci_bus *bus) -{ - struct pci_dev *dev; - - list_for_each_entry(dev, &bus->devices, bus_list) { - /* Skip already-added devices */ - if (!dev->is_added) { - int i; - - /* Fill device archdata and setup iommu table */ - pcibios_setup_new_device(dev); - - pci_read_irq_line(dev); - for (i = 0; i < PCI_NUM_RESOURCES; i++) { - struct resource *r = &dev->resource[i]; - - if (r->parent || !r->start || !r->flags) - continue; - pci_claim_resource(dev, i); - } - } - } -} -EXPORT_SYMBOL_GPL(pcibios_fixup_new_pci_devices); - -static int -pcibios_pci_config_bridge(struct pci_dev *dev) -{ - u8 sec_busno; - struct pci_bus *child_bus; - - /* Get busno of downstream bus */ - pci_read_config_byte(dev, PCI_SECONDARY_BUS, &sec_busno); - - /* Add to children of PCI bridge dev->bus */ - child_bus = pci_add_new_bus(dev->bus, dev, sec_busno); - if (!child_bus) { - printk (KERN_ERR "%s: could not add second bus\n", __func__); - return -EIO; - } - sprintf(child_bus->name, "PCI Bus #%02x", child_bus->number); - - pci_scan_child_bus(child_bus); - - /* Fixup new pci devices */ - pcibios_fixup_new_pci_devices(child_bus); - - /* Make the discovered devices available */ - pci_bus_add_devices(child_bus); - - eeh_add_device_tree_late(child_bus); - return 0; -} - /** * pcibios_add_pci_devices - adds new pci devices to bus * @@ -147,10 +100,9 @@ pcibios_pci_config_bridge(struct pci_dev *dev) * is how this routine differs from other, similar pcibios * routines.) */ -void -pcibios_add_pci_devices(struct pci_bus * bus) +void pcibios_add_pci_devices(struct pci_bus * bus) { - int slotno, num, mode; + int slotno, num, mode, pass, max; struct pci_dev *dev; struct device_node *dn = pci_bus_to_OF_node(bus); @@ -162,26 +114,23 @@ pcibios_add_pci_devices(struct pci_bus * bus) if (mode == PCI_PROBE_DEVTREE) { /* use ofdt-based probe */ - of_scan_bus(dn, bus); - if (!list_empty(&bus->devices)) { - pcibios_fixup_new_pci_devices(bus); - pci_bus_add_devices(bus); - eeh_add_device_tree_late(bus); - } + of_rescan_bus(dn, bus); } else if (mode == PCI_PROBE_NORMAL) { /* use legacy probe */ slotno = PCI_SLOT(PCI_DN(dn->child)->devfn); num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0)); - if (num) { - pcibios_fixup_new_pci_devices(bus); - pci_bus_add_devices(bus); - eeh_add_device_tree_late(bus); + if (!num) + return; + pcibios_setup_bus_devices(bus); + max = bus->secondary; + for (pass=0; pass < 2; pass++) + list_for_each_entry(dev, &bus->devices, bus_list) { + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || + dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) + max = pci_scan_bridge(bus, dev, max, pass); } - - list_for_each_entry(dev, &bus->devices, bus_list) - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) - pcibios_pci_config_bridge(dev); } + pcibios_finish_adding_to_bus(bus); } EXPORT_SYMBOL_GPL(pcibios_add_pci_devices); @@ -190,6 +139,8 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn) struct pci_controller *phb; int primary; + pr_debug("PCI: Initializing new hotplug PHB %s\n", dn->full_name); + primary = list_empty(&hose_list); phb = pcibios_alloc_controller(dn); if (!phb) @@ -203,10 +154,59 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn) eeh_add_device_tree_early(dn); scan_phb(phb); - pcibios_fixup_new_pci_devices(phb->bus); - pci_bus_add_devices(phb->bus); - eeh_add_device_tree_late(phb->bus); + pcibios_finish_adding_to_bus(phb->bus); return phb; } EXPORT_SYMBOL_GPL(init_phb_dynamic); + +/* RPA-specific bits for removing PHBs */ +int remove_phb_dynamic(struct pci_controller *phb) +{ + struct pci_bus *b = phb->bus; + struct resource *res; + int rc, i; + + pr_debug("PCI: Removing PHB %04x:%02x... \n", + pci_domain_nr(b), b->number); + + /* We cannot to remove a root bus that has children */ + if (!(list_empty(&b->children) && list_empty(&b->devices))) + return -EBUSY; + + /* We -know- there aren't any child devices anymore at this stage + * and thus, we can safely unmap the IO space as it's not in use + */ + res = &phb->io_resource; + if (res->flags & IORESOURCE_IO) { + rc = pcibios_unmap_io_space(b); + if (rc) { + printk(KERN_ERR "%s: failed to unmap IO on bus %s\n", + __func__, b->name); + return 1; + } + } + + /* Unregister the bridge device from sysfs and remove the PCI bus */ + device_unregister(b->bridge); + phb->bus = NULL; + pci_remove_bus(b); + + /* Now release the IO resource */ + if (res->flags & IORESOURCE_IO) + release_resource(res); + + /* Release memory resources */ + for (i = 0; i < 3; ++i) { + res = &phb->mem_resources[i]; + if (!(res->flags & IORESOURCE_MEM)) + continue; + release_resource(res); + } + + /* Free pci_controller data structure */ + pcibios_free_controller(phb); + + return 0; +} +EXPORT_SYMBOL_GPL(remove_phb_dynamic); diff --git a/arch/powerpc/platforms/pseries/phyp_dump.c b/arch/powerpc/platforms/pseries/phyp_dump.c index edbc012c2eb..6cf35cd8d0b 100644 --- a/arch/powerpc/platforms/pseries/phyp_dump.c +++ b/arch/powerpc/platforms/pseries/phyp_dump.c @@ -130,6 +130,9 @@ static unsigned long init_dump_header(struct phyp_dump_header *ph) static void print_dump_header(const struct phyp_dump_header *ph) { #ifdef DEBUG + if (ph == NULL) + return; + printk(KERN_INFO "dump header:\n"); /* setup some ph->sections required */ printk(KERN_INFO "version = %d\n", ph->version); @@ -411,6 +414,8 @@ static int __init phyp_dump_setup(void) of_node_put(rtas); } + ibm_configure_kernel_dump = rtas_token("ibm,configure-kernel-dump"); + print_dump_header(dump_header); dump_area_length = init_dump_header(&phdr); /* align down */ diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 7637bd38c79..c591a25b0b0 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -466,11 +466,11 @@ static int do_update_property(char *buf, size_t bufsize) else action = PSERIES_DRCONF_MEM_REMOVE; - blocking_notifier_call_chain(&pSeries_reconfig_chain, - action, value); + rc = blocking_notifier_call_chain(&pSeries_reconfig_chain, + action, value); } - return 0; + return rc; } /** diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c index c9ffd8c225f..afad9f5ac0a 100644 --- a/arch/powerpc/platforms/pseries/rtasd.c +++ b/arch/powerpc/platforms/pseries/rtasd.c @@ -208,6 +208,7 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) break; case ERR_TYPE_KERNEL_PANIC: default: + WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */ spin_unlock_irqrestore(&rtasd_log_lock, s); return; } @@ -227,6 +228,7 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) /* Check to see if we need to or have stopped logging */ if (fatal || !logging_enabled) { logging_enabled = 0; + WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */ spin_unlock_irqrestore(&rtasd_log_lock, s); return; } @@ -249,11 +251,13 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) else rtas_log_start += 1; + WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */ spin_unlock_irqrestore(&rtasd_log_lock, s); wake_up_interruptible(&rtas_log_wait); break; case ERR_TYPE_KERNEL_PANIC: default: + WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */ spin_unlock_irqrestore(&rtasd_log_lock, s); return; } @@ -295,19 +299,29 @@ static ssize_t rtas_log_read(struct file * file, char __user * buf, if (!tmp) return -ENOMEM; - spin_lock_irqsave(&rtasd_log_lock, s); /* if it's 0, then we know we got the last one (the one in NVRAM) */ - if (rtas_log_size == 0 && logging_enabled) - nvram_clear_error_log(); - spin_unlock_irqrestore(&rtasd_log_lock, s); + while (rtas_log_size == 0) { + if (file->f_flags & O_NONBLOCK) { + spin_unlock_irqrestore(&rtasd_log_lock, s); + error = -EAGAIN; + goto out; + } + if (!logging_enabled) { + spin_unlock_irqrestore(&rtasd_log_lock, s); + error = -ENODATA; + goto out; + } + nvram_clear_error_log(); - error = wait_event_interruptible(rtas_log_wait, rtas_log_size); - if (error) - goto out; + spin_unlock_irqrestore(&rtasd_log_lock, s); + error = wait_event_interruptible(rtas_log_wait, rtas_log_size); + if (error) + goto out; + spin_lock_irqsave(&rtasd_log_lock, s); + } - spin_lock_irqsave(&rtasd_log_lock, s); offset = rtas_error_log_buffer_max * (rtas_log_start & LOG_NUMBER_MASK); memcpy(tmp, &rtas_log_buf[offset], count); diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 9d8f8c84ab8..1a231c389ba 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -37,7 +37,6 @@ #include <asm/paca.h> #include <asm/time.h> #include <asm/machdep.h> -#include "xics.h" #include <asm/cputable.h> #include <asm/firmware.h> #include <asm/system.h> @@ -49,11 +48,12 @@ #include "plpar_wrappers.h" #include "pseries.h" +#include "xics.h" /* - * The primary thread of each non-boot processor is recorded here before - * smp init. + * The Primary thread of each non-boot processor was started from the OF client + * interface by prom_hold_cpus and is spinning on secondary_hold_spinloop. */ static cpumask_t of_spin_map; @@ -105,36 +105,6 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu) } #ifdef CONFIG_XICS -static inline void smp_xics_do_message(int cpu, int msg) -{ - set_bit(msg, &xics_ipi_message[cpu].value); - mb(); - xics_cause_IPI(cpu); -} - -static void smp_xics_message_pass(int target, int msg) -{ - unsigned int i; - - if (target < NR_CPUS) { - smp_xics_do_message(target, msg); - } else { - for_each_online_cpu(i) { - if (target == MSG_ALL_BUT_SELF - && i == smp_processor_id()) - continue; - smp_xics_do_message(i, msg); - } - } -} - -static int __init smp_xics_probe(void) -{ - xics_request_IPIs(); - - return cpus_weight(cpu_possible_map); -} - static void __devinit smp_xics_setup_cpu(int cpu) { if (cpu != boot_cpuid) @@ -191,8 +161,7 @@ static void __devinit smp_pSeries_kick_cpu(int nr) static int smp_pSeries_cpu_bootable(unsigned int nr) { /* Special case - we inhibit secondary thread startup - * during boot if the user requests it. Odd-numbered - * cpus are assumed to be secondary threads. + * during boot if the user requests it. */ if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT) && @@ -229,11 +198,7 @@ static void __init smp_init_pseries(void) /* Mark threads which are still spinning in hold loops. */ if (cpu_has_feature(CPU_FTR_SMT)) { for_each_present_cpu(i) { - if (i % 2 == 0) - /* - * Even-numbered logical cpus correspond to - * primary threads. - */ + if (cpu_thread_in_core(i) == 0) cpu_set(i, of_spin_map); } } else { diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 0fc830f576f..f7a69021b7b 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -9,32 +9,30 @@ * 2 of the License, or (at your option) any later version. */ - #include <linux/types.h> #include <linux/threads.h> #include <linux/kernel.h> #include <linux/irq.h> #include <linux/smp.h> #include <linux/interrupt.h> -#include <linux/signal.h> #include <linux/init.h> -#include <linux/gfp.h> #include <linux/radix-tree.h> #include <linux/cpu.h> +#include <linux/of.h> #include <asm/firmware.h> -#include <asm/prom.h> #include <asm/io.h> #include <asm/pgtable.h> #include <asm/smp.h> #include <asm/rtas.h> #include <asm/hvcall.h> #include <asm/machdep.h> -#include <asm/i8259.h> #include "xics.h" #include "plpar_wrappers.h" +static struct irq_host *xics_host; + #define XICS_IPI 2 #define XICS_IRQ_SPURIOUS 0 @@ -47,6 +45,20 @@ */ #define IPI_PRIORITY 4 +static unsigned int default_server = 0xFF; +static unsigned int default_distrib_server = 0; +static unsigned int interrupt_server_size = 8; + +/* RTAS service tokens */ +static int ibm_get_xive; +static int ibm_set_xive; +static int ibm_int_on; +static int ibm_int_off; + + +/* Direct hardware low level accessors */ + +/* The part of the interrupt presentation layer that we care about */ struct xics_ipl { union { u32 word; @@ -65,27 +77,6 @@ struct xics_ipl { static struct xics_ipl __iomem *xics_per_cpu[NR_CPUS]; -static unsigned int default_server = 0xFF; -static unsigned int default_distrib_server = 0; -static unsigned int interrupt_server_size = 8; - -static struct irq_host *xics_host; - -/* - * XICS only has a single IPI, so encode the messages per CPU - */ -struct xics_ipi_struct xics_ipi_message[NR_CPUS] __cacheline_aligned; - -/* RTAS service tokens */ -static int ibm_get_xive; -static int ibm_set_xive; -static int ibm_int_on; -static int ibm_int_off; - - -/* Direct HW low level accessors */ - - static inline unsigned int direct_xirr_info_get(void) { int cpu = smp_processor_id(); @@ -93,7 +84,7 @@ static inline unsigned int direct_xirr_info_get(void) return in_be32(&xics_per_cpu[cpu]->xirr.word); } -static inline void direct_xirr_info_set(int value) +static inline void direct_xirr_info_set(unsigned int value) { int cpu = smp_processor_id(); @@ -115,7 +106,6 @@ static inline void direct_qirr_info(int n_cpu, u8 value) /* LPAR low level accessors */ - static inline unsigned int lpar_xirr_info_get(void) { unsigned long lpar_rc; @@ -127,15 +117,14 @@ static inline unsigned int lpar_xirr_info_get(void) return (unsigned int)return_value; } -static inline void lpar_xirr_info_set(int value) +static inline void lpar_xirr_info_set(unsigned int value) { unsigned long lpar_rc; - unsigned long val64 = value & 0xffffffff; - lpar_rc = plpar_eoi(val64); + lpar_rc = plpar_eoi(value); if (lpar_rc != H_SUCCESS) - panic("bad return code EOI - rc = %ld, value=%lx\n", lpar_rc, - val64); + panic("bad return code EOI - rc = %ld, value=%x\n", lpar_rc, + value); } static inline void lpar_cppr_info(u8 value) @@ -157,48 +146,7 @@ static inline void lpar_qirr_info(int n_cpu , u8 value) } -/* High level handlers and init code */ - -static void xics_update_irq_servers(void) -{ - int i, j; - struct device_node *np; - u32 ilen; - const u32 *ireg, *isize; - u32 hcpuid; - - /* Find the server numbers for the boot cpu. */ - np = of_get_cpu_node(boot_cpuid, NULL); - BUG_ON(!np); - - ireg = of_get_property(np, "ibm,ppc-interrupt-gserver#s", &ilen); - if (!ireg) { - of_node_put(np); - return; - } - - i = ilen / sizeof(int); - hcpuid = get_hard_smp_processor_id(boot_cpuid); - - /* Global interrupt distribution server is specified in the last - * entry of "ibm,ppc-interrupt-gserver#s" property. Get the last - * entry fom this property for current boot cpu id and use it as - * default distribution server - */ - for (j = 0; j < i; j += 2) { - if (ireg[j] == hcpuid) { - default_server = hcpuid; - default_distrib_server = ireg[j+1]; - - isize = of_get_property(np, - "ibm,interrupt-server#-size", NULL); - if (isize) - interrupt_server_size = *isize; - } - } - - of_node_put(np); -} +/* Interface to generic irq subsystem */ #ifdef CONFIG_SMP static int get_irq_server(unsigned int virq, unsigned int strict_check) @@ -208,9 +156,6 @@ static int get_irq_server(unsigned int virq, unsigned int strict_check) cpumask_t cpumask = irq_desc[virq].affinity; cpumask_t tmp = CPU_MASK_NONE; - if (! cpu_isset(default_server, cpu_online_map)) - xics_update_irq_servers(); - if (!distribute_irqs) return default_server; @@ -238,7 +183,6 @@ static int get_irq_server(unsigned int virq, unsigned int strict_check) } #endif - static void xics_unmask_irq(unsigned int virq) { unsigned int irq; @@ -257,21 +201,28 @@ static void xics_unmask_irq(unsigned int virq) call_status = rtas_call(ibm_set_xive, 3, 1, NULL, irq, server, DEFAULT_PRIORITY); if (call_status != 0) { - printk(KERN_ERR "xics_enable_irq: irq=%u: ibm_set_xive " - "returned %d\n", irq, call_status); - printk("set_xive %x, server %x\n", ibm_set_xive, server); + printk(KERN_ERR + "%s: ibm_set_xive irq %u server %x returned %d\n", + __func__, irq, server, call_status); return; } /* Now unmask the interrupt (often a no-op) */ call_status = rtas_call(ibm_int_on, 1, 1, NULL, irq); if (call_status != 0) { - printk(KERN_ERR "xics_enable_irq: irq=%u: ibm_int_on " - "returned %d\n", irq, call_status); + printk(KERN_ERR "%s: ibm_int_on irq=%u returned %d\n", + __func__, irq, call_status); return; } } +static unsigned int xics_startup(unsigned int virq) +{ + /* unmask it */ + xics_unmask_irq(virq); + return 0; +} + static void xics_mask_real_irq(unsigned int irq) { int call_status; @@ -281,8 +232,8 @@ static void xics_mask_real_irq(unsigned int irq) call_status = rtas_call(ibm_int_off, 1, 1, NULL, irq); if (call_status != 0) { - printk(KERN_ERR "xics_disable_real_irq: irq=%u: " - "ibm_int_off returned %d\n", irq, call_status); + printk(KERN_ERR "%s: ibm_int_off irq=%u returned %d\n", + __func__, irq, call_status); return; } @@ -290,8 +241,8 @@ static void xics_mask_real_irq(unsigned int irq) call_status = rtas_call(ibm_set_xive, 3, 1, NULL, irq, default_server, 0xff); if (call_status != 0) { - printk(KERN_ERR "xics_disable_irq: irq=%u: ibm_set_xive(0xff)" - " returned %d\n", irq, call_status); + printk(KERN_ERR "%s: ibm_set_xive(0xff) irq=%u returned %d\n", + __func__, irq, call_status); return; } } @@ -308,132 +259,77 @@ static void xics_mask_irq(unsigned int virq) xics_mask_real_irq(irq); } -static unsigned int xics_startup(unsigned int virq) +static void xics_mask_unknown_vec(unsigned int vec) { - unsigned int irq; - - /* force a reverse mapping of the interrupt so it gets in the cache */ - irq = (unsigned int)irq_map[virq].hwirq; - irq_radix_revmap(xics_host, irq); - - /* unmask it */ - xics_unmask_irq(virq); - return 0; -} - -static void xics_eoi_direct(unsigned int virq) -{ - unsigned int irq = (unsigned int)irq_map[virq].hwirq; - - iosync(); - direct_xirr_info_set((0xff << 24) | irq); + printk(KERN_ERR "Interrupt %u (real) is invalid, disabling it.\n", vec); + xics_mask_real_irq(vec); } - -static void xics_eoi_lpar(unsigned int virq) +static inline unsigned int xics_xirr_vector(unsigned int xirr) { - unsigned int irq = (unsigned int)irq_map[virq].hwirq; - - iosync(); - lpar_xirr_info_set((0xff << 24) | irq); + /* + * The top byte is the old cppr, to be restored on EOI. + * The remaining 24 bits are the vector. + */ + return xirr & 0x00ffffff; } -static inline unsigned int xics_remap_irq(unsigned int vec) +static unsigned int xics_get_irq_direct(void) { + unsigned int xirr = direct_xirr_info_get(); + unsigned int vec = xics_xirr_vector(xirr); unsigned int irq; - vec &= 0x00ffffff; - if (vec == XICS_IRQ_SPURIOUS) return NO_IRQ; - irq = irq_radix_revmap(xics_host, vec); + + irq = irq_radix_revmap_lookup(xics_host, vec); if (likely(irq != NO_IRQ)) return irq; - printk(KERN_ERR "Interrupt %u (real) is invalid," - " disabling it.\n", vec); - xics_mask_real_irq(vec); - return NO_IRQ; -} + /* We don't have a linux mapping, so have rtas mask it. */ + xics_mask_unknown_vec(vec); -static unsigned int xics_get_irq_direct(void) -{ - return xics_remap_irq(direct_xirr_info_get()); + /* We might learn about it later, so EOI it */ + direct_xirr_info_set(xirr); + return NO_IRQ; } static unsigned int xics_get_irq_lpar(void) { - return xics_remap_irq(lpar_xirr_info_get()); -} - -#ifdef CONFIG_SMP - -static irqreturn_t xics_ipi_dispatch(int cpu) -{ - WARN_ON(cpu_is_offline(cpu)); + unsigned int xirr = lpar_xirr_info_get(); + unsigned int vec = xics_xirr_vector(xirr); + unsigned int irq; - while (xics_ipi_message[cpu].value) { - if (test_and_clear_bit(PPC_MSG_CALL_FUNCTION, - &xics_ipi_message[cpu].value)) { - mb(); - smp_message_recv(PPC_MSG_CALL_FUNCTION); - } - if (test_and_clear_bit(PPC_MSG_RESCHEDULE, - &xics_ipi_message[cpu].value)) { - mb(); - smp_message_recv(PPC_MSG_RESCHEDULE); - } - if (test_and_clear_bit(PPC_MSG_CALL_FUNC_SINGLE, - &xics_ipi_message[cpu].value)) { - mb(); - smp_message_recv(PPC_MSG_CALL_FUNC_SINGLE); - } -#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) - if (test_and_clear_bit(PPC_MSG_DEBUGGER_BREAK, - &xics_ipi_message[cpu].value)) { - mb(); - smp_message_recv(PPC_MSG_DEBUGGER_BREAK); - } -#endif - } - return IRQ_HANDLED; -} + if (vec == XICS_IRQ_SPURIOUS) + return NO_IRQ; -static irqreturn_t xics_ipi_action_direct(int irq, void *dev_id) -{ - int cpu = smp_processor_id(); + irq = irq_radix_revmap_lookup(xics_host, vec); + if (likely(irq != NO_IRQ)) + return irq; - direct_qirr_info(cpu, 0xff); + /* We don't have a linux mapping, so have RTAS mask it. */ + xics_mask_unknown_vec(vec); - return xics_ipi_dispatch(cpu); + /* We might learn about it later, so EOI it */ + lpar_xirr_info_set(xirr); + return NO_IRQ; } -static irqreturn_t xics_ipi_action_lpar(int irq, void *dev_id) +static void xics_eoi_direct(unsigned int virq) { - int cpu = smp_processor_id(); - - lpar_qirr_info(cpu, 0xff); + unsigned int irq = (unsigned int)irq_map[virq].hwirq; - return xics_ipi_dispatch(cpu); + iosync(); + direct_xirr_info_set((0xff << 24) | irq); } -void xics_cause_IPI(int cpu) +static void xics_eoi_lpar(unsigned int virq) { - if (firmware_has_feature(FW_FEATURE_LPAR)) - lpar_qirr_info(cpu, IPI_PRIORITY); - else - direct_qirr_info(cpu, IPI_PRIORITY); -} - -#endif /* CONFIG_SMP */ + unsigned int irq = (unsigned int)irq_map[virq].hwirq; -static void xics_set_cpu_priority(unsigned char cppr) -{ - if (firmware_has_feature(FW_FEATURE_LPAR)) - lpar_cppr_info(cppr); - else - direct_cppr_info(cppr); iosync(); + lpar_xirr_info_set((0xff << 24) | irq); } static void xics_set_affinity(unsigned int virq, cpumask_t cpumask) @@ -450,8 +346,8 @@ static void xics_set_affinity(unsigned int virq, cpumask_t cpumask) status = rtas_call(ibm_get_xive, 1, 3, xics_status, irq); if (status) { - printk(KERN_ERR "xics_set_affinity: irq=%u ibm,get-xive " - "returns %d\n", irq, status); + printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n", + __func__, irq, status); return; } @@ -463,8 +359,9 @@ static void xics_set_affinity(unsigned int virq, cpumask_t cpumask) if (irq_server == -1) { char cpulist[128]; cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask); - printk(KERN_WARNING "xics_set_affinity: No online cpus in " - "the mask %s for irq %d\n", cpulist, virq); + printk(KERN_WARNING + "%s: No online cpus in the mask %s for irq %d\n", + __func__, cpulist, virq); return; } @@ -472,28 +369,12 @@ static void xics_set_affinity(unsigned int virq, cpumask_t cpumask) irq, irq_server, xics_status[1]); if (status) { - printk(KERN_ERR "xics_set_affinity: irq=%u ibm,set-xive " - "returns %d\n", irq, status); + printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n", + __func__, irq, status); return; } } -void xics_setup_cpu(void) -{ - xics_set_cpu_priority(0xff); - - /* - * Put the calling processor into the GIQ. This is really only - * necessary from a secondary thread as the OF start-cpu interface - * performs this function for us on primary threads. - * - * XXX: undo of teardown on kexec needs this too, as may hotplug - */ - rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, - (1UL << interrupt_server_size) - 1 - default_distrib_server, 1); -} - - static struct irq_chip xics_pic_direct = { .typename = " XICS ", .startup = xics_startup, @@ -503,7 +384,6 @@ static struct irq_chip xics_pic_direct = { .set_affinity = xics_set_affinity }; - static struct irq_chip xics_pic_lpar = { .typename = " XICS ", .startup = xics_startup, @@ -513,6 +393,9 @@ static struct irq_chip xics_pic_lpar = { .set_affinity = xics_set_affinity }; + +/* Interface to arch irq controller subsystem layer */ + /* Points to the irq_chip we're actually using */ static struct irq_chip *xics_irq_chip; @@ -530,6 +413,9 @@ static int xics_host_map(struct irq_host *h, unsigned int virq, { pr_debug("xics: map virq %d, hwirq 0x%lx\n", virq, hw); + /* Insert the interrupt mapping into the radix tree for fast lookup */ + irq_radix_revmap_insert(xics_host, virq, hw); + get_irq_desc(virq)->status |= IRQ_LEVEL; set_irq_chip_and_handler(virq, xics_irq_chip, handle_fasteoi_irq); return 0; @@ -569,10 +455,164 @@ static void __init xics_init_host(void) irq_set_default_host(xics_host); } + +/* Inter-processor interrupt support */ + +#ifdef CONFIG_SMP +/* + * XICS only has a single IPI, so encode the messages per CPU + */ +struct xics_ipi_struct { + unsigned long value; + } ____cacheline_aligned; + +static struct xics_ipi_struct xics_ipi_message[NR_CPUS] __cacheline_aligned; + +static inline void smp_xics_do_message(int cpu, int msg) +{ + set_bit(msg, &xics_ipi_message[cpu].value); + mb(); + if (firmware_has_feature(FW_FEATURE_LPAR)) + lpar_qirr_info(cpu, IPI_PRIORITY); + else + direct_qirr_info(cpu, IPI_PRIORITY); +} + +void smp_xics_message_pass(int target, int msg) +{ + unsigned int i; + + if (target < NR_CPUS) { + smp_xics_do_message(target, msg); + } else { + for_each_online_cpu(i) { + if (target == MSG_ALL_BUT_SELF + && i == smp_processor_id()) + continue; + smp_xics_do_message(i, msg); + } + } +} + +static irqreturn_t xics_ipi_dispatch(int cpu) +{ + WARN_ON(cpu_is_offline(cpu)); + + mb(); /* order mmio clearing qirr */ + while (xics_ipi_message[cpu].value) { + if (test_and_clear_bit(PPC_MSG_CALL_FUNCTION, + &xics_ipi_message[cpu].value)) { + smp_message_recv(PPC_MSG_CALL_FUNCTION); + } + if (test_and_clear_bit(PPC_MSG_RESCHEDULE, + &xics_ipi_message[cpu].value)) { + smp_message_recv(PPC_MSG_RESCHEDULE); + } + if (test_and_clear_bit(PPC_MSG_CALL_FUNC_SINGLE, + &xics_ipi_message[cpu].value)) { + smp_message_recv(PPC_MSG_CALL_FUNC_SINGLE); + } +#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) + if (test_and_clear_bit(PPC_MSG_DEBUGGER_BREAK, + &xics_ipi_message[cpu].value)) { + smp_message_recv(PPC_MSG_DEBUGGER_BREAK); + } +#endif + } + return IRQ_HANDLED; +} + +static irqreturn_t xics_ipi_action_direct(int irq, void *dev_id) +{ + int cpu = smp_processor_id(); + + direct_qirr_info(cpu, 0xff); + + return xics_ipi_dispatch(cpu); +} + +static irqreturn_t xics_ipi_action_lpar(int irq, void *dev_id) +{ + int cpu = smp_processor_id(); + + lpar_qirr_info(cpu, 0xff); + + return xics_ipi_dispatch(cpu); +} + +static void xics_request_ipi(void) +{ + unsigned int ipi; + int rc; + + ipi = irq_create_mapping(xics_host, XICS_IPI); + BUG_ON(ipi == NO_IRQ); + + /* + * IPIs are marked IRQF_DISABLED as they must run with irqs + * disabled + */ + set_irq_handler(ipi, handle_percpu_irq); + if (firmware_has_feature(FW_FEATURE_LPAR)) + rc = request_irq(ipi, xics_ipi_action_lpar, + IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL); + else + rc = request_irq(ipi, xics_ipi_action_direct, + IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL); + BUG_ON(rc); +} + +int __init smp_xics_probe(void) +{ + xics_request_ipi(); + + return cpus_weight(cpu_possible_map); +} + +#endif /* CONFIG_SMP */ + + +/* Initialization */ + +static void xics_update_irq_servers(void) +{ + int i, j; + struct device_node *np; + u32 ilen; + const u32 *ireg; + u32 hcpuid; + + /* Find the server numbers for the boot cpu. */ + np = of_get_cpu_node(boot_cpuid, NULL); + BUG_ON(!np); + + ireg = of_get_property(np, "ibm,ppc-interrupt-gserver#s", &ilen); + if (!ireg) { + of_node_put(np); + return; + } + + i = ilen / sizeof(int); + hcpuid = get_hard_smp_processor_id(boot_cpuid); + + /* Global interrupt distribution server is specified in the last + * entry of "ibm,ppc-interrupt-gserver#s" property. Get the last + * entry fom this property for current boot cpu id and use it as + * default distribution server + */ + for (j = 0; j < i; j += 2) { + if (ireg[j] == hcpuid) { + default_server = hcpuid; + default_distrib_server = ireg[j+1]; + } + } + + of_node_put(np); +} + static void __init xics_map_one_cpu(int hw_id, unsigned long addr, unsigned long size) { -#ifdef CONFIG_SMP int i; /* This may look gross but it's good enough for now, we don't quite @@ -586,11 +626,6 @@ static void __init xics_map_one_cpu(int hw_id, unsigned long addr, return; } } -#else - if (hw_id != 0) - return; - xics_per_cpu[0] = ioremap(addr, size); -#endif /* CONFIG_SMP */ } static void __init xics_init_one_node(struct device_node *np, @@ -642,6 +677,7 @@ void __init xics_init_IRQ(void) struct device_node *np; u32 indx = 0; int found = 0; + const u32 *isize; ppc64_boot_msg(0x20, "XICS Init"); @@ -652,15 +688,37 @@ void __init xics_init_IRQ(void) for_each_node_by_type(np, "PowerPC-External-Interrupt-Presentation") { found = 1; - if (firmware_has_feature(FW_FEATURE_LPAR)) + if (firmware_has_feature(FW_FEATURE_LPAR)) { + of_node_put(np); break; + } xics_init_one_node(np, &indx); } if (found == 0) return; - xics_init_host(); + /* get the bit size of server numbers */ + found = 0; + + for_each_compatible_node(np, NULL, "ibm,ppc-xics") { + isize = of_get_property(np, "ibm,interrupt-server#-size", NULL); + + if (!isize) + continue; + + if (!found) { + interrupt_server_size = *isize; + found = 1; + } else if (*isize != interrupt_server_size) { + printk(KERN_WARNING "XICS: " + "mismatched ibm,interrupt-server#-size\n"); + interrupt_server_size = max(*isize, + interrupt_server_size); + } + } + xics_update_irq_servers(); + xics_init_host(); if (firmware_has_feature(FW_FEATURE_LPAR)) ppc_md.get_irq = xics_get_irq_lpar; @@ -672,30 +730,40 @@ void __init xics_init_IRQ(void) ppc64_boot_msg(0x21, "XICS Done"); } +/* Cpu startup, shutdown, and hotplug */ -#ifdef CONFIG_SMP -void xics_request_IPIs(void) +static void xics_set_cpu_priority(unsigned char cppr) { - unsigned int ipi; - int rc; - - ipi = irq_create_mapping(xics_host, XICS_IPI); - BUG_ON(ipi == NO_IRQ); - - /* - * IPIs are marked IRQF_DISABLED as they must run with irqs - * disabled - */ - set_irq_handler(ipi, handle_percpu_irq); if (firmware_has_feature(FW_FEATURE_LPAR)) - rc = request_irq(ipi, xics_ipi_action_lpar, IRQF_DISABLED, - "IPI", NULL); + lpar_cppr_info(cppr); else - rc = request_irq(ipi, xics_ipi_action_direct, IRQF_DISABLED, - "IPI", NULL); - BUG_ON(rc); + direct_cppr_info(cppr); + iosync(); +} + +/* Have the calling processor join or leave the specified global queue */ +static void xics_set_cpu_giq(unsigned int gserver, unsigned int join) +{ + int index; + int status; + + if (!rtas_indicator_present(GLOBAL_INTERRUPT_QUEUE, NULL)) + return; + + index = (1UL << interrupt_server_size) - 1 - gserver; + + status = rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, index, join); + + WARN(status < 0, "set-indicator(%d, %d, %u) returned %d\n", + GLOBAL_INTERRUPT_QUEUE, index, join, status); +} + +void xics_setup_cpu(void) +{ + xics_set_cpu_priority(0xff); + + xics_set_cpu_giq(default_distrib_server, 1); } -#endif /* CONFIG_SMP */ void xics_teardown_cpu(void) { @@ -703,9 +771,7 @@ void xics_teardown_cpu(void) xics_set_cpu_priority(0); - /* - * Clear IPI - */ + /* Clear any pending IPI request */ if (firmware_has_feature(FW_FEATURE_LPAR)) lpar_qirr_info(cpu, 0xff); else @@ -714,34 +780,28 @@ void xics_teardown_cpu(void) void xics_kexec_teardown_cpu(int secondary) { - unsigned int ipi; - struct irq_desc *desc; - xics_teardown_cpu(); /* - * we need to EOI the IPI + * we take the ipi irq but and never return so we + * need to EOI the IPI, but want to leave our priority 0 * - * probably need to check all the other interrupts too + * should we check all the other interrupts too? * should we be flagging idle loop instead? * or creating some task to be scheduled? */ - ipi = irq_find_mapping(xics_host, XICS_IPI); - if (ipi == XICS_IRQ_SPURIOUS) - return; - desc = get_irq_desc(ipi); - if (desc->chip && desc->chip->eoi) - desc->chip->eoi(ipi); + if (firmware_has_feature(FW_FEATURE_LPAR)) + lpar_xirr_info_set((0x00 << 24) | XICS_IPI); + else + direct_xirr_info_set((0x00 << 24) | XICS_IPI); /* * Some machines need to have at least one cpu in the GIQ, * so leave the master cpu in the group. */ if (secondary) - rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, - (1UL << interrupt_server_size) - 1 - - default_distrib_server, 0); + xics_set_cpu_giq(default_distrib_server, 0); } #ifdef CONFIG_HOTPLUG_CPU @@ -749,17 +809,18 @@ void xics_kexec_teardown_cpu(int secondary) /* Interrupts are disabled. */ void xics_migrate_irqs_away(void) { - int status; int cpu = smp_processor_id(), hw_cpu = hard_smp_processor_id(); unsigned int irq, virq; + /* If we used to be the default server, move to the new "boot_cpuid" */ + if (hw_cpu == default_server) + xics_update_irq_servers(); + /* Reject any interrupt that was queued to us... */ xics_set_cpu_priority(0); - /* remove ourselves from the global interrupt queue */ - status = rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, - (1UL << interrupt_server_size) - 1 - default_distrib_server, 0); - WARN_ON(status < 0); + /* Remove ourselves from the global interrupt queue */ + xics_set_cpu_giq(default_distrib_server, 0); /* Allow IPIs again... */ xics_set_cpu_priority(DEFAULT_PRIORITY); @@ -767,6 +828,7 @@ void xics_migrate_irqs_away(void) for_each_irq(virq) { struct irq_desc *desc; int xics_status[2]; + int status; unsigned long flags; /* We cant set affinity on ISA interrupts */ @@ -790,9 +852,8 @@ void xics_migrate_irqs_away(void) status = rtas_call(ibm_get_xive, 1, 3, xics_status, irq); if (status) { - printk(KERN_ERR "migrate_irqs_away: irq=%u " - "ibm,get-xive returns %d\n", - virq, status); + printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n", + __func__, irq, status); goto unlock; } diff --git a/arch/powerpc/platforms/pseries/xics.h b/arch/powerpc/platforms/pseries/xics.h index 1c5321ae8f2..d1d5a83039a 100644 --- a/arch/powerpc/platforms/pseries/xics.h +++ b/arch/powerpc/platforms/pseries/xics.h @@ -12,20 +12,12 @@ #ifndef _POWERPC_KERNEL_XICS_H #define _POWERPC_KERNEL_XICS_H -#include <linux/cache.h> - extern void xics_init_IRQ(void); extern void xics_setup_cpu(void); extern void xics_teardown_cpu(void); extern void xics_kexec_teardown_cpu(int secondary); -extern void xics_cause_IPI(int cpu); -extern void xics_request_IPIs(void); extern void xics_migrate_irqs_away(void); - -struct xics_ipi_struct { - volatile unsigned long value; -} ____cacheline_aligned; - -extern struct xics_ipi_struct xics_ipi_message[NR_CPUS] __cacheline_aligned; +extern int smp_xics_probe(void); +extern void smp_xics_message_pass(int target, int msg); #endif /* _POWERPC_KERNEL_XICS_H */ |