diff options
Diffstat (limited to 'arch')
38 files changed, 677 insertions, 510 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 56c3c4065eb..8699dadcd09 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -107,6 +107,11 @@ config AUDIT_ARCH bool default y +config GENERIC_BUG + bool + default y + depends on BUG + config DEFAULT_UIMAGE bool help @@ -478,6 +483,7 @@ config PPC_MAPLE select PPC_UDBG_16550 select PPC_970_NAP select PPC_NATIVE + select PPC_RTAS default n help This option enables support for the Maple 970FX Evaluation Board. @@ -714,7 +720,7 @@ config FORCE_MAX_ZONEORDER config MATH_EMULATION bool "Math emulation" - depends on 4xx || 8xx || E200 || E500 + depends on 4xx || 8xx || E200 || PPC_83xx || E500 ---help--- Some PowerPC chips designed for embedded applications do not have a floating-point unit and therefore do not implement the diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index f2d888e014a..70ed61337f5 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -157,6 +157,7 @@ CONFIG_SPU_BASE=y CONFIG_PS3_HTAB_SIZE=20 CONFIG_PS3_DYNAMIC_DMA=y CONFIG_PS3_USE_LPAR_ADDR=y +CONFIG_PS3_VUART=y # # Kernel options diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 4fe53d08ab8..d2ded19e406 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -77,6 +77,7 @@ endif ifeq ($(CONFIG_PPC_ISERIES),y) extra-y += lparmap.s +$(obj)/head_64.o: $(obj)/lparmap.s AFLAGS_head_64.o += -I$(obj) endif diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 9d1614c3ce6..b742013bb9d 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -833,7 +833,7 @@ static struct cpu_spec cpu_specs[] = { .pvr_mask = 0x7fff0000, .pvr_value = 0x00840000, .cpu_name = "e300c2", - .cpu_features = CPU_FTRS_E300, + .cpu_features = CPU_FTRS_E300C2, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, .icache_bsize = 32, .dcache_bsize = 32, @@ -1136,8 +1136,7 @@ static struct cpu_spec cpu_specs[] = { .pvr_mask = 0xff000fff, .pvr_value = 0x53000890, .cpu_name = "440SPe Rev. A", - .cpu_features = CPU_FTR_SPLIT_ID_CACHE | - CPU_FTR_USE_TB, + .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, .dcache_bsize = 32, diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index d88e182e40b..9417cf5b4b7 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -437,6 +437,13 @@ Alignment: /* Floating-point unavailable */ . = 0x800 FPUnavailable: +BEGIN_FTR_SECTION +/* + * Certain Freescale cores don't have a FPU and treat fp instructions + * as a FP Unavailable exception. Redirect to illegal/emulation handling. + */ + b ProgramCheck +END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE) EXCEPTION_PROLOG bne load_up_fpu /* if from user, just load it up */ addi r3,r1,STACK_FRAME_OVERHEAD diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index e2c3c6a85f3..8339fd609de 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -23,6 +23,7 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/cache.h> +#include <linux/bug.h> #include "setup.h" @@ -290,23 +291,11 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { const Elf_Shdr *sect; + int err; - me->arch.bug_table = NULL; - me->arch.num_bugs = 0; - - /* Find the __bug_table section, if present */ - sect = find_section(hdr, sechdrs, "__bug_table"); - if (sect != NULL) { - me->arch.bug_table = (void *) sect->sh_addr; - me->arch.num_bugs = sect->sh_size / sizeof(struct bug_entry); - } - - /* - * Strictly speaking this should have a spinlock to protect against - * traversals, but since we only traverse on BUG()s, a spinlock - * could potentially lead to deadlock and thus be counter-productive. - */ - list_add(&me->arch.bug_list, &module_bug_list); + err = module_bug_finalize(hdr, sechdrs, me); + if (err) /* never true, currently */ + return err; /* Apply feature fixups */ sect = find_section(hdr, sechdrs, "__ftr_fixup"); @@ -320,7 +309,7 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { - list_del(&mod->arch.bug_list); + module_bug_cleanup(mod); } struct bug_entry *module_find_bug(unsigned long bugaddr) diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 8dd1f0aae5d..75c7c4f1928 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -20,6 +20,7 @@ #include <linux/moduleloader.h> #include <linux/err.h> #include <linux/vmalloc.h> +#include <linux/bug.h> #include <asm/module.h> #include <asm/uaccess.h> #include <asm/firmware.h> @@ -439,23 +440,11 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { const Elf_Shdr *sect; + int err; - me->arch.bug_table = NULL; - me->arch.num_bugs = 0; - - /* Find the __bug_table section, if present */ - sect = find_section(hdr, sechdrs, "__bug_table"); - if (sect != NULL) { - me->arch.bug_table = (void *) sect->sh_addr; - me->arch.num_bugs = sect->sh_size / sizeof(struct bug_entry); - } - - /* - * Strictly speaking this should have a spinlock to protect against - * traversals, but since we only traverse on BUG()s, a spinlock - * could potentially lead to deadlock and thus be counter-productive. - */ - list_add(&me->arch.bug_list, &module_bug_list); + err = module_bug_finalize(hdr, sechdrs, me); + if (err) + return err; /* Apply feature fixups */ sect = find_section(hdr, sechdrs, "__ftr_fixup"); @@ -475,7 +464,7 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { - list_del(&mod->arch.bug_list); + module_bug_cleanup(mod); } struct bug_entry *module_find_bug(unsigned long bugaddr) diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c index 8a06724e029..e921514e655 100644 --- a/arch/powerpc/kernel/of_device.c +++ b/arch/powerpc/kernel/of_device.c @@ -109,9 +109,7 @@ int of_device_register(struct of_device *ofdev) if (rc) return rc; - device_create_file(&ofdev->dev, &dev_attr_devspec); - - return 0; + return device_create_file(&ofdev->dev, &dev_attr_devspec); } void of_device_unregister(struct of_device *ofdev) diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index b3189d0161b..3002ea3a61a 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -169,7 +169,7 @@ static void of_platform_make_bus_id(struct of_device *dev) char *name = dev->dev.bus_id; const u32 *reg; u64 addr; - long magic; + int magic; /* * If it's a DCR based device, use 'd' for native DCRs diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 2f54cd81dea..8336deafc62 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -736,25 +736,51 @@ scan_OF_pci_childs(struct device_node* node, pci_OF_scan_iterator filter, void* return NULL; } -static int -scan_OF_pci_childs_iterator(struct device_node* node, void* data) +static struct device_node *scan_OF_for_pci_dev(struct device_node *parent, + unsigned int devfn) { - const unsigned int *reg; - u8* fdata = (u8*)data; - - reg = get_property(node, "reg", NULL); - if (reg && ((reg[0] >> 8) & 0xff) == fdata[1] - && ((reg[0] >> 16) & 0xff) == fdata[0]) - return 1; - return 0; + struct device_node *np = NULL; + const u32 *reg; + unsigned int psize; + + while ((np = of_get_next_child(parent, np)) != NULL) { + reg = get_property(np, "reg", &psize); + if (reg == NULL || psize < 4) + continue; + if (((reg[0] >> 8) & 0xff) == devfn) + return np; + } + return NULL; } -static struct device_node* -scan_OF_childs_for_device(struct device_node* node, u8 bus, u8 dev_fn) + +static struct device_node *scan_OF_for_pci_bus(struct pci_bus *bus) { - u8 filter_data[2] = {bus, dev_fn}; + struct device_node *parent, *np; + + /* Are we a root bus ? */ + if (bus->self == NULL || bus->parent == NULL) { + struct pci_controller *hose = pci_bus_to_hose(bus->number); + if (hose == NULL) + return NULL; + return of_node_get(hose->arch_data); + } + + /* not a root bus, we need to get our parent */ + parent = scan_OF_for_pci_bus(bus->parent); + if (parent == NULL) + return NULL; + + /* now iterate for children for a match */ + np = scan_OF_for_pci_dev(parent, bus->self->devfn); + of_node_put(parent); - return scan_OF_pci_childs(node, scan_OF_pci_childs_iterator, filter_data); + /* sanity check */ + if (strcmp(np->type, "pci") != 0) + printk(KERN_WARNING "pci: wrong type \"%s\" for bridge %s\n", + np->type, np->full_name); + + return np; } /* @@ -763,43 +789,25 @@ scan_OF_childs_for_device(struct device_node* node, u8 bus, u8 dev_fn) struct device_node * pci_busdev_to_OF_node(struct pci_bus *bus, int devfn) { - struct pci_controller *hose; - struct device_node *node; - int busnr; + struct device_node *parent, *np; if (!have_of) return NULL; - - /* Lookup the hose */ - busnr = bus->number; - hose = pci_bus_to_hose(busnr); - if (!hose) - return NULL; - /* Check it has an OF node associated */ - node = (struct device_node *) hose->arch_data; - if (!node) + DBG("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn); + parent = scan_OF_for_pci_bus(bus); + if (parent == NULL) return NULL; - - /* Fixup bus number according to what OF think it is. */ -#ifdef CONFIG_PPC_PMAC - /* The G5 need a special case here. Basically, we don't remap all - * busses on it so we don't create the pci-OF-map. However, we do - * remap the AGP bus and so have to deal with it. A future better - * fix has to be done by making the remapping per-host and always - * filling the pci_to_OF map. --BenH + DBG(" parent is %s\n", parent ? parent->full_name : "<NULL>"); + np = scan_OF_for_pci_dev(parent, devfn); + of_node_put(parent); + DBG(" result is %s\n", np ? np->full_name : "<NULL>"); + + /* XXX most callers don't release the returned node + * mostly because ppc64 doesn't increase the refcount, + * we need to fix that. */ - if (machine_is(powermac) && busnr >= 0xf0) - busnr -= 0xf0; - else -#endif - if (pci_to_OF_bus_map) - busnr = pci_to_OF_bus_map[busnr]; - if (busnr == 0xff) - return NULL; - - /* Now, lookup childs of the hose */ - return scan_OF_childs_for_device(node->child, busnr, devfn); + return np; } EXPORT_SYMBOL(pci_busdev_to_OF_node); @@ -1544,7 +1552,7 @@ pci_resource_to_bus(struct pci_dev *pdev, struct resource *res) static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, - unsigned long *offset, + resource_size_t *offset, enum pci_mmap_state mmap_state) { struct pci_controller *hose = pci_bus_to_hose(dev->bus->number); @@ -1556,7 +1564,9 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, /* If memory, add on the PCI bridge address offset */ if (mmap_state == pci_mmap_mem) { +#if 0 /* See comment in pci_resource_to_user() for why this is disabled */ *offset += hose->pci_mem_offset; +#endif res_bit = IORESOURCE_MEM; } else { io_offset = hose->io_base_virt - (void __iomem *)_IO_BASE; @@ -1624,9 +1634,6 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, else prot |= _PAGE_GUARDED; - printk("PCI map for %s:%llx, prot: %lx\n", pci_name(dev), - (unsigned long long)rp->start, prot); - return __pgprot(prot); } @@ -1695,7 +1702,7 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine) { - unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT; struct resource *rp; int ret; @@ -1808,22 +1815,42 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, resource_size_t *start, resource_size_t *end) { struct pci_controller *hose = pci_bus_to_hose(dev->bus->number); - unsigned long offset = 0; + resource_size_t offset = 0; if (hose == NULL) return; if (rsrc->flags & IORESOURCE_IO) - offset = (void __iomem *)_IO_BASE - hose->io_base_virt - + hose->io_base_phys; + offset = (unsigned long)hose->io_base_virt - _IO_BASE; + + /* We pass a fully fixed up address to userland for MMIO instead of + * a BAR value because X is lame and expects to be able to use that + * to pass to /dev/mem ! + * + * That means that we'll have potentially 64 bits values where some + * userland apps only expect 32 (like X itself since it thinks only + * Sparc has 64 bits MMIO) but if we don't do that, we break it on + * 32 bits CHRPs :-( + * + * Hopefully, the sysfs insterface is immune to that gunk. Once X + * has been fixed (and the fix spread enough), we can re-enable the + * 2 lines below and pass down a BAR value to userland. In that case + * we'll also have to re-enable the matching code in + * __pci_mmap_make_offset(). + * + * BenH. + */ +#if 0 + else if (rsrc->flags & IORESOURCE_MEM) + offset = hose->pci_mem_offset; +#endif - *start = rsrc->start + offset; - *end = rsrc->end + offset; + *start = rsrc->start - offset; + *end = rsrc->end - offset; } -void __init -pci_init_resource(struct resource *res, unsigned long start, unsigned long end, - int flags, char *name) +void __init pci_init_resource(struct resource *res, resource_size_t start, + resource_size_t end, int flags, char *name) { res->start = start; res->end = end; diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 6fa9a0a5c8d..a6b7692c726 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -682,7 +682,7 @@ int pci_proc_domain(struct pci_bus *bus) * Returns negative error code on failure, zero on success. */ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, - unsigned long *offset, + resource_size_t *offset, enum pci_mmap_state mmap_state) { struct pci_controller *hose = pci_bus_to_host(dev->bus); @@ -694,7 +694,9 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, /* If memory, add on the PCI bridge address offset */ if (mmap_state == pci_mmap_mem) { +#if 0 /* See comment in pci_resource_to_user() for why this is disabled */ *offset += hose->pci_mem_offset; +#endif res_bit = IORESOURCE_MEM; } else { io_offset = (unsigned long)hose->io_base_virt - pci_io_base; @@ -762,9 +764,6 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, else prot |= _PAGE_GUARDED; - printk(KERN_DEBUG "PCI map for %s:%lx, prot: %lx\n", pci_name(dev), rp->start, - prot); - return __pgprot(prot); } @@ -832,7 +831,7 @@ pgprot_t pci_phys_mem_access_prot(struct file *file, int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine) { - unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT; struct resource *rp; int ret; @@ -1333,20 +1332,41 @@ EXPORT_SYMBOL(pci_read_irq_line); void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, - u64 *start, u64 *end) + resource_size_t *start, resource_size_t *end) { struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long offset = 0; + resource_size_t offset = 0; if (hose == NULL) return; if (rsrc->flags & IORESOURCE_IO) - offset = pci_io_base - (unsigned long)hose->io_base_virt + - hose->io_base_phys; + offset = (unsigned long)hose->io_base_virt - pci_io_base; + + /* We pass a fully fixed up address to userland for MMIO instead of + * a BAR value because X is lame and expects to be able to use that + * to pass to /dev/mem ! + * + * That means that we'll have potentially 64 bits values where some + * userland apps only expect 32 (like X itself since it thinks only + * Sparc has 64 bits MMIO) but if we don't do that, we break it on + * 32 bits CHRPs :-( + * + * Hopefully, the sysfs insterface is immune to that gunk. Once X + * has been fixed (and the fix spread enough), we can re-enable the + * 2 lines below and pass down a BAR value to userland. In that case + * we'll also have to re-enable the matching code in + * __pci_mmap_make_offset(). + * + * BenH. + */ +#if 0 + else if (rsrc->flags & IORESOURCE_MEM) + offset = hose->pci_mem_offset; +#endif - *start = rsrc->start + offset; - *end = rsrc->end + offset; + *start = rsrc->start - offset; + *end = rsrc->end - offset; } struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node) diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 9179f0739ea..95776b6af4e 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -208,7 +208,7 @@ EXPORT_SYMBOL(mmu_hash_lock); /* For MOL */ extern long *intercept_table; EXPORT_SYMBOL(intercept_table); #endif /* CONFIG_PPC_STD_MMU_32 */ -#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) +#ifdef CONFIG_PPC_DCR_NATIVE EXPORT_SYMBOL(__mtdcr); EXPORT_SYMBOL(__mfdcr); #endif diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index c18dbe77fdc..1fc732a552d 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -804,6 +804,56 @@ static unsigned long __init dt_mem_next_cell(int s, cell_t **cellp) return of_read_ulong(p, s); } +#ifdef CONFIG_PPC_PSERIES +/* + * Interpret the ibm,dynamic-memory property in the + * /ibm,dynamic-reconfiguration-memory node. + * This contains a list of memory blocks along with NUMA affinity + * information. + */ +static int __init early_init_dt_scan_drconf_memory(unsigned long node) +{ + cell_t *dm, *ls; + unsigned long l, n; + unsigned long base, size, lmb_size, flags; + + ls = (cell_t *)of_get_flat_dt_prop(node, "ibm,lmb-size", &l); + if (ls == NULL || l < dt_root_size_cells * sizeof(cell_t)) + return 0; + lmb_size = dt_mem_next_cell(dt_root_size_cells, &ls); + + dm = (cell_t *)of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l); + if (dm == NULL || l < sizeof(cell_t)) + return 0; + + n = *dm++; /* number of entries */ + if (l < (n * (dt_root_addr_cells + 4) + 1) * sizeof(cell_t)) + return 0; + + for (; n != 0; --n) { + base = dt_mem_next_cell(dt_root_addr_cells, &dm); + flags = dm[3]; + /* skip DRC index, pad, assoc. list index, flags */ + dm += 4; + /* skip this block if the reserved bit is set in flags (0x80) + or if the block is not assigned to this partition (0x8) */ + if ((flags & 0x80) || !(flags & 0x8)) + continue; + size = lmb_size; + if (iommu_is_off) { + if (base >= 0x80000000ul) + continue; + if ((base + size) > 0x80000000ul) + size = 0x80000000ul - base; + } + lmb_add(base, size); + } + lmb_dump_all(); + return 0; +} +#else +#define early_init_dt_scan_drconf_memory(node) 0 +#endif /* CONFIG_PPC_PSERIES */ static int __init early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data) @@ -812,6 +862,11 @@ static int __init early_init_dt_scan_memory(unsigned long node, cell_t *reg, *endp; unsigned long l; + /* Look for the ibm,dynamic-reconfiguration-memory node */ + if (depth == 1 && + strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) + return early_init_dt_scan_drconf_memory(node); + /* We are scanning "memory" nodes only */ if (type == NULL) { /* diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 46cf32670dd..520ef42f642 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -679,7 +679,7 @@ static unsigned char ibm_architecture_vec[] = { /* option vector 5: PAPR/OF options */ 3 - 2, /* length */ 0, /* don't ignore, don't halt */ - OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES, + OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY, }; /* Old method - ELF header with PT_NOTE sections */ diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 387ed0d9ad6..76b5d7ebdcc 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -303,6 +303,12 @@ int rtas_token(const char *service) } EXPORT_SYMBOL(rtas_token); +int rtas_service_present(const char *service) +{ + return rtas_token(service) != RTAS_UNKNOWN_SERVICE; +} +EXPORT_SYMBOL(rtas_service_present); + #ifdef CONFIG_RTAS_ERROR_LOGGING /* * Return the firmware-specified size of the error log buffer @@ -810,32 +816,6 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) return 0; } -#ifdef CONFIG_HOTPLUG_CPU -/* This version can't take the spinlock, because it never returns */ -static struct rtas_args rtas_stop_self_args = { - /* The token is initialized for real in setup_system() */ - .token = RTAS_UNKNOWN_SERVICE, - .nargs = 0, - .nret = 1, - .rets = &rtas_stop_self_args.args[0], -}; - -void rtas_stop_self(void) -{ - struct rtas_args *rtas_args = &rtas_stop_self_args; - - local_irq_disable(); - - BUG_ON(rtas_args->token == RTAS_UNKNOWN_SERVICE); - - printk("cpu %u (hwid %u) Ready to die...\n", - smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(rtas_args)); - - panic("Alas, I survived.\n"); -} -#endif - /* * Call early during boot, before mem init or bootmem, to retrieve the RTAS * informations from the device-tree and allocate the RMO buffer for userland @@ -880,9 +860,6 @@ void __init rtas_initialize(void) #endif rtas_rmo_buf = lmb_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region); -#ifdef CONFIG_HOTPLUG_CPU - rtas_stop_self_args.token = rtas_token("stop-self"); -#endif /* CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); #endif diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 63ed265b7f0..400ab2b946e 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -181,6 +181,8 @@ SYSFS_PMCSETUP(pmc6, SPRN_PMC6); SYSFS_PMCSETUP(pmc7, SPRN_PMC7); SYSFS_PMCSETUP(pmc8, SPRN_PMC8); SYSFS_PMCSETUP(purr, SPRN_PURR); +SYSFS_PMCSETUP(spurr, SPRN_SPURR); +SYSFS_PMCSETUP(dscr, SPRN_DSCR); static SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0); static SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1); @@ -194,6 +196,8 @@ static SYSDEV_ATTR(pmc6, 0600, show_pmc6, store_pmc6); static SYSDEV_ATTR(pmc7, 0600, show_pmc7, store_pmc7); static SYSDEV_ATTR(pmc8, 0600, show_pmc8, store_pmc8); static SYSDEV_ATTR(purr, 0600, show_purr, NULL); +static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL); +static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr); static void register_cpu_online(unsigned int cpu) { @@ -231,6 +235,12 @@ static void register_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PURR)) sysdev_create_file(s, &attr_purr); + + if (cpu_has_feature(CPU_FTR_SPURR)) + sysdev_create_file(s, &attr_spurr); + + if (cpu_has_feature(CPU_FTR_DSCR)) + sysdev_create_file(s, &attr_dscr); } #ifdef CONFIG_HOTPLUG_CPU @@ -272,6 +282,12 @@ static void unregister_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PURR)) sysdev_remove_file(s, &attr_purr); + + if (cpu_has_feature(CPU_FTR_SPURR)) + sysdev_remove_file(s, &attr_spurr); + + if (cpu_has_feature(CPU_FTR_DSCR)) + sysdev_remove_file(s, &attr_dscr); } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 0d4e203fa7a..535f5066564 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -32,6 +32,7 @@ #include <linux/kprobes.h> #include <linux/kexec.h> #include <linux/backlight.h> +#include <linux/bug.h> #include <asm/kdebug.h> #include <asm/pgtable.h> @@ -727,54 +728,9 @@ static int emulate_instruction(struct pt_regs *regs) return -EINVAL; } -/* - * Look through the list of trap instructions that are used for BUG(), - * BUG_ON() and WARN_ON() and see if we hit one. At this point we know - * that the exception was caused by a trap instruction of some kind. - * Returns 1 if we should continue (i.e. it was a WARN_ON) or 0 - * otherwise. - */ -extern struct bug_entry __start___bug_table[], __stop___bug_table[]; - -#ifndef CONFIG_MODULES -#define module_find_bug(x) NULL -#endif - -struct bug_entry *find_bug(unsigned long bugaddr) +int is_valid_bugaddr(unsigned long addr) { - struct bug_entry *bug; - - for (bug = __start___bug_table; bug < __stop___bug_table; ++bug) - if (bugaddr == bug->bug_addr) - return bug; - return module_find_bug(bugaddr); -} - -static int check_bug_trap(struct pt_regs *regs) -{ - struct bug_entry *bug; - unsigned long addr; - - if (regs->msr & MSR_PR) - return 0; /* not in kernel */ - addr = regs->nip; /* address of trap instruction */ - if (addr < PAGE_OFFSET) - return 0; - bug = find_bug(regs->nip); - if (bug == NULL) - return 0; - if (bug->line & BUG_WARNING_TRAP) { - /* this is a WARN_ON rather than BUG/BUG_ON */ - printk(KERN_ERR "Badness in %s at %s:%ld\n", - bug->function, bug->file, - bug->line & ~BUG_WARNING_TRAP); - dump_stack(); - return 1; - } - printk(KERN_CRIT "kernel BUG in %s at %s:%ld!\n", - bug->function, bug->file, bug->line); - - return 0; + return is_kernel_addr(addr); } void __kprobes program_check_exception(struct pt_regs *regs) @@ -782,6 +738,8 @@ void __kprobes program_check_exception(struct pt_regs *regs) unsigned int reason = get_reason(regs); extern int do_mathemu(struct pt_regs *regs); + /* We can now get here via a FP Unavailable exception if the core + * has no FPU, in that case no reason flags will be set */ #ifdef CONFIG_MATH_EMULATION /* (reason & REASON_ILLEGAL) would be the obvious thing here, * but there seems to be a hardware bug on the 405GP (RevD) @@ -808,7 +766,9 @@ void __kprobes program_check_exception(struct pt_regs *regs) return; if (debugger_bpt(regs)) return; - if (check_bug_trap(regs)) { + + if (!(regs->msr & MSR_PR) && /* not user-mode */ + report_bug(regs->nip) == BUG_TRAP_TYPE_WARN) { regs->nip += 4; return; } diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 04b98671a06..04b8e71bf5b 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -62,11 +62,7 @@ SECTIONS __stop___ex_table = .; } - __bug_table : { - __start___bug_table = .; - *(__bug_table) - __stop___bug_table = .; - } + BUG_TABLE /* * Init sections discarded at runtime diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 9da01dc8cfd..262790910ff 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -295,6 +295,63 @@ static unsigned long __init numa_enforce_memory_limit(unsigned long start, return lmb_end_of_DRAM() - start; } +/* + * Extract NUMA information from the ibm,dynamic-reconfiguration-memory + * node. This assumes n_mem_{addr,size}_cells have been set. + */ +static void __init parse_drconf_memory(struct device_node *memory) +{ + const unsigned int *lm, *dm, *aa; + unsigned int ls, ld, la; + unsigned int n, aam, aalen; + unsigned long lmb_size, size; + int nid, default_nid = 0; + unsigned int start, ai, flags; + + lm = get_property(memory, "ibm,lmb-size", &ls); + dm = get_property(memory, "ibm,dynamic-memory", &ld); + aa = get_property(memory, "ibm,associativity-lookup-arrays", &la); + if (!lm || !dm || !aa || + ls < sizeof(unsigned int) || ld < sizeof(unsigned int) || + la < 2 * sizeof(unsigned int)) + return; + + lmb_size = read_n_cells(n_mem_size_cells, &lm); + n = *dm++; /* number of LMBs */ + aam = *aa++; /* number of associativity lists */ + aalen = *aa++; /* length of each associativity list */ + if (ld < (n * (n_mem_addr_cells + 4) + 1) * sizeof(unsigned int) || + la < (aam * aalen + 2) * sizeof(unsigned int)) + return; + + for (; n != 0; --n) { + start = read_n_cells(n_mem_addr_cells, &dm); + ai = dm[2]; + flags = dm[3]; + dm += 4; + /* 0x80 == reserved, 0x8 = assigned to us */ + if ((flags & 0x80) || !(flags & 0x8)) + continue; + nid = default_nid; + /* flags & 0x40 means associativity index is invalid */ + if (min_common_depth > 0 && min_common_depth <= aalen && + (flags & 0x40) == 0 && ai < aam) { + /* this is like of_node_to_nid_single */ + nid = aa[ai * aalen + min_common_depth - 1]; + if (nid == 0xffff || nid >= MAX_NUMNODES) + nid = default_nid; + } + node_set_online(nid); + + size = numa_enforce_memory_limit(start, lmb_size); + if (!size) + continue; + + add_active_range(nid, start >> PAGE_SHIFT, + (start >> PAGE_SHIFT) + (size >> PAGE_SHIFT)); + } +} + static int __init parse_numa_properties(void) { struct device_node *cpu = NULL; @@ -385,6 +442,14 @@ new_range: goto new_range; } + /* + * Now do the same thing for each LMB listed in the ibm,dynamic-memory + * property in the ibm,dynamic-reconfiguration-memory node. + */ + memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); + if (memory) + parse_drconf_memory(memory); + return 0; } diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c index a375c15b431..eaff71e74fb 100644 --- a/arch/powerpc/platforms/52xx/lite5200.c +++ b/arch/powerpc/platforms/52xx/lite5200.c @@ -40,8 +40,6 @@ #include <asm/prom.h> #include <asm/udbg.h> #include <sysdev/fsl_soc.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> #include <asm/of_platform.h> #include <asm/mpc52xx.h> diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c index 616a0a3fd0e..70e0d968d30 100644 --- a/arch/powerpc/platforms/cell/cbe_thermal.c +++ b/arch/powerpc/platforms/cell/cbe_thermal.c @@ -115,6 +115,7 @@ static struct sysdev_attribute attr_spu_temperature = { static struct attribute *spu_attributes[] = { &attr_spu_temperature.attr, + NULL, }; static struct attribute_group spu_attribute_group = { @@ -135,6 +136,7 @@ static struct sysdev_attribute attr_ppe_temperature1 = { static struct attribute *ppe_attributes[] = { &attr_ppe_temperature0.attr, &attr_ppe_temperature1.attr, + NULL, }; static struct attribute_group ppe_attribute_group = { diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c index 99c612025e8..d04ae1671e6 100644 --- a/arch/powerpc/platforms/cell/pmu.c +++ b/arch/powerpc/platforms/cell/pmu.c @@ -382,11 +382,14 @@ static irqreturn_t cbe_pm_irq(int irq, void *dev_id) return IRQ_HANDLED; } -int __init cbe_init_pm_irq(void) +static int __init cbe_init_pm_irq(void) { unsigned int irq; int rc, node; + if (!machine_is(cell)) + return 0; + for_each_node(node) { irq = irq_create_mapping(NULL, IIC_IRQ_IOEX_PMI | (node << IIC_IRQ_NODE_SHIFT)); diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index 26945c491f6..725e1956115 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -147,7 +147,7 @@ static int spufs_arch_notes_size(void) struct fdtable *fdt = files_fdtable(current->files); int size = 0, fd; - for (fd = 0; fd < fdt->max_fdset && fd < fdt->max_fds; fd++) { + for (fd = 0; fd < fdt->max_fds; fd++) { if (FD_ISSET(fd, fdt->open_fds)) { struct file *file = fcheck(fd); diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index 3a32deda765..3f6a69f6719 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -562,7 +562,7 @@ void __init maple_pci_init(void) for (np = NULL; (np = of_get_next_child(root, np)) != NULL;) { if (np->name == NULL) continue; - if (strcmp(np->name, "pci") == 0) { + if (!strcmp(np->name, "pci") || !strcmp(np->name, "pcie")) { if (add_bridge(np) == 0) of_node_get(np); } diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index 094989d50ba..f12d5c69e74 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -60,6 +60,7 @@ #include <asm/of_device.h> #include <asm/lmb.h> #include <asm/mpic.h> +#include <asm/rtas.h> #include <asm/udbg.h> #include "maple.h" @@ -166,6 +167,16 @@ struct smp_ops_t maple_smp_ops = { }; #endif /* CONFIG_SMP */ +static void __init maple_use_rtas_reboot_and_halt_if_present(void) +{ + if (rtas_service_present("system-reboot") && + rtas_service_present("power-off")) { + ppc_md.restart = rtas_restart; + ppc_md.power_off = rtas_power_off; + ppc_md.halt = rtas_halt; + } +} + void __init maple_setup_arch(void) { /* init to some ~sane value until calibrate_delay() runs */ @@ -181,6 +192,7 @@ void __init maple_setup_arch(void) #ifdef CONFIG_DUMMY_CONSOLE conswitchp = &dummy_con; #endif + maple_use_rtas_reboot_and_halt_if_present(); printk(KERN_DEBUG "Using native/NAP idle loop\n"); } diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig index 451bfcd5502..de52ec4e9e5 100644 --- a/arch/powerpc/platforms/ps3/Kconfig +++ b/arch/powerpc/platforms/ps3/Kconfig @@ -40,4 +40,15 @@ config PS3_USE_LPAR_ADDR If you have any doubt, choose the default y. +config PS3_VUART + depends on PPC_PS3 + bool "PS3 Virtual UART support" + default y + help + Include support for the PS3 Virtual UART. + + This support is required for several system services + including the System Manager and AV Settings. In + general, all users will say Y. + endmenu diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 997243a91be..69590fbf83d 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -10,6 +10,8 @@ obj-$(CONFIG_XICS) += xics.o obj-$(CONFIG_SCANLOG) += scanlog.o obj-$(CONFIG_EEH) += eeh.o eeh_cache.o eeh_driver.o eeh_event.o +obj-$(CONFIG_HOTPLUG_CPU) += hotplug-cpu.o + obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o obj-$(CONFIG_HVCS) += hvcserver.o obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 3c2d63ebf78..da6e5362e7c 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -337,6 +337,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) printk (KERN_ERR "EEH: Device driver ignored %d bad reads, panicing\n", pdn->eeh_check_count); dump_stack(); + msleep(5000); /* re-read the slot reset state */ if (read_slot_reset_state(pdn, rets) != 0) diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c index c2bc9904f1c..cbd6b0711ab 100644 --- a/arch/powerpc/platforms/pseries/eeh_driver.c +++ b/arch/powerpc/platforms/pseries/eeh_driver.c @@ -170,14 +170,19 @@ static void eeh_report_reset(struct pci_dev *dev, void *userdata) static void eeh_report_resume(struct pci_dev *dev, void *userdata) { struct pci_driver *driver = dev->driver; + struct device_node *dn = pci_device_to_OF_node(dev); dev->error_state = pci_channel_io_normal; if (!driver) return; - if (!driver->err_handler) - return; - if (!driver->err_handler->resume) + + if ((PCI_DN(dn)->eeh_mode) & EEH_MODE_IRQ_DISABLED) { + PCI_DN(dn)->eeh_mode &= ~EEH_MODE_IRQ_DISABLED; + enable_irq(dev->irq); + } + if (!driver->err_handler || + !driver->err_handler->resume) return; driver->err_handler->resume(dev); @@ -407,6 +412,8 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event) if (rc) result = PCI_ERS_RESULT_NEED_RESET; + else + result = PCI_ERS_RESULT_RECOVERED; } /* If any device has a hard failure, then shut off everything. */ diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c new file mode 100644 index 00000000000..f460b9cbfd4 --- /dev/null +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -0,0 +1,275 @@ +/* + * pseries CPU Hotplug infrastructure. + * + * Split out from arch/powerpc/platforms/pseries/setup.c + * arch/powerpc/kernel/rtas.c, and arch/powerpc/platforms/pseries/smp.c + * + * Peter Bergner, IBM March 2001. + * Copyright (C) 2001 IBM. + * Dave Engebretsen, Peter Bergner, and + * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com + * Plus various changes from other IBM teams... + * + * Copyright (C) 2006 Michael Ellerman, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/delay.h> +#include <linux/cpu.h> +#include <asm/system.h> +#include <asm/prom.h> +#include <asm/rtas.h> +#include <asm/firmware.h> +#include <asm/machdep.h> +#include <asm/vdso_datapage.h> +#include <asm/pSeries_reconfig.h> +#include "xics.h" + +/* This version can't take the spinlock, because it never returns */ +static struct rtas_args rtas_stop_self_args = { + .token = RTAS_UNKNOWN_SERVICE, + .nargs = 0, + .nret = 1, + .rets = &rtas_stop_self_args.args[0], +}; + +static void rtas_stop_self(void) +{ + struct rtas_args *args = &rtas_stop_self_args; + + local_irq_disable(); + + BUG_ON(args->token == RTAS_UNKNOWN_SERVICE); + + printk("cpu %u (hwid %u) Ready to die...\n", + smp_processor_id(), hard_smp_processor_id()); + enter_rtas(__pa(args)); + + panic("Alas, I survived.\n"); +} + +static void pseries_mach_cpu_die(void) +{ + local_irq_disable(); + idle_task_exit(); + xics_teardown_cpu(0); + rtas_stop_self(); + /* Should never get here... */ + BUG(); + for(;;); +} + +static int qcss_tok; /* query-cpu-stopped-state token */ + +/* Get state of physical CPU. + * Return codes: + * 0 - The processor is in the RTAS stopped state + * 1 - stop-self is in progress + * 2 - The processor is not in the RTAS stopped state + * -1 - Hardware Error + * -2 - Hardware Busy, Try again later. + */ +static int query_cpu_stopped(unsigned int pcpu) +{ + int cpu_status, status; + + status = rtas_call(qcss_tok, 1, 2, &cpu_status, pcpu); + if (status != 0) { + printk(KERN_ERR + "RTAS query-cpu-stopped-state failed: %i\n", status); + return status; + } + + return cpu_status; +} + +static int pseries_cpu_disable(void) +{ + int cpu = smp_processor_id(); + + cpu_clear(cpu, cpu_online_map); + vdso_data->processorCount--; + + /*fix boot_cpuid here*/ + if (cpu == boot_cpuid) + boot_cpuid = any_online_cpu(cpu_online_map); + + /* FIXME: abstract this to not be platform specific later on */ + xics_migrate_irqs_away(); + return 0; +} + +static void pseries_cpu_die(unsigned int cpu) +{ + int tries; + int cpu_status; + unsigned int pcpu = get_hard_smp_processor_id(cpu); + + for (tries = 0; tries < 25; tries++) { + cpu_status = query_cpu_stopped(pcpu); + if (cpu_status == 0 || cpu_status == -1) + break; + msleep(200); + } + if (cpu_status != 0) { + printk("Querying DEAD? cpu %i (%i) shows %i\n", + cpu, pcpu, cpu_status); + } + + /* Isolation and deallocation are definatly done by + * drslot_chrp_cpu. If they were not they would be + * done here. Change isolate state to Isolate and + * change allocation-state to Unusable. + */ + paca[cpu].cpu_start = 0; +} + +/* + * Update cpu_present_map and paca(s) for a new cpu node. The wrinkle + * here is that a cpu device node may represent up to two logical cpus + * in the SMT case. We must honor the assumption in other code that + * the logical ids for sibling SMT threads x and y are adjacent, such + * that x^1 == y and y^1 == x. + */ +static int pseries_add_processor(struct device_node *np) +{ + unsigned int cpu; + cpumask_t candidate_map, tmp = CPU_MASK_NONE; + int err = -ENOSPC, len, nthreads, i; + const u32 *intserv; + + intserv = get_property(np, "ibm,ppc-interrupt-server#s", &len); + if (!intserv) + return 0; + + nthreads = len / sizeof(u32); + for (i = 0; i < nthreads; i++) + cpu_set(i, tmp); + + lock_cpu_hotplug(); + + BUG_ON(!cpus_subset(cpu_present_map, cpu_possible_map)); + + /* Get a bitmap of unoccupied slots. */ + cpus_xor(candidate_map, cpu_possible_map, cpu_present_map); + if (cpus_empty(candidate_map)) { + /* If we get here, it most likely means that NR_CPUS is + * less than the partition's max processors setting. + */ + printk(KERN_ERR "Cannot add cpu %s; this system configuration" + " supports %d logical cpus.\n", np->full_name, + cpus_weight(cpu_possible_map)); + goto out_unlock; + } + + while (!cpus_empty(tmp)) + if (cpus_subset(tmp, candidate_map)) + /* Found a range where we can insert the new cpu(s) */ + break; + else + cpus_shift_left(tmp, tmp, nthreads); + + if (cpus_empty(tmp)) { + printk(KERN_ERR "Unable to find space in cpu_present_map for" + " processor %s with %d thread(s)\n", np->name, + nthreads); + goto out_unlock; + } + + for_each_cpu_mask(cpu, tmp) { + BUG_ON(cpu_isset(cpu, cpu_present_map)); + cpu_set(cpu, cpu_present_map); + set_hard_smp_processor_id(cpu, *intserv++); + } + err = 0; +out_unlock: + unlock_cpu_hotplug(); + return err; +} + +/* + * Update the present map for a cpu node which is going away, and set + * the hard id in the paca(s) to -1 to be consistent with boot time + * convention for non-present cpus. + */ +static void pseries_remove_processor(struct device_node *np) +{ + unsigned int cpu; + int len, nthreads, i; + const u32 *intserv; + + intserv = get_property(np, "ibm,ppc-interrupt-server#s", &len); + if (!intserv) + return; + + nthreads = len / sizeof(u32); + + lock_cpu_hotplug(); + for (i = 0; i < nthreads; i++) { + for_each_present_cpu(cpu) { + if (get_hard_smp_processor_id(cpu) != intserv[i]) + continue; + BUG_ON(cpu_online(cpu)); + cpu_clear(cpu, cpu_present_map); + set_hard_smp_processor_id(cpu, -1); + break; + } + if (cpu == NR_CPUS) + printk(KERN_WARNING "Could not find cpu to remove " + "with physical id 0x%x\n", intserv[i]); + } + unlock_cpu_hotplug(); +} + +static int pseries_smp_notifier(struct notifier_block *nb, + unsigned long action, void *node) +{ + int err = NOTIFY_OK; + + switch (action) { + case PSERIES_RECONFIG_ADD: + if (pseries_add_processor(node)) + err = NOTIFY_BAD; + break; + case PSERIES_RECONFIG_REMOVE: + pseries_remove_processor(node); + break; + default: + err = NOTIFY_DONE; + break; + } + return err; +} + +static struct notifier_block pseries_smp_nb = { + .notifier_call = pseries_smp_notifier, +}; + +static int __init pseries_cpu_hotplug_init(void) +{ + rtas_stop_self_args.token = rtas_token("stop-self"); + qcss_tok = rtas_token("query-cpu-stopped-state"); + + if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE || + qcss_tok == RTAS_UNKNOWN_SERVICE) { + printk(KERN_INFO "CPU Hotplug not supported by firmware " + "- disabling.\n"); + return 0; + } + + ppc_md.cpu_die = pseries_mach_cpu_die; + smp_ops->cpu_disable = pseries_cpu_disable; + smp_ops->cpu_die = pseries_cpu_die; + + /* Processors can be added/removed only on LPAR */ + if (firmware_has_feature(FW_FEATURE_LPAR)) + pSeries_reconfig_notifier_register(&pseries_smp_nb); + + return 0; +} +arch_initcall(pseries_cpu_hotplug_init); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 0dc2548ca9b..042ecae107a 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -347,21 +347,6 @@ static int __init pSeries_init_panel(void) } arch_initcall(pSeries_init_panel); -#ifdef CONFIG_HOTPLUG_CPU -static void pSeries_mach_cpu_die(void) -{ - local_irq_disable(); - idle_task_exit(); - xics_teardown_cpu(0); - rtas_stop_self(); - /* Should never get here... */ - BUG(); - for(;;); -} -#else -#define pSeries_mach_cpu_die NULL -#endif - static int pseries_set_dabr(unsigned long dabr) { return plpar_hcall_norets(H_SET_DABR, dabr); @@ -437,19 +422,14 @@ static int __init pSeries_probe_hypertas(unsigned long node, if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL) != NULL) powerpc_firmware_features |= FW_FEATURE_LPAR; - if (firmware_has_feature(FW_FEATURE_LPAR)) - hpte_init_lpar(); - else - hpte_init_native(); - return 1; } static int __init pSeries_probe(void) { unsigned long root = of_get_flat_dt_root(); - char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(), - "device_type", NULL); + char *dtype = of_get_flat_dt_prop(root, "device_type", NULL); + if (dtype == NULL) return 0; if (strcmp(dtype, "chrp")) @@ -467,6 +447,11 @@ static int __init pSeries_probe(void) /* Now try to figure out if we are running on LPAR */ of_scan_flat_dt(pSeries_probe_hypertas, NULL); + if (firmware_has_feature(FW_FEATURE_LPAR)) + hpte_init_lpar(); + else + hpte_init_native(); + DBG("Machine is%s LPAR !\n", (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not"); @@ -561,7 +546,6 @@ define_machine(pseries) { .power_off = rtas_power_off, .halt = rtas_halt, .panic = rtas_os_term, - .cpu_die = pSeries_mach_cpu_die, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, .set_rtc_time = rtas_set_rtc_time, diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index c6624b8a0e7..4408518eaeb 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -64,197 +64,6 @@ static cpumask_t of_spin_map; extern void generic_secondary_smp_init(unsigned long); -#ifdef CONFIG_HOTPLUG_CPU - -/* Get state of physical CPU. - * Return codes: - * 0 - The processor is in the RTAS stopped state - * 1 - stop-self is in progress - * 2 - The processor is not in the RTAS stopped state - * -1 - Hardware Error - * -2 - Hardware Busy, Try again later. - */ -static int query_cpu_stopped(unsigned int pcpu) -{ - int cpu_status; - int status, qcss_tok; - - qcss_tok = rtas_token("query-cpu-stopped-state"); - if (qcss_tok == RTAS_UNKNOWN_SERVICE) - return -1; - status = rtas_call(qcss_tok, 1, 2, &cpu_status, pcpu); - if (status != 0) { - printk(KERN_ERR - "RTAS query-cpu-stopped-state failed: %i\n", status); - return status; - } - - return cpu_status; -} - -static int pSeries_cpu_disable(void) -{ - int cpu = smp_processor_id(); - - cpu_clear(cpu, cpu_online_map); - vdso_data->processorCount--; - - /*fix boot_cpuid here*/ - if (cpu == boot_cpuid) - boot_cpuid = any_online_cpu(cpu_online_map); - - /* FIXME: abstract this to not be platform specific later on */ - xics_migrate_irqs_away(); - return 0; -} - -static void pSeries_cpu_die(unsigned int cpu) -{ - int tries; - int cpu_status; - unsigned int pcpu = get_hard_smp_processor_id(cpu); - - for (tries = 0; tries < 25; tries++) { - cpu_status = query_cpu_stopped(pcpu); - if (cpu_status == 0 || cpu_status == -1) - break; - msleep(200); - } - if (cpu_status != 0) { - printk("Querying DEAD? cpu %i (%i) shows %i\n", - cpu, pcpu, cpu_status); - } - - /* Isolation and deallocation are definatly done by - * drslot_chrp_cpu. If they were not they would be - * done here. Change isolate state to Isolate and - * change allocation-state to Unusable. - */ - paca[cpu].cpu_start = 0; -} - -/* - * Update cpu_present_map and paca(s) for a new cpu node. The wrinkle - * here is that a cpu device node may represent up to two logical cpus - * in the SMT case. We must honor the assumption in other code that - * the logical ids for sibling SMT threads x and y are adjacent, such - * that x^1 == y and y^1 == x. - */ -static int pSeries_add_processor(struct device_node *np) -{ - unsigned int cpu; - cpumask_t candidate_map, tmp = CPU_MASK_NONE; - int err = -ENOSPC, len, nthreads, i; - const u32 *intserv; - - intserv = get_property(np, "ibm,ppc-interrupt-server#s", &len); - if (!intserv) - return 0; - - nthreads = len / sizeof(u32); - for (i = 0; i < nthreads; i++) - cpu_set(i, tmp); - - lock_cpu_hotplug(); - - BUG_ON(!cpus_subset(cpu_present_map, cpu_possible_map)); - - /* Get a bitmap of unoccupied slots. */ - cpus_xor(candidate_map, cpu_possible_map, cpu_present_map); - if (cpus_empty(candidate_map)) { - /* If we get here, it most likely means that NR_CPUS is - * less than the partition's max processors setting. - */ - printk(KERN_ERR "Cannot add cpu %s; this system configuration" - " supports %d logical cpus.\n", np->full_name, - cpus_weight(cpu_possible_map)); - goto out_unlock; - } - - while (!cpus_empty(tmp)) - if (cpus_subset(tmp, candidate_map)) - /* Found a range where we can insert the new cpu(s) */ - break; - else - cpus_shift_left(tmp, tmp, nthreads); - - if (cpus_empty(tmp)) { - printk(KERN_ERR "Unable to find space in cpu_present_map for" - " processor %s with %d thread(s)\n", np->name, - nthreads); - goto out_unlock; - } - - for_each_cpu_mask(cpu, tmp) { - BUG_ON(cpu_isset(cpu, cpu_present_map)); - cpu_set(cpu, cpu_present_map); - set_hard_smp_processor_id(cpu, *intserv++); - } - err = 0; -out_unlock: - unlock_cpu_hotplug(); - return err; -} - -/* - * Update the present map for a cpu node which is going away, and set - * the hard id in the paca(s) to -1 to be consistent with boot time - * convention for non-present cpus. - */ -static void pSeries_remove_processor(struct device_node *np) -{ - unsigned int cpu; - int len, nthreads, i; - const u32 *intserv; - - intserv = get_property(np, "ibm,ppc-interrupt-server#s", &len); - if (!intserv) - return; - - nthreads = len / sizeof(u32); - - lock_cpu_hotplug(); - for (i = 0; i < nthreads; i++) { - for_each_present_cpu(cpu) { - if (get_hard_smp_processor_id(cpu) != intserv[i]) - continue; - BUG_ON(cpu_online(cpu)); - cpu_clear(cpu, cpu_present_map); - set_hard_smp_processor_id(cpu, -1); - break; - } - if (cpu == NR_CPUS) - printk(KERN_WARNING "Could not find cpu to remove " - "with physical id 0x%x\n", intserv[i]); - } - unlock_cpu_hotplug(); -} - -static int pSeries_smp_notifier(struct notifier_block *nb, unsigned long action, void *node) -{ - int err = NOTIFY_OK; - - switch (action) { - case PSERIES_RECONFIG_ADD: - if (pSeries_add_processor(node)) - err = NOTIFY_BAD; - break; - case PSERIES_RECONFIG_REMOVE: - pSeries_remove_processor(node); - break; - default: - err = NOTIFY_DONE; - break; - } - return err; -} - -static struct notifier_block pSeries_smp_nb = { - .notifier_call = pSeries_smp_notifier, -}; - -#endif /* CONFIG_HOTPLUG_CPU */ - /** * smp_startup_cpu() - start the given cpu * @@ -422,15 +231,6 @@ static void __init smp_init_pseries(void) DBG(" -> smp_init_pSeries()\n"); -#ifdef CONFIG_HOTPLUG_CPU - smp_ops->cpu_disable = pSeries_cpu_disable; - smp_ops->cpu_die = pSeries_cpu_die; - - /* Processors can be added/removed only on LPAR */ - if (firmware_has_feature(FW_FEATURE_LPAR)) - pSeries_reconfig_notifier_register(&pSeries_smp_nb); -#endif - /* Mark threads which are still spinning in hold loops. */ if (cpu_has_feature(CPU_FTR_SMT)) { for_each_present_cpu(i) { diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 6cc34597a62..04d4917eb30 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -5,7 +5,8 @@ endif obj-$(CONFIG_MPIC) += mpic.o obj-$(CONFIG_PPC_INDIRECT_PCI) += indirect_pci.o obj-$(CONFIG_PPC_MPC106) += grackle.o -obj-$(CONFIG_PPC_DCR) += dcr.o dcr-low.o +obj-$(CONFIG_PPC_DCR) += dcr.o +obj-$(CONFIG_PPC_DCR_NATIVE) += dcr-low.o obj-$(CONFIG_U3_DART) += dart_iommu.o obj-$(CONFIG_MMIO_NVRAM) += mmio_nvram.o obj-$(CONFIG_FSL_SOC) += fsl_soc.o diff --git a/arch/powerpc/sysdev/dcr.S b/arch/powerpc/sysdev/dcr.S deleted file mode 100644 index 2078f39e2f1..00000000000 --- a/arch/powerpc/sysdev/dcr.S +++ /dev/null @@ -1,39 +0,0 @@ -/* - * "Indirect" DCR access - * - * Copyright (c) 2004 Eugene Surovegin <ebs@ebshome.net> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#include <asm/ppc_asm.h> -#include <asm/processor.h> - -#define DCR_ACCESS_PROLOG(table) \ - rlwinm r3,r3,4,18,27; \ - lis r5,table@h; \ - ori r5,r5,table@l; \ - add r3,r3,r5; \ - mtctr r3; \ - bctr - -_GLOBAL(__mfdcr) - DCR_ACCESS_PROLOG(__mfdcr_table) - -_GLOBAL(__mtdcr) - DCR_ACCESS_PROLOG(__mtdcr_table) - -__mfdcr_table: - mfdcr r3,0; blr -__mtdcr_table: - mtdcr 0,r4; blr - -dcr = 1 - .rept 1023 - mfdcr r3,dcr; blr - mtdcr dcr,r4; blr - dcr = dcr + 1 - .endr diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c index 6995f51b948..74e48d94f27 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_ic.c +++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c @@ -223,23 +223,15 @@ static void qe_ic_mask_irq(unsigned int virq) qe_ic_write(qe_ic->regs, qe_ic_info[src].mask_reg, temp & ~qe_ic_info[src].mask); - spin_unlock_irqrestore(&qe_ic_lock, flags); -} - -static void qe_ic_mask_irq_and_ack(unsigned int virq) -{ - struct qe_ic *qe_ic = qe_ic_from_irq(virq); - unsigned int src = virq_to_hw(virq); - unsigned long flags; - u32 temp; - - spin_lock_irqsave(&qe_ic_lock, flags); - - temp = qe_ic_read(qe_ic->regs, qe_ic_info[src].mask_reg); - qe_ic_write(qe_ic->regs, qe_ic_info[src].mask_reg, - temp & ~qe_ic_info[src].mask); - - /* There is nothing to do for ack here, ack is handled in ISR */ + /* Flush the above write before enabling interrupts; otherwise, + * spurious interrupts will sometimes happen. To be 100% sure + * that the write has reached the device before interrupts are + * enabled, the mask register would have to be read back; however, + * this is not required for correctness, only to avoid wasting + * time on a large number of spurious interrupts. In testing, + * a sync reduced the observed spurious interrupts to zero. + */ + mb(); spin_unlock_irqrestore(&qe_ic_lock, flags); } @@ -248,7 +240,7 @@ static struct irq_chip qe_ic_irq_chip = { .typename = " QEIC ", .unmask = qe_ic_unmask_irq, .mask = qe_ic_mask_irq, - .mask_ack = qe_ic_mask_irq_and_ack, + .mask_ack = qe_ic_mask_irq, }; static int qe_ic_host_match(struct irq_host *h, struct device_node *node) @@ -331,34 +323,22 @@ unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic) return irq_linear_revmap(qe_ic->irqhost, irq); } -/* FIXME: We mask all the QE Low interrupts while handling. We should - * let other interrupt come in, but BAD interrupts are generated */ void fastcall qe_ic_cascade_low(unsigned int irq, struct irq_desc *desc) { struct qe_ic *qe_ic = desc->handler_data; - struct irq_chip *chip = irq_desc[irq].chip; - unsigned int cascade_irq = qe_ic_get_low_irq(qe_ic); - chip->mask_ack(irq); if (cascade_irq != NO_IRQ) generic_handle_irq(cascade_irq); - chip->unmask(irq); } -/* FIXME: We mask all the QE High interrupts while handling. We should - * let other interrupt come in, but BAD interrupts are generated */ void fastcall qe_ic_cascade_high(unsigned int irq, struct irq_desc *desc) { struct qe_ic *qe_ic = desc->handler_data; - struct irq_chip *chip = irq_desc[irq].chip; - unsigned int cascade_irq = qe_ic_get_high_irq(qe_ic); - chip->mask_ack(irq); if (cascade_irq != NO_IRQ) generic_handle_irq(cascade_irq); - chip->unmask(irq); } void __init qe_ic_init(struct device_node *node, unsigned int flags) diff --git a/arch/powerpc/sysdev/rom.c b/arch/powerpc/sysdev/rom.c index bf5b3f10e6c..c855a3b298a 100644 --- a/arch/powerpc/sysdev/rom.c +++ b/arch/powerpc/sysdev/rom.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <asm/of_device.h> +#include <asm/of_platform.h> static int __init powerpc_flash_init(void) { diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index a34ed49e035..77540a2f770 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -22,6 +22,7 @@ #include <linux/sysrq.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/bug.h> #include <asm/ptrace.h> #include <asm/string.h> @@ -35,7 +36,6 @@ #include <asm/cputable.h> #include <asm/rtas.h> #include <asm/sstep.h> -#include <asm/bug.h> #include <asm/irq_regs.h> #include <asm/spu.h> #include <asm/spu_priv1.h> @@ -1346,7 +1346,7 @@ static void backtrace(struct pt_regs *excp) static void print_bug_trap(struct pt_regs *regs) { - struct bug_entry *bug; + const struct bug_entry *bug; unsigned long addr; if (regs->msr & MSR_PR) @@ -1357,11 +1357,11 @@ static void print_bug_trap(struct pt_regs *regs) bug = find_bug(regs->nip); if (bug == NULL) return; - if (bug->line & BUG_WARNING_TRAP) + if (is_warning_bug(bug)) return; - printf("kernel BUG in %s at %s:%d!\n", - bug->function, bug->file, (unsigned int)bug->line); + printf("kernel BUG at %s:%u!\n", + bug->file, bug->line); } void excprint(struct pt_regs *fp) diff --git a/arch/ppc/kernel/pci.c b/arch/ppc/kernel/pci.c index 63808e01cb0..5e723c4c257 100644 --- a/arch/ppc/kernel/pci.c +++ b/arch/ppc/kernel/pci.c @@ -879,7 +879,7 @@ pci_resource_to_bus(struct pci_dev *pdev, struct resource *res) static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, - unsigned long *offset, + resource_size_t *offset, enum pci_mmap_state mmap_state) { struct pci_controller *hose = pci_bus_to_hose(dev->bus->number); @@ -891,7 +891,9 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, /* If memory, add on the PCI bridge address offset */ if (mmap_state == pci_mmap_mem) { +#if 0 /* See comment in pci_resource_to_user() for why this is disabled */ *offset += hose->pci_mem_offset; +#endif res_bit = IORESOURCE_MEM; } else { io_offset = hose->io_base_virt - ___IO_BASE; @@ -1030,7 +1032,7 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine) { - unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT; struct resource *rp; int ret; @@ -1132,21 +1134,42 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, resource_size_t *start, resource_size_t *end) { struct pci_controller *hose = pci_bus_to_hose(dev->bus->number); - unsigned long offset = 0; + resource_size_t offset = 0; if (hose == NULL) return; if (rsrc->flags & IORESOURCE_IO) - offset = ___IO_BASE - hose->io_base_virt + hose->io_base_phys; + offset = (unsigned long)hose->io_base_virt - _IO_BASE; + + /* We pass a fully fixed up address to userland for MMIO instead of + * a BAR value because X is lame and expects to be able to use that + * to pass to /dev/mem ! + * + * That means that we'll have potentially 64 bits values where some + * userland apps only expect 32 (like X itself since it thinks only + * Sparc has 64 bits MMIO) but if we don't do that, we break it on + * 32 bits CHRPs :-( + * + * Hopefully, the sysfs insterface is immune to that gunk. Once X + * has been fixed (and the fix spread enough), we can re-enable the + * 2 lines below and pass down a BAR value to userland. In that case + * we'll also have to re-enable the matching code in + * __pci_mmap_make_offset(). + * + * BenH. + */ +#if 0 + else if (rsrc->flags & IORESOURCE_MEM) + offset = hose->pci_mem_offset; +#endif - *start = rsrc->start + offset; - *end = rsrc->end + offset; + *start = rsrc->start - offset; + *end = rsrc->end - offset; } -void __init -pci_init_resource(struct resource *res, unsigned long start, unsigned long end, - int flags, char *name) +void __init pci_init_resource(struct resource *res, resource_size_t start, + resource_size_t end, int flags, char *name) { res->start = start; res->end = end; |