diff options
Diffstat (limited to 'arch/powerpc')
33 files changed, 320 insertions, 167 deletions
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 84fdf68..a613d2c 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -200,10 +200,11 @@ static inline void __user *arch_compat_alloc_user_space(long len) /* * We can't access below the stack pointer in the 32bit ABI and - * can access 288 bytes in the 64bit ABI + * can access 288 bytes in the 64bit big-endian ABI, + * or 512 bytes with the new ELFv2 little-endian ABI. */ if (!is_32bit_task()) - usp -= 288; + usp -= USER_REDZONE_SIZE; return (void __user *) (usp - len); } diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index d3e5e9b..e37db7f 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -117,6 +117,16 @@ static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev) return edev ? edev->pdev : NULL; } +/* Return values from eeh_ops::next_error */ +enum { + EEH_NEXT_ERR_NONE = 0, + EEH_NEXT_ERR_INF, + EEH_NEXT_ERR_FROZEN_PE, + EEH_NEXT_ERR_FENCED_PHB, + EEH_NEXT_ERR_DEAD_PHB, + EEH_NEXT_ERR_DEAD_IOC +}; + /* * The struct is used to trace the registered EEH operation * callback functions. Actually, those operation callback diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index cca12f0..9cf9635 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -265,7 +265,7 @@ do_kvm_##n: \ subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */ \ beq- 1f; \ ld r1,PACAKSAVE(r13); /* kernel stack to use */ \ -1: cmpdi cr1,r1,0; /* check if r1 is in userspace */ \ +1: cmpdi cr1,r1,-INT_FRAME_SIZE; /* check if r1 is in userspace */ \ blt+ cr1,3f; /* abort if it is */ \ li r1,(n); /* will be reloaded later */ \ sth r1,PACA_TRAP_SAVE(r13); \ diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h index 27b2386..842846c 100644 --- a/arch/powerpc/include/asm/pgalloc-32.h +++ b/arch/powerpc/include/asm/pgalloc-32.h @@ -84,10 +84,8 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { - struct page *page = page_address(table); - tlb_flush_pgtable(tlb, address); - pgtable_page_dtor(page); - pgtable_free_tlb(tlb, page, 0); + pgtable_page_dtor(table); + pgtable_free_tlb(tlb, page_address(table), 0); } #endif /* _ASM_POWERPC_PGALLOC_32_H */ diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index f65e27b..256d6f8 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -144,11 +144,9 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { - struct page *page = page_address(table); - tlb_flush_pgtable(tlb, address); - pgtable_page_dtor(page); - pgtable_free_tlb(tlb, page, 0); + pgtable_page_dtor(table); + pgtable_free_tlb(tlb, page_address(table), 0); } #else /* if CONFIG_PPC_64K_PAGES */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 5995457..c2dcfaa 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -478,13 +478,6 @@ BEGIN_FTR_SECTION_NESTED(945) \ std ra,TASKTHREADPPR(rb); \ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,945) -#define RESTORE_PPR(ra, rb) \ -BEGIN_FTR_SECTION_NESTED(946) \ - ld ra,PACACURRENT(r13); \ - ld rb,TASKTHREADPPR(ra); \ - mtspr SPRN_PPR,rb; /* Restore PPR */ \ -END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,946) - #endif /* diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index becc08e..279b80f 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -28,11 +28,23 @@ #ifdef __powerpc64__ +/* + * Size of redzone that userspace is allowed to use below the stack + * pointer. This is 288 in the 64-bit big-endian ELF ABI, and 512 in + * the new ELFv2 little-endian ABI, so we allow the larger amount. + * + * For kernel code we allow a 288-byte redzone, in order to conserve + * kernel stack space; gcc currently only uses 288 bytes, and will + * hopefully allow explicit control of the redzone size in future. + */ +#define USER_REDZONE_SIZE 512 +#define KERNEL_REDZONE_SIZE 288 + #define STACK_FRAME_OVERHEAD 112 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 2 /* Location of LR in stack frame */ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265) #define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + \ - STACK_FRAME_OVERHEAD + 288) + STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE) #define STACK_FRAME_MARKER 12 /* Size of dummy stack frame allocated when calling signal handler. */ @@ -41,6 +53,8 @@ #else /* __powerpc64__ */ +#define USER_REDZONE_SIZE 0 +#define KERNEL_REDZONE_SIZE 0 #define STACK_FRAME_OVERHEAD 16 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 1 /* Location of LR in stack frame */ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 89e3ef2..d0b5fca 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -22,7 +22,15 @@ struct device_node; static inline int cpu_to_node(int cpu) { - return numa_cpu_lookup_table[cpu]; + int nid; + + nid = numa_cpu_lookup_table[cpu]; + + /* + * During early boot, the numa-cpu lookup table might not have been + * setup for all CPUs yet. In such cases, default to node 0. + */ + return (nid < 0) ? 0 : nid; } #define parent_node(node) (node) diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 6549327..bfb8236 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -794,6 +794,9 @@ static void remove_cache_dir(struct cache_dir *cache_dir) { remove_index_dirs(cache_dir); + /* Remove cache dir from sysfs */ + kobject_del(cache_dir->kobj); + kobject_put(cache_dir->kobj); kfree(cache_dir); diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 779a78c..c16ceb1 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -98,17 +98,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf) { void *vaddr; + phys_addr_t paddr; if (!csize) return 0; csize = min_t(size_t, csize, PAGE_SIZE); + paddr = pfn << PAGE_SHIFT; - if ((min_low_pfn < pfn) && (pfn < max_pfn)) { - vaddr = __va(pfn << PAGE_SHIFT); + if (memblock_is_region_memory(paddr, csize)) { + vaddr = __va(paddr); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); } else { - vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0); + vaddr = __ioremap(paddr, PAGE_SIZE, 0); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); iounmap(vaddr); } diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 55593ee..c766cf5 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -687,6 +687,15 @@ void eeh_save_bars(struct eeh_dev *edev) for (i = 0; i < 16; i++) eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]); + + /* + * For PCI bridges including root port, we need enable bus + * master explicitly. Otherwise, it can't fetch IODA table + * entries correctly. So we cache the bit in advance so that + * we can restore it after reset, either PHB range or PE range. + */ + if (edev->mode & EEH_DEV_BRIDGE) + edev->config_space[1] |= PCI_COMMAND_MASTER; } /** diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 36bed5a..d3a132c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -626,84 +626,90 @@ static void eeh_handle_special_event(void) { struct eeh_pe *pe, *phb_pe; struct pci_bus *bus; - struct pci_controller *hose, *tmp; + struct pci_controller *hose; unsigned long flags; - int rc = 0; + int rc; - /* - * The return value from next_error() has been classified as follows. - * It might be good to enumerate them. However, next_error() is only - * supported by PowerNV platform for now. So it would be fine to use - * integer directly: - * - * 4 - Dead IOC 3 - Dead PHB - * 2 - Fenced PHB 1 - Frozen PE - * 0 - No error found - * - */ - rc = eeh_ops->next_error(&pe); - if (rc <= 0) - return; - switch (rc) { - case 4: - /* Mark all PHBs in dead state */ - eeh_serialize_lock(&flags); - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe) continue; - - eeh_pe_state_mark(phb_pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + do { + rc = eeh_ops->next_error(&pe); + + switch (rc) { + case EEH_NEXT_ERR_DEAD_IOC: + /* Mark all PHBs in dead state */ + eeh_serialize_lock(&flags); + + /* Purge all events */ + eeh_remove_event(NULL); + + list_for_each_entry(hose, &hose_list, list_node) { + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe) continue; + + eeh_pe_state_mark(phb_pe, + EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + } + + eeh_serialize_unlock(flags); + + break; + case EEH_NEXT_ERR_FROZEN_PE: + case EEH_NEXT_ERR_FENCED_PHB: + case EEH_NEXT_ERR_DEAD_PHB: + /* Mark the PE in fenced state */ + eeh_serialize_lock(&flags); + + /* Purge all events of the PHB */ + eeh_remove_event(pe); + + if (rc == EEH_NEXT_ERR_DEAD_PHB) + eeh_pe_state_mark(pe, + EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); + else + eeh_pe_state_mark(pe, + EEH_PE_ISOLATED | EEH_PE_RECOVERING); + + eeh_serialize_unlock(flags); + + break; + case EEH_NEXT_ERR_NONE: + return; + default: + pr_warn("%s: Invalid value %d from next_error()\n", + __func__, rc); + return; } - eeh_serialize_unlock(flags); - - /* Purge all events */ - eeh_remove_event(NULL); - break; - case 3: - case 2: - case 1: - /* Mark the PE in fenced state */ - eeh_serialize_lock(&flags); - if (rc == 3) - eeh_pe_state_mark(pe, - EEH_PE_ISOLATED | EEH_PE_PHB_DEAD); - else - eeh_pe_state_mark(pe, - EEH_PE_ISOLATED | EEH_PE_RECOVERING); - eeh_serialize_unlock(flags); - - /* Purge all events of the PHB */ - eeh_remove_event(pe); - break; - default: - pr_err("%s: Invalid value %d from next_error()\n", - __func__, rc); - return; - } - /* - * For fenced PHB and frozen PE, it's handled as normal - * event. We have to remove the affected PHBs for dead - * PHB and IOC - */ - if (rc == 2 || rc == 1) - eeh_handle_normal_event(pe); - else { - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { - phb_pe = eeh_phb_pe_get(hose); - if (!phb_pe || !(phb_pe->state & EEH_PE_PHB_DEAD)) - continue; - - bus = eeh_pe_bus_get(phb_pe); - /* Notify all devices that they're about to go down. */ - eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); - pcibios_remove_pci_devices(bus); + /* + * For fenced PHB and frozen PE, it's handled as normal + * event. We have to remove the affected PHBs for dead + * PHB and IOC + */ + if (rc == EEH_NEXT_ERR_FROZEN_PE || + rc == EEH_NEXT_ERR_FENCED_PHB) { + eeh_handle_normal_event(pe); + } else { + list_for_each_entry(hose, &hose_list, list_node) { + phb_pe = eeh_phb_pe_get(hose); + if (!phb_pe || + !(phb_pe->state & EEH_PE_PHB_DEAD)) + continue; + + /* Notify all devices to be down */ + bus = eeh_pe_bus_get(phb_pe); + eeh_pe_dev_traverse(pe, + eeh_report_failure, NULL); + pcibios_remove_pci_devices(bus); + } } - } + + /* + * If we have detected dead IOC, we needn't proceed + * any more since all PHBs would have been removed + */ + if (rc == EEH_NEXT_ERR_DEAD_IOC) + break; + } while (rc != EEH_NEXT_ERR_NONE); } /** diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index c04cdf7..7be3717 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -820,6 +820,12 @@ fast_exception_return: andi. r0,r3,MSR_RI beq- unrecov_restore + /* Load PPR from thread struct before we clear MSR:RI */ +BEGIN_FTR_SECTION + ld r2,PACACURRENT(r13) + ld r2,TASKTHREADPPR(r2) +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + /* * Clear RI before restoring r13. If we are returning to * userspace and we take an exception after restoring r13, @@ -840,8 +846,10 @@ fast_exception_return: */ andi. r0,r3,MSR_PR beq 1f +BEGIN_FTR_SECTION + mtspr SPRN_PPR,r2 /* Restore PPR */ +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ACCOUNT_CPU_USER_EXIT(r2, r4) - RESTORE_PPR(r2, r4) REST_GPR(13, r1) 1: mtspr SPRN_SRR1,r3 diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index ccae7dd..6342268 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -482,6 +482,7 @@ _STATIC(__after_prom_start) mtctr r8 bctr +.balign 8 p_end: .llong _end - _stext 4: /* Now copy the rest of the kernel up to _end */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ec5ae55..681ae5b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -929,6 +929,15 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) flush_altivec_to_thread(src); flush_vsx_to_thread(src); flush_spe_to_thread(src); + /* + * Flush TM state out so we can copy it. __switch_to_tm() does this + * flush but it removes the checkpointed state from the current CPU and + * transitions the CPU out of TM mode. Hence we need to call + * tm_recheckpoint_new_task() (on the same task) to restore the + * checkpointed state back and the TM mode. + */ + __switch_to_tm(src); + tm_recheckpoint_new_task(src); *dst = *src; diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index b47a0e1..c712ece 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -81,6 +81,7 @@ _GLOBAL(relocate) 6: blr +.balign 8 p_dyn: .llong __dynamic_start - 0b p_rela: .llong __rela_dyn_start - 0b p_st: .llong _stext - 0b diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3f220d9..e143d03 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -445,6 +445,12 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, #endif /* CONFIG_ALTIVEC */ if (copy_fpr_to_user(&frame->mc_fregs, current)) return 1; + + /* + * Clear the MSR VSX bit to indicate there is no valid state attached + * to this context, except in the specific case below where we set it. + */ + msr &= ~MSR_VSX; #ifdef CONFIG_VSX /* * Copy VSR 0-31 upper half from thread_struct to local diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index f93ec28..36b1d1d 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -65,8 +65,8 @@ struct rt_sigframe { struct siginfo __user *pinfo; void __user *puc; struct siginfo info; - /* 64 bit ABI allows for 288 bytes below sp before decrementing it. */ - char abigap[288]; + /* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */ + char abigap[USER_REDZONE_SIZE]; } __attribute__ ((aligned (16))); static const char fmt32[] = KERN_INFO \ @@ -121,6 +121,12 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, flush_fp_to_thread(current); /* copy fpr regs and fpscr */ err |= copy_fpr_to_user(&sc->fp_regs, current); + + /* + * Clear the MSR VSX bit to indicate there is no valid state attached + * to this context, except in the specific case below where we set it. + */ + msr &= ~MSR_VSX; #ifdef CONFIG_VSX /* * Copy VSX low doubleword to local buffer for formatting, diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index e05b487..ea429ff 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -213,8 +213,6 @@ static u64 scan_dispatch_log(u64 stop_tb) if (i == be64_to_cpu(vpa->dtl_idx)) return 0; while (i < be64_to_cpu(vpa->dtl_idx)) { - if (dtl_consumer) - dtl_consumer(dtl, i); dtb = be64_to_cpu(dtl->timebase); tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + be32_to_cpu(dtl->ready_to_enqueue_time); @@ -227,6 +225,8 @@ static u64 scan_dispatch_log(u64 stop_tb) } if (dtb > stop_tb) break; + if (dtl_consumer) + dtl_consumer(dtl, i); stolen += tb_delta; ++i; ++dtl; diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index d38cc08..cb92d82 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1531,12 +1531,12 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, dn = dev->of_node; if (!dn) { - strcat(buf, "\n"); + strcpy(buf, "\n"); return strlen(buf); } cp = of_get_property(dn, "compatible", NULL); if (!cp) { - strcat(buf, "\n"); + strcpy(buf, "\n"); return strlen(buf); } diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 043eec8..46ff251 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -473,11 +473,14 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, slb_v = vcpu->kvm->arch.vrma_slb_v; } + preempt_disable(); /* Find the HPTE in the hash table */ index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v, HPTE_V_VALID | HPTE_V_ABSENT); - if (index < 0) + if (index < 0) { + preempt_enable(); return -ENOENT; + } hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4)); v = hptep[0] & ~HPTE_V_HVLOCK; gr = kvm->arch.revmap[index].guest_rpte; @@ -485,6 +488,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, /* Unlock the HPTE */ asm volatile("lwsync" : : : "memory"); hptep[0] = v; + preempt_enable(); gpte->eaddr = eaddr; gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 62a2b5a..e1ab62e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -82,10 +82,13 @@ void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) /* CPU points to the first thread of the core */ if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) { +#ifdef CONFIG_KVM_XICS int real_cpu = cpu + vcpu->arch.ptid; if (paca[real_cpu].kvm_hstate.xics_phys) xics_wake_cpu(real_cpu); - else if (cpu_online(cpu)) + else +#endif + if (cpu_online(cpu)) smp_send_reschedule(cpu); } put_cpu(); @@ -1089,7 +1092,9 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu) smp_wmb(); #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP) if (vcpu->arch.ptid) { +#ifdef CONFIG_KVM_XICS xics_wake_cpu(cpu); +#endif ++vc->n_woken; } #endif diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 9c51544..ea17b30 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -749,6 +749,10 @@ static int slb_base_page_shift[4] = { 20, /* 1M, unsupported */ }; +/* When called from virtmode, this func should be protected by + * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK + * can trigger deadlock issue. + */ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, unsigned long valid) { diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index 6d6f153..c17600d 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -127,7 +127,7 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500, } static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu, - unsigned int eaddr, int as) + gva_t eaddr, int as) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); unsigned int victim, tsized; diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c index 6936547..c5f734e 100644 --- a/arch/powerpc/mm/gup.c +++ b/arch/powerpc/mm/gup.c @@ -123,6 +123,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct mm_struct *mm = current->mm; unsigned long addr, len, end; unsigned long next; + unsigned long flags; pgd_t *pgdp; int nr = 0; @@ -156,7 +157,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, * So long as we atomically load page table pointers versus teardown, * we can follow the address down to the the page and take a ref on it. */ - local_irq_disable(); + local_irq_save(flags); pgdp = pgd_offset(mm, addr); do { @@ -179,7 +180,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, break; } while (pgdp++, addr = next, addr != end); - local_irq_enable(); + local_irq_restore(flags); return nr; } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index c916127..4788ea2 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -31,6 +31,8 @@ #include <asm/sparsemem.h> #include <asm/prom.h> #include <asm/smp.h> +#include <asm/cputhreads.h> +#include <asm/topology.h> #include <asm/firmware.h> #include <asm/paca.h> #include <asm/hvcall.h> @@ -152,9 +154,22 @@ static void __init get_node_active_region(unsigned long pfn, } } -static void map_cpu_to_node(int cpu, int node) +static void reset_numa_cpu_lookup_table(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + numa_cpu_lookup_table[cpu] = -1; +} + +static void update_numa_cpu_lookup_table(unsigned int cpu, int node) { numa_cpu_lookup_table[cpu] = node; +} + +static void map_cpu_to_node(int cpu, int node) +{ + update_numa_cpu_lookup_table(cpu, node); dbg("adding cpu %d to node %d\n", cpu, node); @@ -522,11 +537,24 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem, */ static int numa_setup_cpu(unsigned long lcpu) { - int nid = 0; - struct device_node *cpu = of_get_cpu_node(lcpu, NULL); + int nid; + struct device_node *cpu; + + /* + * If a valid cpu-to-node mapping is already available, use it + * directly instead of querying the firmware, since it represents + * the most recent mapping notified to us by the platform (eg: VPHN). + */ + if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) { + map_cpu_to_node(lcpu, nid); + return nid; + } + + cpu = of_get_cpu_node(lcpu, NULL); if (!cpu) { WARN_ON(1); + nid = 0; goto out; } @@ -1068,6 +1096,7 @@ void __init do_init_bootmem(void) */ setup_node_to_cpumask_map(); + reset_numa_cpu_lookup_table(); register_cpu_notifier(&ppc64_numa_nb); cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE, (void *)(unsigned long)boot_cpuid); @@ -1446,6 +1475,33 @@ static int update_cpu_topology(void *data) return 0; } +static int update_lookup_table(void *data) +{ + struct topology_update_data *update; + + if (!data) + return -EINVAL; + + /* + * Upon topology update, the numa-cpu lookup table needs to be updated + * for all threads in the core, including offline CPUs, to ensure that + * future hotplug operations respect the cpu-to-node associativity + * properly. + */ + for (update = data; update; update = update->next) { + int nid, base, j; + + nid = update->new_nid; + base = cpu_first_thread_sibling(update->cpu); + + for (j = 0; j < threads_per_core; j++) { + update_numa_cpu_lookup_table(base + j, nid); + } + } + + return 0; +} + /* * Update the node maps and sysfs entries for each cpu whose home node * has changed. Returns 1 when the topology has changed, and 0 otherwise. @@ -1514,6 +1570,14 @@ int arch_update_cpu_topology(void) stop_machine(update_cpu_topology, &updates[0], &updated_cpus); + /* + * Update the numa-cpu lookup table with the new mappings, even for + * offline CPUs. It is best to perform this update from the stop- + * machine context. + */ + stop_machine(update_lookup_table, &updates[0], + cpumask_of(raw_smp_processor_id())); + for (ud = &updates[0]; ud; ud = ud->next) { unregister_cpu_under_node(ud->cpu, ud->old_nid); register_cpu_under_node(ud->cpu, ud->new_nid); diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 3e99c14..7ce9cf3 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -258,7 +258,7 @@ static bool slice_scan_available(unsigned long addr, slice = GET_HIGH_SLICE_INDEX(addr); *boundary_addr = (slice + end) ? ((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP; - return !!(available.high_slices & (1u << slice)); + return !!(available.high_slices & (1ul << slice)); } } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 2345bdb..ebbb2f1 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -209,10 +209,11 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, } PPC_DIVWU(r_A, r_A, r_X); break; - case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */ + case BPF_S_ALU_DIV_K: /* A /= K */ + if (K == 1) + break; PPC_LI32(r_scratch1, K); - /* Top 32 bits of 64bit result -> A */ - PPC_MULHWU(r_A, r_A, r_scratch1); + PPC_DIVWU(r_A, r_A, r_scratch1); break; case BPF_S_ALU_AND_X: ctx->seen |= SEEN_XREG; diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index a82a41b..1a7b1d0 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -303,6 +303,9 @@ void __init mpc512x_setup_diu(void) diu_ops.release_bootmem = mpc512x_release_bootmem; } +#else +void __init mpc512x_setup_diu(void) { /* EMPTY */ } +void __init mpc512x_init_diu(void) { /* EMPTY */ } #endif void __init mpc512x_init_IRQ(void) diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index 90f4496..af54174 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -57,5 +57,5 @@ config PPC_MPC5200_BUGFIX config PPC_MPC5200_LPBFIFO tristate "MPC5200 LocalPlus bus FIFO driver" - depends on PPC_MPC52xx + depends on PPC_MPC52xx && PPC_BESTCOMM select PPC_BESTCOMM_GEN_BD diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index cf42e74..227c7fe 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -463,8 +463,7 @@ static int ioda_eeh_bridge_reset(struct pci_controller *hose, static int ioda_eeh_reset(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; - struct eeh_dev *edev; - struct pci_dev *dev; + struct pci_bus *bus; int ret; /* @@ -493,31 +492,11 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) if (pe->type & EEH_PE_PHB) { ret = ioda_eeh_phb_reset(hose, option); } else { - if (pe->type & EEH_PE_DEVICE) { - /* - * If it's device PE, we didn't refer to the parent - * PCI bus yet. So we have to figure it out indirectly. - */ - edev = list_first_entry(&pe->edevs, - struct eeh_dev, list); - dev = eeh_dev_to_pci_dev(edev); - dev = dev->bus->self; - } else { - /* - * If it's bus PE, the parent PCI bus is already there - * and just pick it up. - */ - dev = pe->bus->self; - } - - /* - * Do reset based on the fact that the direct upstream bridge - * is root bridge (port) or not. - */ - if (dev->bus->number == 0) + bus = eeh_pe_bus_get(pe); + if (pci_is_root_bus(bus)) ret = ioda_eeh_root_reset(hose, option); else - ret = ioda_eeh_bridge_reset(hose, dev, option); + ret = ioda_eeh_bridge_reset(hose, bus->self, option); } return ret; @@ -787,12 +766,12 @@ static int ioda_eeh_get_pe(struct pci_controller *hose, */ static int ioda_eeh_next_error(struct eeh_pe **pe) { - struct pci_controller *hose, *tmp; + struct pci_controller *hose; struct pnv_phb *phb; u64 frozen_pe_no; u16 err_type, severity; long rc; - int ret = 1; + int ret = EEH_NEXT_ERR_NONE; /* * While running here, it's safe to purge the event queue. @@ -802,7 +781,7 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) eeh_remove_event(NULL); opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + list_for_each_entry(hose, &hose_list, list_node) { /* * If the subordinate PCI buses of the PHB has been * removed, we needn't take care of it any more. @@ -841,19 +820,19 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) switch (err_type) { case OPAL_EEH_IOC_ERROR: if (severity == OPAL_EEH_SEV_IOC_DEAD) { - list_for_each_entry_safe(hose, tmp, - &hose_list, list_node) { + list_for_each_entry(hose, &hose_list, + list_node) { phb = hose->private_data; phb->eeh_state |= PNV_EEH_STATE_REMOVED; } pr_err("EEH: dead IOC detected\n"); - ret = 4; - goto out; + ret = EEH_NEXT_ERR_DEAD_IOC; } else if (severity == OPAL_EEH_SEV_INF) { pr_info("EEH: IOC informative error " "detected\n"); ioda_eeh_hub_diag(hose); + ret = EEH_NEXT_ERR_NONE; } break; @@ -865,21 +844,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) pr_err("EEH: dead PHB#%x detected\n", hose->global_number); phb->eeh_state |= PNV_EEH_STATE_REMOVED; - ret = 3; - goto out; + ret = EEH_NEXT_ERR_DEAD_PHB; } else if (severity == OPAL_EEH_SEV_PHB_FENCED) { if (ioda_eeh_get_phb_pe(hose, pe)) break; pr_err("EEH: fenced PHB#%x detected\n", hose->global_number); - ret = 2; - goto out; + ret = EEH_NEXT_ERR_FENCED_PHB; } else if (severity == OPAL_EEH_SEV_INF) { pr_info("EEH: PHB#%x informative error " "detected\n", hose->global_number); ioda_eeh_phb_diag(hose); + ret = EEH_NEXT_ERR_NONE; } break; @@ -889,13 +867,23 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) pr_err("EEH: Frozen PE#%x on PHB#%x detected\n", (*pe)->addr, (*pe)->phb->global_number); - ret = 1; - goto out; + ret = EEH_NEXT_ERR_FROZEN_PE; + break; + default: + pr_warn("%s: Unexpected error type %d\n", + __func__, err_type); } + + /* + * If we have no errors on the specific PHB or only + * informative error there, we continue poking it. + * Otherwise, we need actions to be taken by upper + * layer. + */ + if (ret > EEH_NEXT_ERR_INF) + break; } - ret = 0; -out: return ret; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 4daa288..50e67d2 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -153,13 +153,23 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) rid_end = pe->rid + 1; } - /* Associate PE in PELT */ + /* + * Associate PE in PELT. We need add the PE into the + * corresponding PELT-V as well. Otherwise, the error + * originated from the PE might contribute to other + * PEs. + */ rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid, bcomp, dcomp, fcomp, OPAL_MAP_PE); if (rc) { pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc); return -ENXIO; } + + rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number, + pe->pe_number, OPAL_ADD_PE_TO_DOMAIN); + if (rc) + pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc); opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 82789e7..0ea99e3 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -35,12 +35,7 @@ #include "offline_states.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 int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) = CPU_STATE_OFFLINE; @@ -93,15 +88,20 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args *args = &rtas_stop_self_args; + struct rtas_args args = { + .token = cpu_to_be32(rtas_stop_self_token), + .nargs = 0, + .nret = 1, + .rets = &args.args[0], + }; local_irq_disable(); - BUG_ON(args->token == RTAS_UNKNOWN_SERVICE); + BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); printk("cpu %u (hwid %u) Ready to die...\n", smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(args)); + enter_rtas(__pa(&args)); panic("Alas, I survived.\n"); } @@ -392,10 +392,10 @@ static int __init pseries_cpu_hotplug_init(void) } } - rtas_stop_self_args.token = rtas_token("stop-self"); + rtas_stop_self_token = rtas_token("stop-self"); qcss_tok = rtas_token("query-cpu-stopped-state"); - if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE || + if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE || qcss_tok == RTAS_UNKNOWN_SERVICE) { printk(KERN_INFO "CPU Hotplug not supported by firmware " "- disabling.\n"); |