diff options
Diffstat (limited to 'arch/powerpc/kernel')
35 files changed, 854 insertions, 843 deletions
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index f5995a912213..9d7dede2847c 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -216,8 +216,6 @@ int main(void) #endif /* CONFIG_PPC_BOOK3E */ #ifdef CONFIG_PPC_STD_MMU_64 - DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real)); - DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr)); DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache)); DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr)); DEFINE(PACAVMALLOCSLLP, offsetof(struct paca_struct, vmalloc_sllp)); @@ -493,6 +491,7 @@ int main(void) DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1)); DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock)); DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits)); + DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls)); DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr)); DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor)); DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v)); @@ -667,6 +666,7 @@ int main(void) DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr)); DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr)); DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc)); + DEFINE(VCPU_SPRG9, offsetof(struct kvm_vcpu, arch.sprg9)); DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst)); DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear)); DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr)); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 965291b4c2fa..9b6dcaaec1a3 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -123,96 +123,6 @@ extern void __restore_cpu_e6500(void); static struct cpu_spec __initdata cpu_specs[] = { #ifdef CONFIG_PPC_BOOK3S_64 - { /* Power3 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00400000, - .cpu_name = "POWER3 (630)", - .cpu_features = CPU_FTRS_POWER3, - .cpu_user_features = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power3", - .oprofile_type = PPC_OPROFILE_RS64, - .platform = "power3", - }, - { /* Power3+ */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00410000, - .cpu_name = "POWER3 (630+)", - .cpu_features = CPU_FTRS_POWER3, - .cpu_user_features = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power3", - .oprofile_type = PPC_OPROFILE_RS64, - .platform = "power3", - }, - { /* Northstar */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00330000, - .cpu_name = "RS64-II (northstar)", - .cpu_features = CPU_FTRS_RS64, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/rs64", - .oprofile_type = PPC_OPROFILE_RS64, - .platform = "rs64", - }, - { /* Pulsar */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00340000, - .cpu_name = "RS64-III (pulsar)", - .cpu_features = CPU_FTRS_RS64, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/rs64", - .oprofile_type = PPC_OPROFILE_RS64, - .platform = "rs64", - }, - { /* I-star */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00360000, - .cpu_name = "RS64-III (icestar)", - .cpu_features = CPU_FTRS_RS64, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/rs64", - .oprofile_type = PPC_OPROFILE_RS64, - .platform = "rs64", - }, - { /* S-star */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00370000, - .cpu_name = "RS64-IV (sstar)", - .cpu_features = CPU_FTRS_RS64, - .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/rs64", - .oprofile_type = PPC_OPROFILE_RS64, - .platform = "rs64", - }, { /* Power4 */ .pvr_mask = 0xffff0000, .pvr_value = 0x00350000, @@ -527,6 +437,26 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, + { /* Power8 DD1: Does not support doorbell IPIs */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x004d0100, + .cpu_name = "POWER8 (raw)", + .cpu_features = CPU_FTRS_POWER8_DD1, + .cpu_user_features = COMMON_USER_POWER8, + .cpu_user_features2 = COMMON_USER2_POWER8, + .mmu_features = MMU_FTRS_POWER8, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power8", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power8, + .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, + .platform = "power8", + }, { /* Power8 */ .pvr_mask = 0xffff0000, .pvr_value = 0x004d0000, @@ -597,7 +527,7 @@ static struct cpu_spec __initdata cpu_specs[] = { #endif /* CONFIG_PPC_BOOK3S_64 */ #ifdef CONFIG_PPC32 -#if CLASSIC_PPC +#ifdef CONFIG_PPC_BOOK3S_32 { /* 601 */ .pvr_mask = 0xffff0000, .pvr_value = 0x00010000, @@ -1237,7 +1167,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_generic, .platform = "ppc603", }, -#endif /* CLASSIC_PPC */ +#endif /* CONFIG_PPC_BOOK3S_32 */ #ifdef CONFIG_8xx { /* 8xx */ .pvr_mask = 0xffff0000, diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 86e25702aaca..59a64f8dc85f 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -27,6 +27,7 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/pci.h> +#include <linux/iommu.h> #include <linux/proc_fs.h> #include <linux/rbtree.h> #include <linux/reboot.h> @@ -40,6 +41,7 @@ #include <asm/eeh.h> #include <asm/eeh_event.h> #include <asm/io.h> +#include <asm/iommu.h> #include <asm/machdep.h> #include <asm/ppc-pci.h> #include <asm/rtas.h> @@ -108,6 +110,9 @@ struct eeh_ops *eeh_ops = NULL; /* Lock to avoid races due to multiple reports of an error */ DEFINE_RAW_SPINLOCK(confirm_error_lock); +/* Lock to protect passed flags */ +static DEFINE_MUTEX(eeh_dev_mutex); + /* Buffer for reporting pci register dumps. Its here in BSS, and * not dynamically alloced, so that it ends up in RMO where RTAS * can access it. @@ -137,7 +142,7 @@ static struct eeh_stats eeh_stats; static int __init eeh_setup(char *str) { if (!strcmp(str, "off")) - eeh_subsystem_flags |= EEH_FORCE_DISABLED; + eeh_add_flag(EEH_FORCE_DISABLED); return 1; } @@ -152,12 +157,13 @@ __setup("eeh=", eeh_setup); * This routine captures assorted PCI configuration space data, * and puts them into a buffer for RTAS error logging. */ -static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) +static size_t eeh_gather_pci_data(struct eeh_dev *edev, char *buf, size_t len) { struct device_node *dn = eeh_dev_to_of_node(edev); u32 cfg; int cap, i; - int n = 0; + int n = 0, l = 0; + char buffer[128]; n += scnprintf(buf+n, len-n, "%s\n", dn->full_name); pr_warn("EEH: of node=%s\n", dn->full_name); @@ -202,8 +208,22 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) for (i=0; i<=8; i++) { eeh_ops->read_config(dn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - pr_warn("EEH: PCI-E %02x: %08x\n", i, cfg); + + if ((i % 4) == 0) { + if (i != 0) + pr_warn("%s\n", buffer); + + l = scnprintf(buffer, sizeof(buffer), + "EEH: PCI-E %02x: %08x ", + 4*i, cfg); + } else { + l += scnprintf(buffer+l, sizeof(buffer)-l, + "%08x ", cfg); + } + } + + pr_warn("%s\n", buffer); } /* If AER capable, dump it */ @@ -212,11 +232,24 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) n += scnprintf(buf+n, len-n, "pci-e AER:\n"); pr_warn("EEH: PCI-E AER capability register set follows:\n"); - for (i=0; i<14; i++) { + for (i=0; i<=13; i++) { eeh_ops->read_config(dn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); - pr_warn("EEH: PCI-E AER %02x: %08x\n", i, cfg); + + if ((i % 4) == 0) { + if (i != 0) + pr_warn("%s\n", buffer); + + l = scnprintf(buffer, sizeof(buffer), + "EEH: PCI-E AER %02x: %08x ", + 4*i, cfg); + } else { + l += scnprintf(buffer+l, sizeof(buffer)-l, + "%08x ", cfg); + } } + + pr_warn("%s\n", buffer); } return n; @@ -247,7 +280,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity) * 0xFF's is always returned from PCI config space. */ if (!(pe->type & EEH_PE_PHB)) { - if (eeh_probe_mode_devtree()) + if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG)) eeh_pci_enable(pe, EEH_OPT_THAW_MMIO); eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); @@ -298,14 +331,14 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) unsigned long flags; int ret; - if (!eeh_probe_mode_dev()) + if (!eeh_has_flag(EEH_PROBE_MODE_DEV)) return -EPERM; /* Find the PHB PE */ phb_pe = eeh_phb_pe_get(pe->phb); if (!phb_pe) { - pr_warning("%s Can't find PE for PHB#%d\n", - __func__, pe->phb->global_number); + pr_warn("%s Can't find PE for PHB#%d\n", + __func__, pe->phb->global_number); return -EEXIST; } @@ -400,6 +433,14 @@ int eeh_dev_check_failure(struct eeh_dev *edev) if (ret > 0) return ret; + /* + * If the PE isn't owned by us, we shouldn't check the + * state. Instead, let the owner handle it if the PE has + * been frozen. + */ + if (eeh_pe_passed(pe)) + return 0; + /* If we already have a pending isolation event for this * slot, we know it's bad already, we don't need to check. * Do this checking under a lock; as multiple PCI devices @@ -746,13 +787,13 @@ void eeh_save_bars(struct eeh_dev *edev) int __init eeh_ops_register(struct eeh_ops *ops) { if (!ops->name) { - pr_warning("%s: Invalid EEH ops name for %p\n", + pr_warn("%s: Invalid EEH ops name for %p\n", __func__, ops); return -EINVAL; } if (eeh_ops && eeh_ops != ops) { - pr_warning("%s: EEH ops of platform %s already existing (%s)\n", + pr_warn("%s: EEH ops of platform %s already existing (%s)\n", __func__, eeh_ops->name, ops->name); return -EEXIST; } @@ -772,7 +813,7 @@ int __init eeh_ops_register(struct eeh_ops *ops) int __exit eeh_ops_unregister(const char *name) { if (!name || !strlen(name)) { - pr_warning("%s: Invalid EEH ops name\n", + pr_warn("%s: Invalid EEH ops name\n", __func__); return -EINVAL; } @@ -788,7 +829,7 @@ int __exit eeh_ops_unregister(const char *name) static int eeh_reboot_notifier(struct notifier_block *nb, unsigned long action, void *unused) { - eeh_set_enable(false); + eeh_clear_flag(EEH_ENABLED); return NOTIFY_DONE; } @@ -837,11 +878,11 @@ int eeh_init(void) /* call platform initialization function */ if (!eeh_ops) { - pr_warning("%s: Platform EEH operation not found\n", + pr_warn("%s: Platform EEH operation not found\n", __func__); return -EEXIST; } else if ((ret = eeh_ops->init())) { - pr_warning("%s: Failed to call platform init function (%d)\n", + pr_warn("%s: Failed to call platform init function (%d)\n", __func__, ret); return ret; } @@ -852,13 +893,13 @@ int eeh_init(void) return ret; /* Enable EEH for all adapters */ - if (eeh_probe_mode_devtree()) { + if (eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) { list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { phb = hose->dn; traverse_pci_devices(phb, eeh_ops->of_probe, NULL); } - } else if (eeh_probe_mode_dev()) { + } else if (eeh_has_flag(EEH_PROBE_MODE_DEV)) { list_for_each_entry_safe(hose, tmp, &hose_list, list_node) pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL); @@ -882,7 +923,7 @@ int eeh_init(void) if (eeh_enabled()) pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); else - pr_warning("EEH: No capable adapters found\n"); + pr_warn("EEH: No capable adapters found\n"); return ret; } @@ -910,7 +951,7 @@ void eeh_add_device_early(struct device_node *dn) * would delay the probe until late stage because * the PCI device isn't available this moment. */ - if (!eeh_probe_mode_devtree()) + if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) return; if (!of_node_to_eeh_dev(dn)) @@ -996,7 +1037,7 @@ void eeh_add_device_late(struct pci_dev *dev) * We have to do the EEH probe here because the PCI device * hasn't been created yet in the early stage. */ - if (eeh_probe_mode_dev()) + if (eeh_has_flag(EEH_PROBE_MODE_DEV)) eeh_ops->dev_probe(dev, NULL); eeh_addr_cache_insert_dev(dev); @@ -1100,6 +1141,285 @@ void eeh_remove_device(struct pci_dev *dev) edev->mode &= ~EEH_DEV_SYSFS; } +/** + * eeh_dev_open - Increase count of pass through devices for PE + * @pdev: PCI device + * + * Increase count of passed through devices for the indicated + * PE. In the result, the EEH errors detected on the PE won't be + * reported. The PE owner will be responsible for detection + * and recovery. + */ +int eeh_dev_open(struct pci_dev *pdev) +{ + struct eeh_dev *edev; + + mutex_lock(&eeh_dev_mutex); + + /* No PCI device ? */ + if (!pdev) + goto out; + + /* No EEH device or PE ? */ + edev = pci_dev_to_eeh_dev(pdev); + if (!edev || !edev->pe) + goto out; + + /* Increase PE's pass through count */ + atomic_inc(&edev->pe->pass_dev_cnt); + mutex_unlock(&eeh_dev_mutex); + + return 0; +out: + mutex_unlock(&eeh_dev_mutex); + return -ENODEV; +} +EXPORT_SYMBOL_GPL(eeh_dev_open); + +/** + * eeh_dev_release - Decrease count of pass through devices for PE + * @pdev: PCI device + * + * Decrease count of pass through devices for the indicated PE. If + * there is no passed through device in PE, the EEH errors detected + * on the PE will be reported and handled as usual. + */ +void eeh_dev_release(struct pci_dev *pdev) +{ + struct eeh_dev *edev; + + mutex_lock(&eeh_dev_mutex); + + /* No PCI device ? */ + if (!pdev) + goto out; + + /* No EEH device ? */ + edev = pci_dev_to_eeh_dev(pdev); + if (!edev || !edev->pe || !eeh_pe_passed(edev->pe)) + goto out; + + /* Decrease PE's pass through count */ + atomic_dec(&edev->pe->pass_dev_cnt); + WARN_ON(atomic_read(&edev->pe->pass_dev_cnt) < 0); +out: + mutex_unlock(&eeh_dev_mutex); +} +EXPORT_SYMBOL(eeh_dev_release); + +#ifdef CONFIG_IOMMU_API + +static int dev_has_iommu_table(struct device *dev, void *data) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct pci_dev **ppdev = data; + struct iommu_table *tbl; + + if (!dev) + return 0; + + tbl = get_iommu_table_base(dev); + if (tbl && tbl->it_group) { + *ppdev = pdev; + return 1; + } + + return 0; +} + +/** + * eeh_iommu_group_to_pe - Convert IOMMU group to EEH PE + * @group: IOMMU group + * + * The routine is called to convert IOMMU group to EEH PE. + */ +struct eeh_pe *eeh_iommu_group_to_pe(struct iommu_group *group) +{ + struct pci_dev *pdev = NULL; + struct eeh_dev *edev; + int ret; + + /* No IOMMU group ? */ + if (!group) + return NULL; + + ret = iommu_group_for_each_dev(group, &pdev, dev_has_iommu_table); + if (!ret || !pdev) + return NULL; + + /* No EEH device or PE ? */ + edev = pci_dev_to_eeh_dev(pdev); + if (!edev || !edev->pe) + return NULL; + + return edev->pe; +} +EXPORT_SYMBOL_GPL(eeh_iommu_group_to_pe); + +#endif /* CONFIG_IOMMU_API */ + +/** + * eeh_pe_set_option - Set options for the indicated PE + * @pe: EEH PE + * @option: requested option + * + * The routine is called to enable or disable EEH functionality + * on the indicated PE, to enable IO or DMA for the frozen PE. + */ +int eeh_pe_set_option(struct eeh_pe *pe, int option) +{ + int ret = 0; + + /* Invalid PE ? */ + if (!pe) + return -ENODEV; + + /* + * EEH functionality could possibly be disabled, just + * return error for the case. And the EEH functinality + * isn't expected to be disabled on one specific PE. + */ + switch (option) { + case EEH_OPT_ENABLE: + if (eeh_enabled()) + break; + ret = -EIO; + break; + case EEH_OPT_DISABLE: + break; + case EEH_OPT_THAW_MMIO: + case EEH_OPT_THAW_DMA: + if (!eeh_ops || !eeh_ops->set_option) { + ret = -ENOENT; + break; + } + + ret = eeh_ops->set_option(pe, option); + break; + default: + pr_debug("%s: Option %d out of range (%d, %d)\n", + __func__, option, EEH_OPT_DISABLE, EEH_OPT_THAW_DMA); + ret = -EINVAL; + } + + return ret; +} +EXPORT_SYMBOL_GPL(eeh_pe_set_option); + +/** + * eeh_pe_get_state - Retrieve PE's state + * @pe: EEH PE + * + * Retrieve the PE's state, which includes 3 aspects: enabled + * DMA, enabled IO and asserted reset. + */ +int eeh_pe_get_state(struct eeh_pe *pe) +{ + int result, ret = 0; + bool rst_active, dma_en, mmio_en; + + /* Existing PE ? */ + if (!pe) + return -ENODEV; + + if (!eeh_ops || !eeh_ops->get_state) + return -ENOENT; + + result = eeh_ops->get_state(pe, NULL); + rst_active = !!(result & EEH_STATE_RESET_ACTIVE); + dma_en = !!(result & EEH_STATE_DMA_ENABLED); + mmio_en = !!(result & EEH_STATE_MMIO_ENABLED); + + if (rst_active) + ret = EEH_PE_STATE_RESET; + else if (dma_en && mmio_en) + ret = EEH_PE_STATE_NORMAL; + else if (!dma_en && !mmio_en) + ret = EEH_PE_STATE_STOPPED_IO_DMA; + else if (!dma_en && mmio_en) + ret = EEH_PE_STATE_STOPPED_DMA; + else + ret = EEH_PE_STATE_UNAVAIL; + + return ret; +} +EXPORT_SYMBOL_GPL(eeh_pe_get_state); + +/** + * eeh_pe_reset - Issue PE reset according to specified type + * @pe: EEH PE + * @option: reset type + * + * The routine is called to reset the specified PE with the + * indicated type, either fundamental reset or hot reset. + * PE reset is the most important part for error recovery. + */ +int eeh_pe_reset(struct eeh_pe *pe, int option) +{ + int ret = 0; + + /* Invalid PE ? */ + if (!pe) + return -ENODEV; + + if (!eeh_ops || !eeh_ops->set_option || !eeh_ops->reset) + return -ENOENT; + + switch (option) { + case EEH_RESET_DEACTIVATE: + ret = eeh_ops->reset(pe, option); + if (ret) + break; + + /* + * The PE is still in frozen state and we need to clear + * that. It's good to clear frozen state after deassert + * to avoid messy IO access during reset, which might + * cause recursive frozen PE. + */ + ret = eeh_ops->set_option(pe, EEH_OPT_THAW_MMIO); + if (!ret) + ret = eeh_ops->set_option(pe, EEH_OPT_THAW_DMA); + if (!ret) + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); + break; + case EEH_RESET_HOT: + case EEH_RESET_FUNDAMENTAL: + ret = eeh_ops->reset(pe, option); + break; + default: + pr_debug("%s: Unsupported option %d\n", + __func__, option); + ret = -EINVAL; + } + + return ret; +} +EXPORT_SYMBOL_GPL(eeh_pe_reset); + +/** + * eeh_pe_configure - Configure PCI bridges after PE reset + * @pe: EEH PE + * + * The routine is called to restore the PCI config space for + * those PCI devices, especially PCI bridges affected by PE + * reset issued previously. + */ +int eeh_pe_configure(struct eeh_pe *pe) +{ + int ret = 0; + + /* Invalid PE ? */ + if (!pe) + return -ENODEV; + + /* Restore config space for the affected devices */ + eeh_pe_restore_bars(pe); + + return ret; +} +EXPORT_SYMBOL_GPL(eeh_pe_configure); + static int proc_eeh_show(struct seq_file *m, void *v) { if (!eeh_enabled()) { @@ -1143,9 +1463,9 @@ static const struct file_operations proc_eeh_operations = { static int eeh_enable_dbgfs_set(void *data, u64 val) { if (val) - eeh_subsystem_flags &= ~EEH_FORCE_DISABLED; + eeh_clear_flag(EEH_FORCE_DISABLED); else - eeh_subsystem_flags |= EEH_FORCE_DISABLED; + eeh_add_flag(EEH_FORCE_DISABLED); /* Notify the backend */ if (eeh_ops->post_init) diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index e8c9fd546a5c..07d8a2423a61 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -143,7 +143,7 @@ eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo, } else { if (dev != piar->pcidev || alo != piar->addr_lo || ahi != piar->addr_hi) { - pr_warning("PIAR: overlapping address range\n"); + pr_warn("PIAR: overlapping address range\n"); } return piar; } @@ -177,19 +177,20 @@ static void __eeh_addr_cache_insert_dev(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); if (!dn) { - pr_warning("PCI: no pci dn found for dev=%s\n", pci_name(dev)); + pr_warn("PCI: no pci dn found for dev=%s\n", + pci_name(dev)); return; } edev = of_node_to_eeh_dev(dn); if (!edev) { - pr_warning("PCI: no EEH dev found for dn=%s\n", + pr_warn("PCI: no EEH dev found for dn=%s\n", dn->full_name); return; } /* Skip any devices for which EEH is not enabled. */ - if (!eeh_probe_mode_dev() && !edev->pe) { + if (!edev->pe) { #ifdef DEBUG pr_info("PCI: skip building address cache for=%s - %s\n", pci_name(dev), dn->full_name); diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c index 1efa28f5fc54..e5274ee9a75f 100644 --- a/arch/powerpc/kernel/eeh_dev.c +++ b/arch/powerpc/kernel/eeh_dev.c @@ -57,7 +57,8 @@ void *eeh_dev_init(struct device_node *dn, void *data) /* Allocate EEH device */ edev = kzalloc(sizeof(*edev), GFP_KERNEL); if (!edev) { - pr_warning("%s: out of memory\n", __func__); + pr_warn("%s: out of memory\n", + __func__); return NULL; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 420da61d4ce0..6a0dcee8e931 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -599,7 +599,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) pe->freeze_count++; if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) goto excess_failures; - pr_warning("EEH: This PCI device has failed %d times in the last hour\n", + pr_warn("EEH: This PCI device has failed %d times in the last hour\n", pe->freeze_count); /* Walk the various device drivers attached to this slot through @@ -616,7 +616,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) */ rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000); if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) { - pr_warning("EEH: Permanent failure\n"); + pr_warn("EEH: Permanent failure\n"); goto hard_fail; } @@ -635,8 +635,8 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) pr_info("EEH: Reset with hotplug activity\n"); rc = eeh_reset_device(pe, frozen_bus); if (rc) { - pr_warning("%s: Unable to reset, err=%d\n", - __func__, rc); + pr_warn("%s: Unable to reset, err=%d\n", + __func__, rc); goto hard_fail; } } @@ -678,7 +678,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) /* If any device has a hard failure, then shut off everything. */ if (result == PCI_ERS_RESULT_DISCONNECT) { - pr_warning("EEH: Device driver gave up\n"); + pr_warn("EEH: Device driver gave up\n"); goto hard_fail; } @@ -687,8 +687,8 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) pr_info("EEH: Reset without hotplug activity\n"); rc = eeh_reset_device(pe, NULL); if (rc) { - pr_warning("%s: Cannot reset, err=%d\n", - __func__, rc); + pr_warn("%s: Cannot reset, err=%d\n", + __func__, rc); goto hard_fail; } @@ -701,7 +701,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) /* All devices should claim they have recovered by now. */ if ((result != PCI_ERS_RESULT_RECOVERED) && (result != PCI_ERS_RESULT_NONE)) { - pr_warning("EEH: Not recovered\n"); + pr_warn("EEH: Not recovered\n"); goto hard_fail; } diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index fbd01eba4473..00e3844525a6 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -32,9 +32,24 @@ #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> +static int eeh_pe_aux_size = 0; static LIST_HEAD(eeh_phb_pe); /** + * eeh_set_pe_aux_size - Set PE auxillary data size + * @size: PE auxillary data size + * + * Set PE auxillary data size + */ +void eeh_set_pe_aux_size(int size) +{ + if (size < 0) + return; + + eeh_pe_aux_size = size; +} + +/** * eeh_pe_alloc - Allocate PE * @phb: PCI controller * @type: PE type @@ -44,9 +59,16 @@ static LIST_HEAD(eeh_phb_pe); static struct eeh_pe *eeh_pe_alloc(struct pci_controller *phb, int type) { struct eeh_pe *pe; + size_t alloc_size; + + alloc_size = sizeof(struct eeh_pe); + if (eeh_pe_aux_size) { + alloc_size = ALIGN(alloc_size, cache_line_size()); + alloc_size += eeh_pe_aux_size; + } /* Allocate PHB PE */ - pe = kzalloc(sizeof(struct eeh_pe), GFP_KERNEL); + pe = kzalloc(alloc_size, GFP_KERNEL); if (!pe) return NULL; /* Initialize PHB PE */ @@ -56,6 +78,8 @@ static struct eeh_pe *eeh_pe_alloc(struct pci_controller *phb, int type) INIT_LIST_HEAD(&pe->child); INIT_LIST_HEAD(&pe->edevs); + pe->data = (void *)pe + ALIGN(sizeof(struct eeh_pe), + cache_line_size()); return pe; } @@ -179,7 +203,8 @@ void *eeh_pe_dev_traverse(struct eeh_pe *root, void *ret; if (!root) { - pr_warning("%s: Invalid PE %p\n", __func__, root); + pr_warn("%s: Invalid PE %p\n", + __func__, root); return NULL; } @@ -351,17 +376,6 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) pe->config_addr = edev->config_addr; /* - * While doing PE reset, we probably hot-reset the - * upstream bridge. However, the PCI devices including - * the associated EEH devices might be removed when EEH - * core is doing recovery. So that won't safe to retrieve - * the bridge through downstream EEH device. We have to - * trace the parent PCI bus, then the upstream bridge. - */ - if (eeh_probe_mode_dev()) - pe->bus = eeh_dev_to_pci_dev(edev)->bus; - - /* * Put the new EEH PE into hierarchy tree. If the parent * can't be found, the newly created PE will be attached * to PHB directly. Otherwise, we have to associate the @@ -802,53 +816,33 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) */ const char *eeh_pe_loc_get(struct eeh_pe *pe) { - struct pci_controller *hose; struct pci_bus *bus = eeh_pe_bus_get(pe); - struct pci_dev *pdev; - struct device_node *dn; - const char *loc; + struct device_node *dn = pci_bus_to_OF_node(bus); + const char *loc = NULL; - if (!bus) - return "N/A"; + if (!dn) + goto out; /* PHB PE or root PE ? */ if (pci_is_root_bus(bus)) { - hose = pci_bus_to_host(bus); - loc = of_get_property(hose->dn, - "ibm,loc-code", NULL); + loc = of_get_property(dn, "ibm,loc-code", NULL); + if (!loc) + loc = of_get_property(dn, "ibm,io-base-loc-code", NULL); if (loc) - return loc; - loc = of_get_property(hose->dn, - "ibm,io-base-loc-code", NULL); - if (loc) - return loc; - - pdev = pci_get_slot(bus, 0x0); - } else { - pdev = bus->self; - } - - if (!pdev) { - loc = "N/A"; - goto out; - } + goto out; - dn = pci_device_to_OF_node(pdev); - if (!dn) { - loc = "N/A"; - goto out; + /* Check the root port */ + dn = dn->child; + if (!dn) + goto out; } loc = of_get_property(dn, "ibm,loc-code", NULL); if (!loc) loc = of_get_property(dn, "ibm,slot-location-code", NULL); - if (!loc) - loc = "N/A"; out: - if (pci_is_root_bus(bus) && pdev) - pci_dev_put(pdev); - return loc; + return loc ? loc : "N/A"; } /** diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 6528c5e2cc44..5bbd1bc8c3b0 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -482,16 +482,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS) ld r8,KSP(r4) /* new stack pointer */ #ifdef CONFIG_PPC_BOOK3S BEGIN_FTR_SECTION - BEGIN_FTR_SECTION_NESTED(95) clrrdi r6,r8,28 /* get its ESID */ clrrdi r9,r1,28 /* get current sp ESID */ - FTR_SECTION_ELSE_NESTED(95) +FTR_SECTION_ELSE clrrdi r6,r8,40 /* get its 1T ESID */ clrrdi r9,r1,40 /* get current sp 1T ESID */ - ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(MMU_FTR_1T_SEGMENT, 95) -FTR_SECTION_ELSE - b 2f -ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_SLB) +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_1T_SEGMENT) clrldi. r0,r6,2 /* is new ESID c00000000? */ cmpd cr1,r6,r9 /* or is new ESID the same as current ESID? */ cror eq,4*cr1+eq,eq @@ -919,6 +915,11 @@ restore_check_irq_replay: addi r3,r1,STACK_FRAME_OVERHEAD; bl do_IRQ b ret_from_except +1: cmpwi cr0,r3,0xe60 + bne 1f + addi r3,r1,STACK_FRAME_OVERHEAD; + bl handle_hmi_exception + b ret_from_except 1: cmpwi cr0,r3,0x900 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index a7d36b19221d..6144d5a6bfe7 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -188,10 +188,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) data_access_pSeries: HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) -BEGIN_FTR_SECTION - b data_access_check_stab -data_access_not_stab: -END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD, KVMTEST, 0x300) @@ -339,7 +335,7 @@ emulation_assist_trampoline: hv_exception_trampoline: SET_SCRATCH0(r13) EXCEPTION_PROLOG_0(PACA_EXGEN) - b hmi_exception_hv + b hmi_exception_early . = 0xe80 hv_doorbell_trampoline: @@ -514,34 +510,6 @@ machine_check_pSeries_0: EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200) EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD) KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) - - /* moved from 0x300 */ -data_access_check_stab: - GET_PACA(r13) - std r9,PACA_EXSLB+EX_R9(r13) - std r10,PACA_EXSLB+EX_R10(r13) - mfspr r10,SPRN_DAR - mfspr r9,SPRN_DSISR - srdi r10,r10,60 - rlwimi r10,r9,16,0x20 -#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE - lbz r9,HSTATE_IN_GUEST(r13) - rlwimi r10,r9,8,0x300 -#endif - mfcr r9 - cmpwi r10,0x2c - beq do_stab_bolted_pSeries - mtcrf 0x80,r9 - ld r9,PACA_EXSLB+EX_R9(r13) - ld r10,PACA_EXSLB+EX_R10(r13) - b data_access_not_stab -do_stab_bolted_pSeries: - std r11,PACA_EXSLB+EX_R11(r13) - std r12,PACA_EXSLB+EX_R12(r13) - GET_SCRATCH0(r10) - std r10,PACA_EXSLB+EX_R13(r13) - EXCEPTION_PROLOG_PSERIES_1(do_stab_bolted, EXC_STD) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400) @@ -621,8 +589,64 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe22) STD_EXCEPTION_HV_OOL(0xe42, emulation_assist) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe42) - STD_EXCEPTION_HV_OOL(0xe62, hmi_exception) /* need to flush cache ? */ + MASKABLE_EXCEPTION_HV_OOL(0xe62, hmi_exception) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe62) + + .globl hmi_exception_early +hmi_exception_early: + EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0xe60) + mr r10,r1 /* Save r1 */ + ld r1,PACAEMERGSP(r13) /* Use emergency stack */ + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + std r9,_CCR(r1) /* save CR in stackframe */ + mfspr r11,SPRN_HSRR0 /* Save HSRR0 */ + std r11,_NIP(r1) /* save HSRR0 in stackframe */ + mfspr r12,SPRN_HSRR1 /* Save SRR1 */ + std r12,_MSR(r1) /* save SRR1 in stackframe */ + std r10,0(r1) /* make stack chain pointer */ + std r0,GPR0(r1) /* save r0 in stackframe */ + std r10,GPR1(r1) /* save r1 in stackframe */ + EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) + EXCEPTION_PROLOG_COMMON_3(0xe60) + addi r3,r1,STACK_FRAME_OVERHEAD + bl hmi_exception_realmode + /* Windup the stack. */ + /* Clear MSR_RI before setting SRR0 and SRR1. */ + li r0,MSR_RI + mfmsr r9 /* get MSR value */ + andc r9,r9,r0 + mtmsrd r9,1 /* Clear MSR_RI */ + /* Move original HSRR0 and HSRR1 into the respective regs */ + ld r9,_MSR(r1) + mtspr SPRN_HSRR1,r9 + ld r3,_NIP(r1) + mtspr SPRN_HSRR0,r3 + ld r9,_CTR(r1) + mtctr r9 + ld r9,_XER(r1) + mtxer r9 + ld r9,_LINK(r1) + mtlr r9 + REST_GPR(0, r1) + REST_8GPRS(2, r1) + REST_GPR(10, r1) + ld r11,_CCR(r1) + mtcr r11 + REST_GPR(11, r1) + REST_2GPRS(12, r1) + /* restore original r1. */ + ld r1,GPR1(r1) + + /* + * Go to virtual mode and pull the HMI event information from + * firmware. + */ + .globl hmi_exception_after_realmode +hmi_exception_after_realmode: + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXGEN) + b hmi_exception_hv + MASKABLE_EXCEPTION_HV_OOL(0xe82, h_doorbell) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe82) @@ -643,6 +667,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) * - If it was a decrementer interrupt, we bump the dec to max and and return. * - If it was a doorbell we return immediately since doorbells are edge * triggered and won't automatically refire. + * - If it was a HMI we return immediately since we handled it in realmode + * and it won't refire. * - else we hard disable and return. * This is called with r10 containing the value to OR to the paca field. */ @@ -660,6 +686,8 @@ masked_##_H##interrupt: \ b 2f; \ 1: cmpwi r10,PACA_IRQ_DBELL; \ beq 2f; \ + cmpwi r10,PACA_IRQ_HMI; \ + beq 2f; \ mfspr r10,SPRN_##_H##SRR1; \ rldicl r10,r10,48,1; /* clear MSR_EE */ \ rotldi r10,r10,16; \ @@ -799,7 +827,7 @@ kvmppc_skip_Hinterrupt: STD_EXCEPTION_COMMON(0xd00, single_step, single_step_exception) STD_EXCEPTION_COMMON(0xe00, trap_0e, unknown_exception) STD_EXCEPTION_COMMON(0xe40, emulation_assist, emulation_assist_interrupt) - STD_EXCEPTION_COMMON(0xe60, hmi_exception, unknown_exception) + STD_EXCEPTION_COMMON_ASYNC(0xe60, hmi_exception, handle_hmi_exception) #ifdef CONFIG_PPC_DOORBELL STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, doorbell_exception) #else @@ -985,66 +1013,6 @@ ppc64_runlatch_on_trampoline: b __ppc64_runlatch_on /* - * Here we have detected that the kernel stack pointer is bad. - * R9 contains the saved CR, r13 points to the paca, - * r10 contains the (bad) kernel stack pointer, - * r11 and r12 contain the saved SRR0 and SRR1. - * We switch to using an emergency stack, save the registers there, - * and call kernel_bad_stack(), which panics. - */ -bad_stack: - ld r1,PACAEMERGSP(r13) - subi r1,r1,64+INT_FRAME_SIZE - std r9,_CCR(r1) - std r10,GPR1(r1) - std r11,_NIP(r1) - std r12,_MSR(r1) - mfspr r11,SPRN_DAR - mfspr r12,SPRN_DSISR - std r11,_DAR(r1) - std r12,_DSISR(r1) - mflr r10 - mfctr r11 - mfxer r12 - std r10,_LINK(r1) - std r11,_CTR(r1) - std r12,_XER(r1) - SAVE_GPR(0,r1) - SAVE_GPR(2,r1) - ld r10,EX_R3(r3) - std r10,GPR3(r1) - SAVE_GPR(4,r1) - SAVE_4GPRS(5,r1) - ld r9,EX_R9(r3) - ld r10,EX_R10(r3) - SAVE_2GPRS(9,r1) - ld r9,EX_R11(r3) - ld r10,EX_R12(r3) - ld r11,EX_R13(r3) - std r9,GPR11(r1) - std r10,GPR12(r1) - std r11,GPR13(r1) -BEGIN_FTR_SECTION - ld r10,EX_CFAR(r3) - std r10,ORIG_GPR3(r1) -END_FTR_SECTION_IFSET(CPU_FTR_CFAR) - SAVE_8GPRS(14,r1) - SAVE_10GPRS(22,r1) - lhz r12,PACA_TRAP_SAVE(r13) - std r12,_TRAP(r1) - addi r11,r1,INT_FRAME_SIZE - std r11,0(r1) - li r12,0 - std r12,0(r11) - ld r2,PACATOC(r13) - ld r11,exception_marker@toc(r2) - std r12,RESULT(r1) - std r11,STACK_FRAME_OVERHEAD-16(r1) -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl kernel_bad_stack - b 1b - -/* * Here r13 points to the paca, r9 contains the saved CR, * SRR0 and SRR1 are saved in r11 and r12, * r9 - r13 are saved in paca->exgen. @@ -1057,7 +1025,7 @@ data_access_common: mfspr r10,SPRN_DSISR stw r10,PACA_EXGEN+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN) - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) ld r12,_MSR(r1) ld r3,PACA_EXGEN+EX_DAR(r13) lwz r4,PACA_EXGEN+EX_DSISR(r13) @@ -1073,7 +1041,7 @@ h_data_storage_common: stw r10,PACA_EXGEN+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) bl save_nvgprs - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl unknown_exception b ret_from_except @@ -1082,7 +1050,7 @@ h_data_storage_common: .globl instruction_access_common instruction_access_common: EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN) - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) ld r12,_MSR(r1) ld r3,_NIP(r1) andis. r4,r12,0x5820 @@ -1146,7 +1114,7 @@ slb_miss_fault: unrecov_user_slb: EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN) - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) bl save_nvgprs 1: addi r3,r1,STACK_FRAME_OVERHEAD bl unrecoverable_exception @@ -1169,7 +1137,7 @@ machine_check_common: stw r10,PACA_EXGEN+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) FINISH_NAP - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) ld r3,PACA_EXGEN+EX_DAR(r13) lwz r4,PACA_EXGEN+EX_DSISR(r13) std r3,_DAR(r1) @@ -1192,7 +1160,7 @@ alignment_common: std r3,_DAR(r1) std r4,_DSISR(r1) bl save_nvgprs - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl alignment_exception b ret_from_except @@ -1202,7 +1170,7 @@ alignment_common: program_check_common: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) bl save_nvgprs - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl program_check_exception b ret_from_except @@ -1213,7 +1181,7 @@ fp_unavailable_common: EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) bne 1f /* if from user, just load it up */ bl save_nvgprs - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl kernel_fp_unavailable_exception BUG_OPCODE @@ -1232,7 +1200,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ bl save_nvgprs - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl fp_unavailable_tm b ret_from_except @@ -1258,7 +1226,7 @@ BEGIN_FTR_SECTION #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ bl save_nvgprs - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl altivec_unavailable_tm b ret_from_except @@ -1267,7 +1235,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif bl save_nvgprs - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl altivec_unavailable_exception b ret_from_except @@ -1292,7 +1260,7 @@ BEGIN_FTR_SECTION #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ bl save_nvgprs - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl vsx_unavailable_tm b ret_from_except @@ -1301,7 +1269,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif bl save_nvgprs - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl vsx_unavailable_exception b ret_from_except @@ -1338,12 +1306,6 @@ fwnmi_data_area: . = 0x8000 #endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */ -/* Space for CPU0's segment table */ - .balign 4096 - .globl initial_stab -initial_stab: - .space 4096 - #ifdef CONFIG_PPC_POWERNV _GLOBAL(opal_mc_secondary_handler) HMT_MEDIUM_PPR_DISCARD @@ -1566,7 +1528,7 @@ slb_miss_realmode: unrecov_slb: EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) - DISABLE_INTS + RECONCILE_IRQ_STATE(r10, r11) bl save_nvgprs 1: addi r3,r1,STACK_FRAME_OVERHEAD bl unrecoverable_exception @@ -1594,12 +1556,6 @@ do_hash_page: bne- handle_page_fault /* if not, try to insert a HPTE */ andis. r0,r4,DSISR_DABRMATCH@h bne- handle_dabr_fault - -BEGIN_FTR_SECTION - andis. r0,r4,0x0020 /* Is it a segment table fault? */ - bne- do_ste_alloc /* If so handle it */ -END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) - CURRENT_THREAD_INFO(r11, r1) lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */ @@ -1681,113 +1637,62 @@ handle_dabr_fault: bl bad_page_fault b ret_from_except - /* here we have a segment miss */ -do_ste_alloc: - bl ste_allocate /* try to insert stab entry */ - cmpdi r3,0 - bne- handle_page_fault - b fast_exception_return - /* - * r13 points to the PACA, r9 contains the saved CR, + * Here we have detected that the kernel stack pointer is bad. + * R9 contains the saved CR, r13 points to the paca, + * r10 contains the (bad) kernel stack pointer, * r11 and r12 contain the saved SRR0 and SRR1. - * r9 - r13 are saved in paca->exslb. - * We assume we aren't going to take any exceptions during this procedure. - * We assume (DAR >> 60) == 0xc. + * We switch to using an emergency stack, save the registers there, + * and call kernel_bad_stack(), which panics. */ - .align 7 -do_stab_bolted: - stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ - std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */ - mfspr r11,SPRN_DAR /* ea */ - - /* - * check for bad kernel/user address - * (ea & ~REGION_MASK) >= PGTABLE_RANGE - */ - rldicr. r9,r11,4,(63 - 46 - 4) - li r9,0 /* VSID = 0 for bad address */ - bne- 0f - - /* - * Calculate VSID: - * This is the kernel vsid, we take the top for context from - * the range. context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 - * Here we know that (ea >> 60) == 0xc - */ - lis r9,(MAX_USER_CONTEXT + 1)@ha - addi r9,r9,(MAX_USER_CONTEXT + 1)@l - - srdi r10,r11,SID_SHIFT - rldimi r10,r9,ESID_BITS,0 /* proto vsid */ - ASM_VSID_SCRAMBLE(r10, r9, 256M) - rldic r9,r10,12,16 /* r9 = vsid << 12 */ - -0: - /* Hash to the primary group */ - ld r10,PACASTABVIRT(r13) - srdi r11,r11,SID_SHIFT - rldimi r10,r11,7,52 /* r10 = first ste of the group */ - - /* Search the primary group for a free entry */ -1: ld r11,0(r10) /* Test valid bit of the current ste */ - andi. r11,r11,0x80 - beq 2f - addi r10,r10,16 - andi. r11,r10,0x70 - bne 1b - - /* Stick for only searching the primary group for now. */ - /* At least for now, we use a very simple random castout scheme */ - /* Use the TB as a random number ; OR in 1 to avoid entry 0 */ - mftb r11 - rldic r11,r11,4,57 /* r11 = (r11 << 4) & 0x70 */ - ori r11,r11,0x10 - - /* r10 currently points to an ste one past the group of interest */ - /* make it point to the randomly selected entry */ - subi r10,r10,128 - or r10,r10,r11 /* r10 is the entry to invalidate */ - - isync /* mark the entry invalid */ - ld r11,0(r10) - rldicl r11,r11,56,1 /* clear the valid bit */ - rotldi r11,r11,8 - std r11,0(r10) - sync - - clrrdi r11,r11,28 /* Get the esid part of the ste */ - slbie r11 - -2: std r9,8(r10) /* Store the vsid part of the ste */ - eieio - - mfspr r11,SPRN_DAR /* Get the new esid */ - clrrdi r11,r11,28 /* Permits a full 32b of ESID */ - ori r11,r11,0x90 /* Turn on valid and kp */ - std r11,0(r10) /* Put new entry back into the stab */ - - sync - - /* All done -- return from exception. */ - lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ - ld r11,PACA_EXSLB+EX_SRR0(r13) /* get saved SRR0 */ - - andi. r10,r12,MSR_RI - beq- unrecov_slb - - mtcrf 0x80,r9 /* restore CR */ - - mfmsr r10 - clrrdi r10,r10,2 - mtmsrd r10,1 - - mtspr SPRN_SRR0,r11 - mtspr SPRN_SRR1,r12 - ld r9,PACA_EXSLB+EX_R9(r13) - ld r10,PACA_EXSLB+EX_R10(r13) - ld r11,PACA_EXSLB+EX_R11(r13) - ld r12,PACA_EXSLB+EX_R12(r13) - ld r13,PACA_EXSLB+EX_R13(r13) - rfid - b . /* prevent speculative execution */ +bad_stack: + ld r1,PACAEMERGSP(r13) + subi r1,r1,64+INT_FRAME_SIZE + std r9,_CCR(r1) + std r10,GPR1(r1) + std r11,_NIP(r1) + std r12,_MSR(r1) + mfspr r11,SPRN_DAR + mfspr r12,SPRN_DSISR + std r11,_DAR(r1) + std r12,_DSISR(r1) + mflr r10 + mfctr r11 + mfxer r12 + std r10,_LINK(r1) + std r11,_CTR(r1) + std r12,_XER(r1) + SAVE_GPR(0,r1) + SAVE_GPR(2,r1) + ld r10,EX_R3(r3) + std r10,GPR3(r1) + SAVE_GPR(4,r1) + SAVE_4GPRS(5,r1) + ld r9,EX_R9(r3) + ld r10,EX_R10(r3) + SAVE_2GPRS(9,r1) + ld r9,EX_R11(r3) + ld r10,EX_R12(r3) + ld r11,EX_R13(r3) + std r9,GPR11(r1) + std r10,GPR12(r1) + std r11,GPR13(r1) +BEGIN_FTR_SECTION + ld r10,EX_CFAR(r3) + std r10,ORIG_GPR3(r1) +END_FTR_SECTION_IFSET(CPU_FTR_CFAR) + SAVE_8GPRS(14,r1) + SAVE_10GPRS(22,r1) + lhz r12,PACA_TRAP_SAVE(r13) + std r12,_TRAP(r1) + addi r11,r1,INT_FRAME_SIZE + std r11,0(r1) + li r12,0 + std r12,0(r11) + ld r2,PACATOC(r13) + ld r11,exception_marker@toc(r2) + std r12,RESULT(r1) + std r11,STACK_FRAME_OVERHEAD-16(r1) +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl kernel_bad_stack + b 1b diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index f202d0731b06..390311c0f03d 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -10,6 +10,8 @@ * */ +#define pr_fmt(fmt) "ftrace-powerpc: " fmt + #include <linux/spinlock.h> #include <linux/hardirq.h> #include <linux/uaccess.h> @@ -105,7 +107,7 @@ __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { unsigned int op; - unsigned long ptr; + unsigned long entry, ptr; unsigned long ip = rec->ip; void *tramp; @@ -115,7 +117,7 @@ __ftrace_make_nop(struct module *mod, /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { - printk(KERN_ERR "Not expected bl: opcode is %x\n", op); + pr_err("Not expected bl: opcode is %x\n", op); return -EINVAL; } @@ -125,21 +127,21 @@ __ftrace_make_nop(struct module *mod, pr_devel("ip:%lx jumps to %p", ip, tramp); if (!is_module_trampoline(tramp)) { - printk(KERN_ERR "Not a trampoline\n"); + pr_err("Not a trampoline\n"); return -EINVAL; } if (module_trampoline_target(mod, tramp, &ptr)) { - printk(KERN_ERR "Failed to get trampoline target\n"); + pr_err("Failed to get trampoline target\n"); return -EFAULT; } pr_devel("trampoline target %lx", ptr); + entry = ppc_global_function_entry((void *)addr); /* This should match what was called */ - if (ptr != ppc_function_entry((void *)addr)) { - printk(KERN_ERR "addr %lx does not match expected %lx\n", - ptr, ppc_function_entry((void *)addr)); + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); return -EINVAL; } @@ -179,7 +181,7 @@ __ftrace_make_nop(struct module *mod, /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { - printk(KERN_ERR "Not expected bl: opcode is %x\n", op); + pr_err("Not expected bl: opcode is %x\n", op); return -EINVAL; } @@ -198,7 +200,7 @@ __ftrace_make_nop(struct module *mod, /* Find where the trampoline jumps to */ if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { - printk(KERN_ERR "Failed to read %lx\n", tramp); + pr_err("Failed to read %lx\n", tramp); return -EFAULT; } @@ -209,7 +211,7 @@ __ftrace_make_nop(struct module *mod, ((jmp[1] & 0xffff0000) != 0x398c0000) || (jmp[2] != 0x7d8903a6) || (jmp[3] != 0x4e800420)) { - printk(KERN_ERR "Not a trampoline\n"); + pr_err("Not a trampoline\n"); return -EINVAL; } @@ -221,8 +223,7 @@ __ftrace_make_nop(struct module *mod, pr_devel(" %lx ", tramp); if (tramp != addr) { - printk(KERN_ERR - "Trampoline location %08lx does not match addr\n", + pr_err("Trampoline location %08lx does not match addr\n", tramp); return -EINVAL; } @@ -263,15 +264,13 @@ int ftrace_make_nop(struct module *mod, */ if (!rec->arch.mod) { if (!mod) { - printk(KERN_ERR "No module loaded addr=%lx\n", - addr); + pr_err("No module loaded addr=%lx\n", addr); return -EFAULT; } rec->arch.mod = mod; } else if (mod) { if (mod != rec->arch.mod) { - printk(KERN_ERR - "Record mod %p not equal to passed in mod %p\n", + pr_err("Record mod %p not equal to passed in mod %p\n", rec->arch.mod, mod); return -EINVAL; } @@ -307,26 +306,25 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * The load offset is different depending on the ABI. For simplicity * just mask it out when doing the compare. */ - if ((op[0] != 0x48000008) || ((op[1] & 0xffff00000) != 0xe8410000)) { - printk(KERN_ERR "Unexpected call sequence: %x %x\n", - op[0], op[1]); + if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) { + pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]); return -EINVAL; } /* If we never set up a trampoline to ftrace_caller, then bail */ if (!rec->arch.mod->arch.tramp) { - printk(KERN_ERR "No ftrace trampoline\n"); + pr_err("No ftrace trampoline\n"); return -EINVAL; } /* Ensure branch is within 24 bits */ - if (create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { - printk(KERN_ERR "Branch out of range"); + if (!create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + pr_err("Branch out of range\n"); return -EINVAL; } if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { - printk(KERN_ERR "REL24 out of range!\n"); + pr_err("REL24 out of range!\n"); return -EINVAL; } @@ -345,13 +343,13 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) /* It should be pointing to a nop */ if (op != PPC_INST_NOP) { - printk(KERN_ERR "Expected NOP but have %x\n", op); + pr_err("Expected NOP but have %x\n", op); return -EINVAL; } /* If we never set up a trampoline to ftrace_caller, then bail */ if (!rec->arch.mod->arch.tramp) { - printk(KERN_ERR "No ftrace trampoline\n"); + pr_err("No ftrace trampoline\n"); return -EINVAL; } @@ -359,7 +357,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) op = create_branch((unsigned int *)ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK); if (!op) { - printk(KERN_ERR "REL24 out of range!\n"); + pr_err("REL24 out of range!\n"); return -EINVAL; } @@ -397,7 +395,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * already have a module defined. */ if (!rec->arch.mod) { - printk(KERN_ERR "No module loaded\n"); + pr_err("No module loaded\n"); return -EINVAL; } @@ -527,6 +525,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long)&return_to_handler; + if (unlikely(ftrace_graph_is_dead())) + return; + if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index a95145d7f61b..d48125d0c048 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -180,6 +180,28 @@ exception_marker: #include "exceptions-64s.S" #endif +#ifdef CONFIG_PPC_BOOK3E +_GLOBAL(fsl_secondary_thread_init) + /* Enable branch prediction */ + lis r3,BUCSR_INIT@h + ori r3,r3,BUCSR_INIT@l + mtspr SPRN_BUCSR,r3 + isync + + /* + * Fix PIR to match the linear numbering in the device tree. + * + * On e6500, the reset value of PIR uses the low three bits for + * the thread within a core, and the upper bits for the core + * number. There are two threads per core, so shift everything + * but the low bit right by two bits so that the cpu numbering is + * continuous. + */ + mfspr r3, SPRN_PIR + rlwimi r3, r3, 30, 2, 30 + mtspr SPRN_PIR, r3 +#endif + _GLOBAL(generic_secondary_thread_init) mr r24,r3 @@ -618,7 +640,7 @@ __secondary_start: addi r14,r14,THREAD_SIZE-STACK_FRAME_OVERHEAD std r14,PACAKSAVE(r13) - /* Do early setup for that CPU (stab, slb, hash table pointer) */ + /* Do early setup for that CPU (SLB and hash table pointer) */ bl early_setup_secondary /* @@ -771,8 +793,10 @@ start_here_multiplatform: li r0,0 stdu r0,-STACK_FRAME_OVERHEAD(r1) - /* Do very early kernel initializations, including initial hash table, - * stab and slb setup before we turn on relocation. */ + /* + * Do very early kernel initializations, including initial hash table + * and SLB setup before we turn on relocation. + */ /* Restore parameters passed from prom_init/kexec */ mr r3,r31 diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 2480256272d4..be05841396cf 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -131,21 +131,72 @@ _GLOBAL(power7_nap) _GLOBAL(power7_sleep) li r3,1 - li r4,0 + li r4,1 b power7_powersave_common /* No return */ +/* + * Make opal call in realmode. This is a generic function to be called + * from realmode from reset vector. It handles endianess. + * + * r13 - paca pointer + * r1 - stack pointer + * r3 - opal token + */ +opal_call_realmode: + mflr r12 + std r12,_LINK(r1) + ld r2,PACATOC(r13) + /* Set opal return address */ + LOAD_REG_ADDR(r0,return_from_opal_call) + mtlr r0 + /* Handle endian-ness */ + li r0,MSR_LE + mfmsr r12 + andc r12,r12,r0 + mtspr SPRN_HSRR1,r12 + mr r0,r3 /* Move opal token to r0 */ + LOAD_REG_ADDR(r11,opal) + ld r12,8(r11) + ld r2,0(r11) + mtspr SPRN_HSRR0,r12 + hrfid + +return_from_opal_call: + FIXUP_ENDIAN + ld r0,_LINK(r1) + mtlr r0 + blr + +#define CHECK_HMI_INTERRUPT \ + mfspr r0,SPRN_SRR1; \ +BEGIN_FTR_SECTION_NESTED(66); \ + rlwinm r0,r0,45-31,0xf; /* extract wake reason field (P8) */ \ +FTR_SECTION_ELSE_NESTED(66); \ + rlwinm r0,r0,45-31,0xe; /* P7 wake reason field is 3 bits */ \ +ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \ + cmpwi r0,0xa; /* Hypervisor maintenance ? */ \ + bne 20f; \ + /* Invoke opal call to handle hmi */ \ + ld r2,PACATOC(r13); \ + ld r1,PACAR1(r13); \ + std r3,ORIG_GPR3(r1); /* Save original r3 */ \ + li r3,OPAL_HANDLE_HMI; /* Pass opal token argument*/ \ + bl opal_call_realmode; \ + ld r3,ORIG_GPR3(r1); /* Restore original r3 */ \ +20: nop; + + _GLOBAL(power7_wakeup_tb_loss) ld r2,PACATOC(r13); ld r1,PACAR1(r13) +BEGIN_FTR_SECTION + CHECK_HMI_INTERRUPT +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) /* Time base re-sync */ - li r0,OPAL_RESYNC_TIMEBASE - LOAD_REG_ADDR(r11,opal); - ld r12,8(r11); - ld r2,0(r11); - mtctr r12 - bctrl + li r3,OPAL_RESYNC_TIMEBASE + bl opal_call_realmode; /* TODO: Check r3 for failure */ @@ -163,6 +214,9 @@ _GLOBAL(power7_wakeup_tb_loss) _GLOBAL(power7_wakeup_loss) ld r1,PACAR1(r13) +BEGIN_FTR_SECTION + CHECK_HMI_INTERRUPT +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) REST_NVGPRS(r1) REST_GPR(2, r1) ld r3,_CCR(r1) @@ -178,6 +232,9 @@ _GLOBAL(power7_wakeup_noloss) lbz r0,PACA_NAPSTATELOST(r13) cmpwi r0,0 bne power7_wakeup_loss +BEGIN_FTR_SECTION + CHECK_HMI_INTERRUPT +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) ld r1,PACAR1(r13) ld r4,_MSR(r1) ld r5,_NIP(r1) diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index b82227e7e21b..12e48d56f771 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -23,7 +23,7 @@ unsigned int ioread16(void __iomem *addr) } unsigned int ioread16be(void __iomem *addr) { - return in_be16(addr); + return readw_be(addr); } unsigned int ioread32(void __iomem *addr) { @@ -31,7 +31,7 @@ unsigned int ioread32(void __iomem *addr) } unsigned int ioread32be(void __iomem *addr) { - return in_be32(addr); + return readl_be(addr); } EXPORT_SYMBOL(ioread8); EXPORT_SYMBOL(ioread16); @@ -49,7 +49,7 @@ void iowrite16(u16 val, void __iomem *addr) } void iowrite16be(u16 val, void __iomem *addr) { - out_be16(addr, val); + writew_be(val, addr); } void iowrite32(u32 val, void __iomem *addr) { @@ -57,7 +57,7 @@ void iowrite32(u32 val, void __iomem *addr) } void iowrite32be(u32 val, void __iomem *addr) { - out_be32(addr, val); + writel_be(val, addr); } EXPORT_SYMBOL(iowrite8); EXPORT_SYMBOL(iowrite16); @@ -75,15 +75,15 @@ EXPORT_SYMBOL(iowrite32be); */ void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) { - _insb((u8 __iomem *) addr, dst, count); + readsb(addr, dst, count); } void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) { - _insw_ns((u16 __iomem *) addr, dst, count); + readsw(addr, dst, count); } void ioread32_rep(void __iomem *addr, void *dst, unsigned long count) { - _insl_ns((u32 __iomem *) addr, dst, count); + readsl(addr, dst, count); } EXPORT_SYMBOL(ioread8_rep); EXPORT_SYMBOL(ioread16_rep); @@ -91,15 +91,15 @@ EXPORT_SYMBOL(ioread32_rep); void iowrite8_rep(void __iomem *addr, const void *src, unsigned long count) { - _outsb((u8 __iomem *) addr, src, count); + writesb(addr, src, count); } void iowrite16_rep(void __iomem *addr, const void *src, unsigned long count) { - _outsw_ns((u16 __iomem *) addr, src, count); + writesw(addr, src, count); } void iowrite32_rep(void __iomem *addr, const void *src, unsigned long count) { - _outsl_ns((u32 __iomem *) addr, src, count); + writesl(addr, src, count); } EXPORT_SYMBOL(iowrite8_rep); EXPORT_SYMBOL(iowrite16_rep); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 88e3ec6e1d96..f84f799babb1 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1037,7 +1037,7 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry, /* if (unlikely(ret)) pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n", - __func__, hwaddr, entry << IOMMU_PAGE_SHIFT(tbl), + __func__, hwaddr, entry << tbl->it_page_shift, hwaddr, ret); */ return ret; @@ -1056,7 +1056,7 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, direction != DMA_TO_DEVICE, &page); if (unlikely(ret != 1)) { /* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n", - tce, entry << IOMMU_PAGE_SHIFT(tbl), ret); */ + tce, entry << tbl->it_page_shift, ret); */ return -EFAULT; } hwaddr = (unsigned long) page_address(page) + offset; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 248ee7e5bebd..4c5891de162e 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -189,6 +189,11 @@ notrace unsigned int __check_irq_replay(void) } #endif /* CONFIG_PPC_BOOK3E */ + /* Check if an hypervisor Maintenance interrupt happened */ + local_paca->irq_happened &= ~PACA_IRQ_HMI; + if (happened & PACA_IRQ_HMI) + return 0xe60; + /* There should be nothing left ! */ BUG_ON(local_paca->irq_happened != 0); @@ -377,6 +382,14 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions); seq_printf(p, " Machine check exceptions\n"); + if (cpu_has_feature(CPU_FTR_HVMODE)) { + seq_printf(p, "%*s: ", prec, "HMI"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + per_cpu(irq_stat, j).hmi_exceptions); + seq_printf(p, " Hypervisor Maintenance Interrupts\n"); + } + #ifdef CONFIG_PPC_DOORBELL if (cpu_has_feature(CPU_FTR_DBELL)) { seq_printf(p, "%*s: ", prec, "DBL"); @@ -400,6 +413,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += per_cpu(irq_stat, cpu).mce_exceptions; sum += per_cpu(irq_stat, cpu).spurious_irqs; sum += per_cpu(irq_stat, cpu).timer_irqs_others; + sum += per_cpu(irq_stat, cpu).hmi_exceptions; #ifdef CONFIG_PPC_DOORBELL sum += per_cpu(irq_stat, cpu).doorbell_irqs; #endif diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 90fab64d911d..2f72af82513c 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -32,6 +32,7 @@ #include <linux/module.h> #include <linux/kdebug.h> #include <linux/slab.h> +#include <asm/code-patching.h> #include <asm/cacheflush.h> #include <asm/sstep.h> #include <asm/uaccess.h> @@ -491,12 +492,10 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -#ifdef CONFIG_PPC64 unsigned long arch_deref_entry_point(void *entry) { - return ((func_descr_t *)entry)->entry; + return ppc_global_function_entry(entry); } -#endif int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { @@ -508,8 +507,12 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) /* setup return addr to the jprobe handler routine */ regs->nip = arch_deref_entry_point(jp->entry); #ifdef CONFIG_PPC64 +#if defined(_CALL_ELF) && _CALL_ELF == 2 + regs->gpr[12] = (unsigned long)jp->entry; +#else regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); #endif +#endif return 1; } diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 077d2ce6c5a7..d807ee626af9 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -315,8 +315,17 @@ static void dedotify_versions(struct modversion_info *vers, struct modversion_info *end; for (end = (void *)vers + size; vers < end; vers++) - if (vers->name[0] == '.') + if (vers->name[0] == '.') { memmove(vers->name, vers->name+1, strlen(vers->name)); +#ifdef ARCH_RELOCATES_KCRCTAB + /* The TOC symbol has no CRC computed. To avoid CRC + * check failing, we must force it to the expected + * value (see CRC check in module.c). + */ + if (!strcmp(vers->name, "TOC.")) + vers->crc = -(unsigned long)reloc_start; +#endif + } } /* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index b49c72fd7f16..b2814e23e1ed 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -123,21 +123,12 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus, void pcibios_reset_secondary_bus(struct pci_dev *dev) { - u16 ctrl; - if (ppc_md.pcibios_reset_secondary_bus) { ppc_md.pcibios_reset_secondary_bus(dev); return; } - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); - ctrl |= PCI_BRIDGE_CTL_BUS_RESET; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); - msleep(2); - - ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); - ssleep(1); + pci_reset_secondary_bus(dev); } static resource_size_t pcibios_io_size(const struct pci_controller *hose) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index be99774d3f44..bf44ae962ab8 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1095,6 +1095,23 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; } +static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) +{ +#ifdef CONFIG_PPC_STD_MMU_64 + unsigned long sp_vsid; + unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; + + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) + sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) + << SLB_VSID_SHIFT_1T; + else + sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_256M) + << SLB_VSID_SHIFT; + sp_vsid |= SLB_VSID_KERNEL | llp; + p->thread.ksp_vsid = sp_vsid; +#endif +} + /* * Copy a thread.. */ @@ -1174,21 +1191,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.vr_save_area = NULL; #endif -#ifdef CONFIG_PPC_STD_MMU_64 - if (mmu_has_feature(MMU_FTR_SLB)) { - unsigned long sp_vsid; - unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; + setup_ksp_vsid(p, sp); - if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) - sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) - << SLB_VSID_SHIFT_1T; - else - sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_256M) - << SLB_VSID_SHIFT; - sp_vsid |= SLB_VSID_KERNEL | llp; - p->thread.ksp_vsid = sp_vsid; - } -#endif /* CONFIG_PPC_STD_MMU_64 */ #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_DSCR)) { p->thread.dscr_inherit = current->thread.dscr_inherit; @@ -1577,7 +1581,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) struct pt_regs *regs = (struct pt_regs *) (sp + STACK_FRAME_OVERHEAD); lr = regs->link; - printk("--- Exception: %lx at %pS\n LR = %pS\n", + printk("--- interrupt: %lx at %pS\n LR = %pS\n", regs->trap, (void *)regs->nip, (void *)lr); firstframe = 1; } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 613a860a203c..1a3b1055f5eb 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -155,7 +155,6 @@ static struct ibm_pa_feature { } ibm_pa_features[] __initdata = { {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, {0, 0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, - {0, MMU_FTR_SLB, 0, 0, 2, 0}, {CPU_FTR_CTRL, 0, 0, 0, 3, 0}, {CPU_FTR_NOEXECUTE, 0, 0, 0, 6, 0}, {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1}, @@ -309,12 +308,10 @@ static int __init early_init_dt_scan_cpus(unsigned long node, /* Get physical cpuid */ intserv = of_get_flat_dt_prop(node, "ibm,ppc-interrupt-server#s", &len); - if (intserv) { - nthreads = len / sizeof(int); - } else { - intserv = of_get_flat_dt_prop(node, "reg", NULL); - nthreads = 1; - } + if (!intserv) + intserv = of_get_flat_dt_prop(node, "reg", &len); + + nthreads = len / sizeof(int); /* * Now see if any of these threads match our boot cpu. @@ -662,13 +659,6 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL); #endif - /* Pre-initialize the cmd_line with the content of boot_commmand_line, - * which will be empty except when the content of the variable has - * been overriden by a bootloading mechanism. This happens typically - * with HAL takeover - */ - strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE); - /* Retrieve various informations from the /chosen node of the * device-tree, including the platform type, initrd location and * size, TCE reserve, and more ... diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 078145acf7fb..1a85d8f96739 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1268,201 +1268,6 @@ static u64 __initdata prom_opal_base; static u64 __initdata prom_opal_entry; #endif -#ifdef __BIG_ENDIAN__ -/* XXX Don't change this structure without updating opal-takeover.S */ -static struct opal_secondary_data { - s64 ack; /* 0 */ - u64 go; /* 8 */ - struct opal_takeover_args args; /* 16 */ -} opal_secondary_data; - -static u64 __initdata prom_opal_align; -static u64 __initdata prom_opal_size; -static int __initdata prom_rtas_start_cpu; -static u64 __initdata prom_rtas_data; -static u64 __initdata prom_rtas_entry; - -extern char opal_secondary_entry; - -static void __init prom_query_opal(void) -{ - long rc; - - /* We must not query for OPAL presence on a machine that - * supports TNK takeover (970 blades), as this uses the same - * h-call with different arguments and will crash - */ - if (PHANDLE_VALID(call_prom("finddevice", 1, 1, - ADDR("/tnk-memory-map")))) { - prom_printf("TNK takeover detected, skipping OPAL check\n"); - return; - } - - prom_printf("Querying for OPAL presence... "); - - rc = opal_query_takeover(&prom_opal_size, - &prom_opal_align); - prom_debug("(rc = %ld) ", rc); - if (rc != 0) { - prom_printf("not there.\n"); - return; - } - of_platform = PLATFORM_OPAL; - prom_printf(" there !\n"); - prom_debug(" opal_size = 0x%lx\n", prom_opal_size); - prom_debug(" opal_align = 0x%lx\n", prom_opal_align); - if (prom_opal_align < 0x10000) - prom_opal_align = 0x10000; -} - -static int __init prom_rtas_call(int token, int nargs, int nret, - int *outputs, ...) -{ - struct rtas_args rtas_args; - va_list list; - int i; - - rtas_args.token = token; - rtas_args.nargs = nargs; - rtas_args.nret = nret; - rtas_args.rets = (rtas_arg_t *)&(rtas_args.args[nargs]); - va_start(list, outputs); - for (i = 0; i < nargs; ++i) - rtas_args.args[i] = va_arg(list, rtas_arg_t); - va_end(list); - - for (i = 0; i < nret; ++i) - rtas_args.rets[i] = 0; - - opal_enter_rtas(&rtas_args, prom_rtas_data, - prom_rtas_entry); - - if (nret > 1 && outputs != NULL) - for (i = 0; i < nret-1; ++i) - outputs[i] = rtas_args.rets[i+1]; - return (nret > 0)? rtas_args.rets[0]: 0; -} - -static void __init prom_opal_hold_cpus(void) -{ - int i, cnt, cpu, rc; - long j; - phandle node; - char type[64]; - u32 servers[8]; - void *entry = (unsigned long *)&opal_secondary_entry; - struct opal_secondary_data *data = &opal_secondary_data; - - prom_debug("prom_opal_hold_cpus: start...\n"); - prom_debug(" - entry = 0x%x\n", entry); - prom_debug(" - data = 0x%x\n", data); - - data->ack = -1; - data->go = 0; - - /* look for cpus */ - for (node = 0; prom_next_node(&node); ) { - type[0] = 0; - prom_getprop(node, "device_type", type, sizeof(type)); - if (strcmp(type, "cpu") != 0) - continue; - - /* Skip non-configured cpus. */ - if (prom_getprop(node, "status", type, sizeof(type)) > 0) - if (strcmp(type, "okay") != 0) - continue; - - cnt = prom_getprop(node, "ibm,ppc-interrupt-server#s", servers, - sizeof(servers)); - if (cnt == PROM_ERROR) - break; - cnt >>= 2; - for (i = 0; i < cnt; i++) { - cpu = servers[i]; - prom_debug("CPU %d ... ", cpu); - if (cpu == prom.cpu) { - prom_debug("booted !\n"); - continue; - } - prom_debug("starting ... "); - - /* Init the acknowledge var which will be reset by - * the secondary cpu when it awakens from its OF - * spinloop. - */ - data->ack = -1; - rc = prom_rtas_call(prom_rtas_start_cpu, 3, 1, - NULL, cpu, entry, data); - prom_debug("rtas rc=%d ...", rc); - - for (j = 0; j < 100000000 && data->ack == -1; j++) { - HMT_low(); - mb(); - } - HMT_medium(); - if (data->ack != -1) - prom_debug("done, PIR=0x%x\n", data->ack); - else - prom_debug("timeout !\n"); - } - } - prom_debug("prom_opal_hold_cpus: end...\n"); -} - -static void __init prom_opal_takeover(void) -{ - struct opal_secondary_data *data = &opal_secondary_data; - struct opal_takeover_args *args = &data->args; - u64 align = prom_opal_align; - u64 top_addr, opal_addr; - - args->k_image = (u64)_stext; - args->k_size = _end - _stext; - args->k_entry = 0; - args->k_entry2 = 0x60; - - top_addr = _ALIGN_UP(args->k_size, align); - - if (prom_initrd_start != 0) { - args->rd_image = prom_initrd_start; - args->rd_size = prom_initrd_end - args->rd_image; - args->rd_loc = top_addr; - top_addr = _ALIGN_UP(args->rd_loc + args->rd_size, align); - } - - /* Pickup an address for the HAL. We want to go really high - * up to avoid problem with future kexecs. On the other hand - * we don't want to be all over the TCEs on P5IOC2 machines - * which are going to be up there too. We assume the machine - * has plenty of memory, and we ask for the HAL for now to - * be just below the 1G point, or above the initrd - */ - opal_addr = _ALIGN_DOWN(0x40000000 - prom_opal_size, align); - if (opal_addr < top_addr) - opal_addr = top_addr; - args->hal_addr = opal_addr; - - /* Copy the command line to the kernel image */ - strlcpy(boot_command_line, prom_cmd_line, - COMMAND_LINE_SIZE); - - prom_debug(" k_image = 0x%lx\n", args->k_image); - prom_debug(" k_size = 0x%lx\n", args->k_size); - prom_debug(" k_entry = 0x%lx\n", args->k_entry); - prom_debug(" k_entry2 = 0x%lx\n", args->k_entry2); - prom_debug(" hal_addr = 0x%lx\n", args->hal_addr); - prom_debug(" rd_image = 0x%lx\n", args->rd_image); - prom_debug(" rd_size = 0x%lx\n", args->rd_size); - prom_debug(" rd_loc = 0x%lx\n", args->rd_loc); - prom_printf("Performing OPAL takeover,this can take a few minutes..\n"); - prom_close_stdin(); - mb(); - data->go = 1; - for (;;) - opal_do_takeover(args); -} -#endif /* __BIG_ENDIAN__ */ - /* * Allocate room for and instantiate OPAL */ @@ -1597,12 +1402,6 @@ static void __init prom_instantiate_rtas(void) &val, sizeof(val)) != PROM_ERROR) rtas_has_query_cpu_stopped = true; -#if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__) - /* PowerVN takeover hack */ - prom_rtas_data = base; - prom_rtas_entry = entry; - prom_getprop(rtas_node, "start-cpu", &prom_rtas_start_cpu, 4); -#endif prom_debug("rtas base = 0x%x\n", base); prom_debug("rtas entry = 0x%x\n", entry); prom_debug("rtas size = 0x%x\n", (long)size); @@ -3027,16 +2826,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, prom_instantiate_rtas(); #ifdef CONFIG_PPC_POWERNV -#ifdef __BIG_ENDIAN__ - /* Detect HAL and try instanciating it & doing takeover */ - if (of_platform == PLATFORM_PSERIES_LPAR) { - prom_query_opal(); - if (of_platform == PLATFORM_OPAL) { - prom_opal_hold_cpus(); - prom_opal_takeover(); - } - } else -#endif /* __BIG_ENDIAN__ */ if (of_platform == PLATFORM_OPAL) prom_instantiate_opal(); #endif /* CONFIG_PPC_POWERNV */ diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 77aa1e95e904..fe8e54b9ef7d 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -21,9 +21,7 @@ _end enter_prom memcpy memset reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224 reloc_got2 kernstart_addr memstart_addr linux_banner _stext -opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry -boot_command_line __prom_init_toc_start __prom_init_toc_end -btext_setup_display TOC." +__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC." NM="$1" OBJ="$2" diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 658e89d2025b..db2b482af658 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -611,17 +611,19 @@ static void rtas_flash_firmware(int reboot_type) for (f = flist; f; f = next) { /* Translate data addrs to absolute */ for (i = 0; i < f->num_blocks; i++) { - f->blocks[i].data = (char *)__pa(f->blocks[i].data); + f->blocks[i].data = (char *)cpu_to_be64(__pa(f->blocks[i].data)); image_size += f->blocks[i].length; + f->blocks[i].length = cpu_to_be64(f->blocks[i].length); } next = f->next; /* Don't translate NULL pointer for last entry */ if (f->next) - f->next = (struct flash_block_list *)__pa(f->next); + f->next = (struct flash_block_list *)cpu_to_be64(__pa(f->next)); else f->next = NULL; /* make num_blocks into the version/length field */ f->num_blocks = (FLASH_BLOCK_LIST_VERSION << 56) | ((f->num_blocks+1)*16); + f->num_blocks = cpu_to_be64(f->num_blocks); } printk(KERN_ALERT "FLASH: flash image is %ld bytes\n", image_size); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index e239df3768ac..1b0e26013a62 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -456,22 +456,32 @@ void __init smp_setup_cpu_maps(void) intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); if (intserv) { - nthreads = len / sizeof(int); DBG(" ibm,ppc-interrupt-server#s -> %d threads\n", nthreads); } else { DBG(" no ibm,ppc-interrupt-server#s -> 1 thread\n"); - intserv = of_get_property(dn, "reg", NULL); + intserv = of_get_property(dn, "reg", &len); if (!intserv) { cpu_be = cpu_to_be32(cpu); intserv = &cpu_be; /* assume logical == phys */ + len = 4; } } + nthreads = len / sizeof(int); + for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { + bool avail; + DBG(" thread %d -> cpu %d (hard id %d)\n", j, cpu, be32_to_cpu(intserv[j])); - set_cpu_present(cpu, of_device_is_available(dn)); + + avail = of_device_is_available(dn); + if (!avail) + avail = !of_property_match_string(dn, + "enable-method", "spin-table"); + + set_cpu_present(cpu, avail); set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j])); set_cpu_possible(cpu, true); cpu++; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index ee082d771178..75d62d63fe68 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -149,13 +149,13 @@ static void check_smt_enabled(void) else if (!strcmp(smt_enabled_cmdline, "off")) smt_enabled_at_boot = 0; else { - long smt; + int smt; int rc; - rc = strict_strtol(smt_enabled_cmdline, 10, &smt); + rc = kstrtoint(smt_enabled_cmdline, 10, &smt); if (!rc) smt_enabled_at_boot = - min(threads_per_core, (int)smt); + min(threads_per_core, smt); } } else { dn = of_find_node_by_path("/options"); @@ -201,7 +201,11 @@ static void cpu_ready_for_interrupts(void) /* Set IR and DR in PACA MSR */ get_paca()->kernel_msr = MSR_KERNEL; - /* Enable AIL if supported */ + /* + * Enable AIL if supported, and we are in hypervisor mode. If we are + * not in hypervisor mode, we enable relocation-on interrupts later + * in pSeries_setup_arch() using the H_SET_MODE hcall. + */ if (cpu_has_feature(CPU_FTR_HVMODE) && cpu_has_feature(CPU_FTR_ARCH_207S)) { unsigned long lpcr = mfspr(SPRN_LPCR); @@ -507,7 +511,11 @@ void __init setup_system(void) check_smt_enabled(); setup_tlb_core_data(); -#ifdef CONFIG_SMP + /* + * Freescale Book3e parts spin in a loop provided by firmware, + * so smp_release_cpus() does nothing for them + */ +#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_FSL_BOOK3E) /* Release secondary cpus out of their spinloops at 0x60 now that * we can map physical -> logical CPU ids */ @@ -673,9 +681,6 @@ void __init setup_arch(char **cmdline_p) exc_lvl_early_init(); emergency_stack_init(); -#ifdef CONFIG_PPC_STD_MMU_64 - stabs_alloc(); -#endif /* set up the bootmem stuff with available memory */ do_init_bootmem(); sparse_init(); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 1c794cef2883..cf8c7e4e0b21 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -31,20 +31,14 @@ int show_unhandled_signals = 1; /* * Allocate space for the signal frame */ -void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp, +void __user *get_sigframe(struct ksignal *ksig, unsigned long sp, size_t frame_size, int is_32) { unsigned long oldsp, newsp; /* Default to using normal stack */ oldsp = get_clean_sp(sp, is_32); - - /* Check for alt stack */ - if ((ka->sa.sa_flags & SA_ONSTACK) && - current->sas_ss_size && !on_sig_stack(oldsp)) - oldsp = (current->sas_ss_sp + current->sas_ss_size); - - /* Get aligned frame */ + oldsp = sigsp(oldsp, ksig); newsp = (oldsp - frame_size) & ~0xFUL; /* Check access */ @@ -105,25 +99,23 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, } } -static int do_signal(struct pt_regs *regs) +static void do_signal(struct pt_regs *regs) { sigset_t *oldset = sigmask_to_save(); - siginfo_t info; - int signr; - struct k_sigaction ka; + struct ksignal ksig; int ret; int is32 = is_32bit_task(); - signr = get_signal_to_deliver(&info, &ka, regs, NULL); + get_signal(&ksig); /* Is there any syscall restart business here ? */ - check_syscall_restart(regs, &ka, signr > 0); + check_syscall_restart(regs, &ksig.ka, ksig.sig > 0); - if (signr <= 0) { + if (ksig.sig <= 0) { /* No signal to deliver -- put the saved sigmask back */ restore_saved_sigmask(); regs->trap = 0; - return 0; /* no signals delivered */ + return; /* no signals delivered */ } #ifndef CONFIG_PPC_ADV_DEBUG_REGS @@ -140,23 +132,16 @@ static int do_signal(struct pt_regs *regs) thread_change_pc(current, regs); if (is32) { - if (ka.sa.sa_flags & SA_SIGINFO) - ret = handle_rt_signal32(signr, &ka, &info, oldset, - regs); + if (ksig.ka.sa.sa_flags & SA_SIGINFO) + ret = handle_rt_signal32(&ksig, oldset, regs); else - ret = handle_signal32(signr, &ka, &info, oldset, - regs); + ret = handle_signal32(&ksig, oldset, regs); } else { - ret = handle_rt_signal64(signr, &ka, &info, oldset, regs); + ret = handle_rt_signal64(&ksig, oldset, regs); } regs->trap = 0; - if (ret) { - signal_delivered(signr, &info, &ka, regs, - test_thread_flag(TIF_SINGLESTEP)); - } - - return ret; + signal_setup_done(ret, &ksig, test_thread_flag(TIF_SINGLESTEP)); } void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index c69b9aeb9f23..51b274199dd9 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -12,15 +12,13 @@ extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags); -extern void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp, +extern void __user *get_sigframe(struct ksignal *ksig, unsigned long sp, size_t frame_size, int is_32); -extern int handle_signal32(unsigned long sig, struct k_sigaction *ka, - siginfo_t *info, sigset_t *oldset, +extern int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs); -extern int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, - siginfo_t *info, sigset_t *oldset, +extern int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs); extern unsigned long copy_fpr_to_user(void __user *to, @@ -44,14 +42,12 @@ extern unsigned long copy_transact_vsx_from_user(struct task_struct *task, #ifdef CONFIG_PPC64 -extern int handle_rt_signal64(int signr, struct k_sigaction *ka, - siginfo_t *info, sigset_t *set, +extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs); #else /* CONFIG_PPC64 */ -static inline int handle_rt_signal64(int signr, struct k_sigaction *ka, - siginfo_t *info, sigset_t *set, +static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { return -EFAULT; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 4e47db686b5d..b171001698ff 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -54,7 +54,6 @@ #include "signal.h" -#undef DEBUG_SIG #ifdef CONFIG_PPC64 #define sys_rt_sigreturn compat_sys_rt_sigreturn @@ -982,9 +981,8 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) * Set up a signal frame for a "real-time" signal handler * (one which gets siginfo). */ -int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, - siginfo_t *info, sigset_t *oldset, - struct pt_regs *regs) +int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, + struct pt_regs *regs) { struct rt_sigframe __user *rt_sf; struct mcontext __user *frame; @@ -996,13 +994,13 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, /* Set up Signal Frame */ /* Put a Real Time Context onto stack */ - rt_sf = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*rt_sf), 1); + rt_sf = get_sigframe(ksig, get_tm_stackpointer(regs), sizeof(*rt_sf), 1); addr = rt_sf; if (unlikely(rt_sf == NULL)) goto badframe; /* Put the siginfo & fill in most of the ucontext */ - if (copy_siginfo_to_user(&rt_sf->info, info) + if (copy_siginfo_to_user(&rt_sf->info, &ksig->info) || __put_user(0, &rt_sf->uc.uc_flags) || __save_altstack(&rt_sf->uc.uc_stack, regs->gpr[1]) || __put_user(to_user_ptr(&rt_sf->uc.uc_mcontext), @@ -1052,21 +1050,17 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, /* Fill registers for signal handler */ regs->gpr[1] = newsp; - regs->gpr[3] = sig; + regs->gpr[3] = ksig->sig; regs->gpr[4] = (unsigned long) &rt_sf->info; regs->gpr[5] = (unsigned long) &rt_sf->uc; regs->gpr[6] = (unsigned long) rt_sf; - regs->nip = (unsigned long) ka->sa.sa_handler; + regs->nip = (unsigned long) ksig->ka.sa.sa_handler; /* enter the signal handler in native-endian mode */ regs->msr &= ~MSR_LE; regs->msr |= (MSR_KERNEL & MSR_LE); - return 1; + return 0; badframe: -#ifdef DEBUG_SIG - printk("badframe in handle_rt_signal, regs=%p frame=%p newsp=%lx\n", - regs, frame, newsp); -#endif if (show_unhandled_signals) printk_ratelimited(KERN_INFO "%s[%d]: bad frame in handle_rt_signal32: " @@ -1074,8 +1068,7 @@ badframe: current->comm, current->pid, addr, regs->nip, regs->link); - force_sigsegv(sig, current); - return 0; + return 1; } static int do_setcontext(struct ucontext __user *ucp, struct pt_regs *regs, int sig) @@ -1414,8 +1407,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx, /* * OK, we're invoking a handler */ -int handle_signal32(unsigned long sig, struct k_sigaction *ka, - siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) +int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs) { struct sigcontext __user *sc; struct sigframe __user *frame; @@ -1425,7 +1417,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, unsigned long tramp; /* Set up Signal Frame */ - frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 1); + frame = get_sigframe(ksig, get_tm_stackpointer(regs), sizeof(*frame), 1); if (unlikely(frame == NULL)) goto badframe; sc = (struct sigcontext __user *) &frame->sctx; @@ -1433,7 +1425,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, #if _NSIG != 64 #error "Please adjust handle_signal()" #endif - if (__put_user(to_user_ptr(ka->sa.sa_handler), &sc->handler) + if (__put_user(to_user_ptr(ksig->ka.sa.sa_handler), &sc->handler) || __put_user(oldset->sig[0], &sc->oldmask) #ifdef CONFIG_PPC64 || __put_user((oldset->sig[0] >> 32), &sc->_unused[3]) @@ -1441,7 +1433,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, || __put_user(oldset->sig[1], &sc->_unused[3]) #endif || __put_user(to_user_ptr(&frame->mctx), &sc->regs) - || __put_user(sig, &sc->signal)) + || __put_user(ksig->sig, &sc->signal)) goto badframe; if (vdso32_sigtramp && current->mm->context.vdso_base) { @@ -1476,18 +1468,14 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, goto badframe; regs->gpr[1] = newsp; - regs->gpr[3] = sig; + regs->gpr[3] = ksig->sig; regs->gpr[4] = (unsigned long) sc; - regs->nip = (unsigned long) ka->sa.sa_handler; + regs->nip = (unsigned long) (unsigned long)ksig->ka.sa.sa_handler; /* enter the signal handler in big-endian mode */ regs->msr &= ~MSR_LE; - return 1; + return 0; badframe: -#ifdef DEBUG_SIG - printk("badframe in handle_signal, regs=%p frame=%p newsp=%lx\n", - regs, frame, newsp); -#endif if (show_unhandled_signals) printk_ratelimited(KERN_INFO "%s[%d]: bad frame in handle_signal32: " @@ -1495,8 +1483,7 @@ badframe: current->comm, current->pid, frame, regs->nip, regs->link); - force_sigsegv(sig, current); - return 0; + return 1; } /* diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index d501dc4dc3e6..2cb0c94cafa5 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -38,7 +38,6 @@ #include "signal.h" -#define DEBUG_SIG 0 #define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs)) #define FP_REGS_SIZE sizeof(elf_fpregset_t) @@ -700,10 +699,6 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, return 0; badframe: -#if DEBUG_SIG - printk("badframe in sys_rt_sigreturn, regs=%p uc=%p &uc->uc_mcontext=%p\n", - regs, uc, &uc->uc_mcontext); -#endif if (show_unhandled_signals) printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, current->comm, current->pid, "rt_sigreturn", @@ -713,20 +708,19 @@ badframe: return 0; } -int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs *regs) +int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct rt_sigframe __user *frame; unsigned long newsp = 0; long err = 0; - frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 0); + frame = get_sigframe(ksig, get_tm_stackpointer(regs), sizeof(*frame), 0); if (unlikely(frame == NULL)) goto badframe; err |= __put_user(&frame->info, &frame->pinfo); err |= __put_user(&frame->uc, &frame->puc); - err |= copy_siginfo_to_user(&frame->info, info); + err |= copy_siginfo_to_user(&frame->info, &ksig->info); if (err) goto badframe; @@ -741,15 +735,15 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, err |= __put_user(&frame->uc_transact, &frame->uc.uc_link); err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext, &frame->uc_transact.uc_mcontext, - regs, signr, + regs, ksig->sig, NULL, - (unsigned long)ka->sa.sa_handler); + (unsigned long)ksig->ka.sa.sa_handler); } else #endif { err |= __put_user(0, &frame->uc.uc_link); - err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, signr, - NULL, (unsigned long)ka->sa.sa_handler, + err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, ksig->sig, + NULL, (unsigned long)ksig->ka.sa.sa_handler, 1); } err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); @@ -775,7 +769,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, /* Set up "regs" so we "return" to the signal handler. */ if (is_elf2_task()) { - regs->nip = (unsigned long) ka->sa.sa_handler; + regs->nip = (unsigned long) ksig->ka.sa.sa_handler; regs->gpr[12] = regs->nip; } else { /* Handler is *really* a pointer to the function descriptor for @@ -784,7 +778,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, * entry is the TOC value we need to use. */ func_descr_t __user *funct_desc_ptr = - (func_descr_t __user *) ka->sa.sa_handler; + (func_descr_t __user *) ksig->ka.sa.sa_handler; err |= get_user(regs->nip, &funct_desc_ptr->entry); err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); @@ -794,9 +788,9 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, regs->msr &= ~MSR_LE; regs->msr |= (MSR_KERNEL & MSR_LE); regs->gpr[1] = newsp; - regs->gpr[3] = signr; + regs->gpr[3] = ksig->sig; regs->result = 0; - if (ka->sa.sa_flags & SA_SIGINFO) { + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { err |= get_user(regs->gpr[4], (unsigned long __user *)&frame->pinfo); err |= get_user(regs->gpr[5], (unsigned long __user *)&frame->puc); regs->gpr[6] = (unsigned long) frame; @@ -806,18 +800,13 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, if (err) goto badframe; - return 1; + return 0; badframe: -#if DEBUG_SIG - printk("badframe in setup_rt_frame, regs=%p frame=%p newsp=%lx\n", - regs, frame, newsp); -#endif if (show_unhandled_signals) printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, current->comm, current->pid, "setup_rt_frame", (long)frame, regs->nip, regs->link); - force_sigsegv(signr, current); - return 0; + return 1; } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 51a3ff78838a..1007fb802e6b 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -747,7 +747,7 @@ int setup_profiling_timer(unsigned int multiplier) #ifdef CONFIG_SCHED_SMT /* cpumask of CPUs with asymetric SMT dependancy */ -static const int powerpc_smt_flags(void) +static int powerpc_smt_flags(void) { int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 895c50ca943c..7ab5d434e2ee 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -39,9 +39,6 @@ .section .rodata,"a" #ifdef CONFIG_PPC64 -#define sys_sigpending sys_ni_syscall -#define sys_old_getrlimit sys_ni_syscall - .p2align 3 #endif diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 9fff9cdcc519..368ab374d33c 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -741,7 +741,7 @@ static cycle_t timebase_read(struct clocksource *cs) } void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, - struct clocksource *clock, u32 mult) + struct clocksource *clock, u32 mult, cycle_t cycle_last) { u64 new_tb_to_xs, new_stamp_xsec; u32 frac_sec; @@ -774,7 +774,7 @@ void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, * We expect the caller to have done the first increment of * vdso_data->tb_update_count already. */ - vdso_data->tb_orig_stamp = clock->cycle_last; + vdso_data->tb_orig_stamp = cycle_last; vdso_data->stamp_xsec = new_stamp_xsec; vdso_data->tb_to_xs = new_tb_to_xs; vdso_data->wtom_clock_sec = wtm->tv_sec; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 239f1cde3fff..0dc43f9932cf 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -302,6 +302,16 @@ long machine_check_early(struct pt_regs *regs) return handled; } +long hmi_exception_realmode(struct pt_regs *regs) +{ + __get_cpu_var(irq_stat).hmi_exceptions++; + + if (ppc_md.hmi_exception_early) + ppc_md.hmi_exception_early(regs); + + return 0; +} + #endif /* @@ -609,7 +619,7 @@ int machine_check_e500(struct pt_regs *regs) if (reason & MCSR_BUS_RBERR) printk("Bus - Read Data Bus Error\n"); if (reason & MCSR_BUS_WBERR) - printk("Bus - Read Data Bus Error\n"); + printk("Bus - Write Data Bus Error\n"); if (reason & MCSR_BUS_IPERR) printk("Bus - Instruction Parity Error\n"); if (reason & MCSR_BUS_RPERR) @@ -738,6 +748,20 @@ void SMIException(struct pt_regs *regs) die("System Management Interrupt", regs, SIGABRT); } +void handle_hmi_exception(struct pt_regs *regs) +{ + struct pt_regs *old_regs; + + old_regs = set_irq_regs(regs); + irq_enter(); + + if (ppc_md.handle_hmi_exception) + ppc_md.handle_hmi_exception(regs); + + irq_exit(); + set_irq_regs(old_regs); +} + void unknown_exception(struct pt_regs *regs) { enum ctx_state prev_state = exception_enter(); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index ce74c335a6a4..f174351842cf 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -840,19 +840,3 @@ static int __init vdso_init(void) return 0; } arch_initcall(vdso_init); - -int in_gate_area_no_mm(unsigned long addr) -{ - return 0; -} - -int in_gate_area(struct mm_struct *mm, unsigned long addr) -{ - return 0; -} - -struct vm_area_struct *get_gate_vma(struct mm_struct *mm) -{ - return NULL; -} - diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 904c66128fae..5bfdab9047be 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -977,7 +977,7 @@ static ssize_t viodev_cmo_desired_set(struct device *dev, size_t new_desired; int ret; - ret = strict_strtoul(buf, 10, &new_desired); + ret = kstrtoul(buf, 10, &new_desired); if (ret) return ret; |
