diff options
Diffstat (limited to 'kernel/arch/powerpc')
41 files changed, 515 insertions, 368 deletions
diff --git a/kernel/arch/powerpc/boot/ps3-head.S b/kernel/arch/powerpc/boot/ps3-head.S index b6fcbaf50..3dc44b05f 100644 --- a/kernel/arch/powerpc/boot/ps3-head.S +++ b/kernel/arch/powerpc/boot/ps3-head.S @@ -57,11 +57,6 @@ __system_reset_overlay: bctr 1: - /* Save the value at addr zero for a null pointer write check later. */ - - li r4, 0 - lwz r3, 0(r4) - /* Primary delays then goes to _zimage_start in wrapper. */ or 31, 31, 31 /* db16cyc */ diff --git a/kernel/arch/powerpc/boot/ps3.c b/kernel/arch/powerpc/boot/ps3.c index 4ec2d86d3..a05558a7e 100644 --- a/kernel/arch/powerpc/boot/ps3.c +++ b/kernel/arch/powerpc/boot/ps3.c @@ -119,13 +119,12 @@ void ps3_copy_vectors(void) flush_cache((void *)0x100, 512); } -void platform_init(unsigned long null_check) +void platform_init(void) { const u32 heapsize = 0x1000000 - (u32)_end; /* 16MiB */ void *chosen; unsigned long ft_addr; u64 rm_size; - unsigned long val; console_ops.write = ps3_console_write; platform_ops.exit = ps3_exit; @@ -153,11 +152,6 @@ void platform_init(unsigned long null_check) printf(" flat tree at 0x%lx\n\r", ft_addr); - val = *(unsigned long *)0; - - if (val != null_check) - printf("null check failed: %lx != %lx\n\r", val, null_check); - ((kernel_entry_t)0)(ft_addr, 0, NULL); ps3_exit(); diff --git a/kernel/arch/powerpc/include/asm/icswx.h b/kernel/arch/powerpc/include/asm/icswx.h index 9f8402b35..27e588f6c 100644 --- a/kernel/arch/powerpc/include/asm/icswx.h +++ b/kernel/arch/powerpc/include/asm/icswx.h @@ -164,6 +164,7 @@ struct coprocessor_request_block { #define ICSWX_INITIATED (0x8) #define ICSWX_BUSY (0x4) #define ICSWX_REJECTED (0x2) +#define ICSWX_XERS0 (0x1) /* undefined or set from XERSO. */ static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb) { diff --git a/kernel/arch/powerpc/include/asm/kvm_host.h b/kernel/arch/powerpc/include/asm/kvm_host.h index f8673ff84..203765805 100644 --- a/kernel/arch/powerpc/include/asm/kvm_host.h +++ b/kernel/arch/powerpc/include/asm/kvm_host.h @@ -545,6 +545,7 @@ struct kvm_vcpu_arch { u64 tfiar; u32 cr_tm; + u64 xer_tm; u64 lr_tm; u64 ctr_tm; u64 amr_tm; diff --git a/kernel/arch/powerpc/include/asm/reg.h b/kernel/arch/powerpc/include/asm/reg.h index 2220f7a60..627d129d7 100644 --- a/kernel/arch/powerpc/include/asm/reg.h +++ b/kernel/arch/powerpc/include/asm/reg.h @@ -707,7 +707,8 @@ #define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 -#define SPRN_MMCR2 769 +#define SPRN_MMCR2 785 +#define SPRN_UMMCR2 769 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL @@ -744,13 +745,13 @@ #define SPRN_PMC6 792 #define SPRN_PMC7 793 #define SPRN_PMC8 794 -#define SPRN_SIAR 780 -#define SPRN_SDAR 781 #define SPRN_SIER 784 #define SIER_SIPR 0x2000000 /* Sampled MSR_PR */ #define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ #define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ #define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ +#define SPRN_SIAR 796 +#define SPRN_SDAR 797 #define SPRN_TACR 888 #define SPRN_TCSCR 889 #define SPRN_CSIGR 890 diff --git a/kernel/arch/powerpc/include/asm/uaccess.h b/kernel/arch/powerpc/include/asm/uaccess.h index 2a8ebae09..a5ffe0207 100644 --- a/kernel/arch/powerpc/include/asm/uaccess.h +++ b/kernel/arch/powerpc/include/asm/uaccess.h @@ -323,30 +323,17 @@ extern unsigned long __copy_tofrom_user(void __user *to, static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { - unsigned long over; - - if (access_ok(VERIFY_READ, from, n)) + if (likely(access_ok(VERIFY_READ, from, n))) return __copy_tofrom_user((__force void __user *)to, from, n); - if ((unsigned long)from < TASK_SIZE) { - over = (unsigned long)from + n - TASK_SIZE; - return __copy_tofrom_user((__force void __user *)to, from, - n - over) + over; - } + memset(to, 0, n); return n; } static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n) { - unsigned long over; - if (access_ok(VERIFY_WRITE, to, n)) return __copy_tofrom_user(to, (__force void __user *)from, n); - if ((unsigned long)to < TASK_SIZE) { - over = (unsigned long)to + n - TASK_SIZE; - return __copy_tofrom_user(to, (__force void __user *)from, - n - over) + over; - } return n; } @@ -437,10 +424,6 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size) might_fault(); if (likely(access_ok(VERIFY_WRITE, addr, size))) return __clear_user(addr, size); - if ((unsigned long)addr < TASK_SIZE) { - unsigned long over = (unsigned long)addr + size - TASK_SIZE; - return __clear_user(addr, size - over) + over; - } return size; } diff --git a/kernel/arch/powerpc/include/asm/word-at-a-time.h b/kernel/arch/powerpc/include/asm/word-at-a-time.h index e4396a7d0..4afe66aa1 100644 --- a/kernel/arch/powerpc/include/asm/word-at-a-time.h +++ b/kernel/arch/powerpc/include/asm/word-at-a-time.h @@ -82,7 +82,7 @@ static inline unsigned long create_zero_mask(unsigned long bits) "andc %1,%1,%2\n\t" "popcntd %0,%1" : "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask) - : "r" (bits)); + : "b" (bits)); return leading_zero_bits; } diff --git a/kernel/arch/powerpc/include/uapi/asm/cputable.h b/kernel/arch/powerpc/include/uapi/asm/cputable.h index 43686043e..2734c005d 100644 --- a/kernel/arch/powerpc/include/uapi/asm/cputable.h +++ b/kernel/arch/powerpc/include/uapi/asm/cputable.h @@ -31,6 +31,7 @@ #define PPC_FEATURE_PSERIES_PERFMON_COMPAT \ 0x00000040 +/* Reserved - do not use 0x00000004 */ #define PPC_FEATURE_TRUE_LE 0x00000002 #define PPC_FEATURE_PPC_LE 0x00000001 diff --git a/kernel/arch/powerpc/include/uapi/asm/kvm.h b/kernel/arch/powerpc/include/uapi/asm/kvm.h index ab4d4732c..720b71a63 100644 --- a/kernel/arch/powerpc/include/uapi/asm/kvm.h +++ b/kernel/arch/powerpc/include/uapi/asm/kvm.h @@ -587,6 +587,7 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67) #define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68) #define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69) +#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a) /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ diff --git a/kernel/arch/powerpc/kernel/asm-offsets.c b/kernel/arch/powerpc/kernel/asm-offsets.c index d6d0c59ef..bd0408153 100644 --- a/kernel/arch/powerpc/kernel/asm-offsets.c +++ b/kernel/arch/powerpc/kernel/asm-offsets.c @@ -585,6 +585,7 @@ int main(void) DEFINE(VCPU_VRS_TM, offsetof(struct kvm_vcpu, arch.vr_tm.vr)); DEFINE(VCPU_VRSAVE_TM, offsetof(struct kvm_vcpu, arch.vrsave_tm)); DEFINE(VCPU_CR_TM, offsetof(struct kvm_vcpu, arch.cr_tm)); + DEFINE(VCPU_XER_TM, offsetof(struct kvm_vcpu, arch.xer_tm)); DEFINE(VCPU_LR_TM, offsetof(struct kvm_vcpu, arch.lr_tm)); DEFINE(VCPU_CTR_TM, offsetof(struct kvm_vcpu, arch.ctr_tm)); DEFINE(VCPU_AMR_TM, offsetof(struct kvm_vcpu, arch.amr_tm)); diff --git a/kernel/arch/powerpc/kernel/eeh.c b/kernel/arch/powerpc/kernel/eeh.c index 40e4d4a27..98949b0df 100644 --- a/kernel/arch/powerpc/kernel/eeh.c +++ b/kernel/arch/powerpc/kernel/eeh.c @@ -677,7 +677,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function) /* Check if the request is finished successfully */ if (active_flag) { rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if (rc <= 0) + if (rc < 0) return rc; if (rc & active_flag) @@ -1072,7 +1072,7 @@ void eeh_add_device_early(struct pci_dn *pdn) struct pci_controller *phb; struct eeh_dev *edev = pdn_to_eeh_dev(pdn); - if (!edev || !eeh_enabled()) + if (!edev) return; if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) diff --git a/kernel/arch/powerpc/kernel/eeh_driver.c b/kernel/arch/powerpc/kernel/eeh_driver.c index 52c1e273f..c314db8b7 100644 --- a/kernel/arch/powerpc/kernel/eeh_driver.c +++ b/kernel/arch/powerpc/kernel/eeh_driver.c @@ -166,6 +166,16 @@ static void *eeh_dev_save_state(void *data, void *userdata) if (!edev) return NULL; + /* + * We cannot access the config space on some adapters. + * Otherwise, it will cause fenced PHB. We don't save + * the content in their config space and will restore + * from the initial config space saved when the EEH + * device is created. + */ + if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) + return NULL; + pdev = eeh_dev_to_pci_dev(edev); if (!pdev) return NULL; @@ -305,6 +315,19 @@ static void *eeh_dev_restore_state(void *data, void *userdata) if (!edev) return NULL; + /* + * The content in the config space isn't saved because + * the blocked config space on some adapters. We have + * to restore the initial saved config space when the + * EEH device is created. + */ + if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) { + if (list_is_last(&edev->list, &edev->pe->edevs)) + eeh_pe_restore_bars(edev->pe); + + return NULL; + } + pdev = eeh_dev_to_pci_dev(edev); if (!pdev) return NULL; @@ -462,7 +485,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) static void *__eeh_clear_pe_frozen_state(void *data, void *flag) { struct eeh_pe *pe = (struct eeh_pe *)data; - bool *clear_sw_state = flag; + bool clear_sw_state = *(bool *)flag; int i, rc = 1; for (i = 0; rc && i < 3; i++) @@ -504,9 +527,6 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) /* Save states */ eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL); - /* Report error */ - eeh_pe_dev_traverse(pe, eeh_report_error, &result); - /* Issue reset */ ret = eeh_reset_pe(pe); if (ret) { @@ -592,8 +612,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) /* Clear frozen state */ rc = eeh_clear_pe_frozen_state(pe, false); - if (rc) + if (rc) { + pci_unlock_rescan_remove(); return rc; + } /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, @@ -889,6 +911,14 @@ static void eeh_handle_special_event(void) /* Notify all devices to be down */ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); bus = eeh_pe_bus_get(phb_pe); + if (!bus) { + pr_err("%s: Cannot find PCI bus for " + "PHB#%d-PE#%x\n", + __func__, + pe->phb->global_number, + pe->addr); + break; + } eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); pcibios_remove_pci_devices(bus); diff --git a/kernel/arch/powerpc/kernel/entry_64.S b/kernel/arch/powerpc/kernel/entry_64.S index 5bb3148e5..1aae3fdb0 100644 --- a/kernel/arch/powerpc/kernel/entry_64.S +++ b/kernel/arch/powerpc/kernel/entry_64.S @@ -334,13 +334,13 @@ syscall_exit_work: tabort_syscall: /* Firstly we need to enable TM in the kernel */ mfmsr r10 - li r13, 1 - rldimi r10, r13, MSR_TM_LG, 63-MSR_TM_LG + li r9, 1 + rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG mtmsrd r10, 0 /* tabort, this dooms the transaction, nothing else */ - li r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) - TABORT(R13) + li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) + TABORT(R9) /* * Return directly to userspace. We have corrupted user register state, @@ -348,8 +348,8 @@ tabort_syscall: * resume after the tbegin of the aborted transaction with the * checkpointed register state. */ - li r13, MSR_RI - andc r10, r10, r13 + li r9, MSR_RI + andc r10, r10, r9 mtmsrd r10, 1 mtspr SPRN_SRR0, r11 mtspr SPRN_SRR1, r12 diff --git a/kernel/arch/powerpc/kernel/exceptions-64s.S b/kernel/arch/powerpc/kernel/exceptions-64s.S index 0a0399c2a..b81ccc5fb 100644 --- a/kernel/arch/powerpc/kernel/exceptions-64s.S +++ b/kernel/arch/powerpc/kernel/exceptions-64s.S @@ -962,11 +962,6 @@ hv_facility_unavailable_relon_trampoline: #endif STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist) - /* Other future vectors */ - .align 7 - .globl __end_interrupts -__end_interrupts: - .align 7 system_call_entry: b system_call_common @@ -1253,6 +1248,17 @@ __end_handlers: STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable) + /* + * The __end_interrupts marker must be past the out-of-line (OOL) + * handlers, so that they are copied to real address 0x100 when running + * a relocatable kernel. This ensures they can be reached from the short + * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch + * directly, without using LOAD_HANDLER(). + */ + .align 7 + .globl __end_interrupts +__end_interrupts: + #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * Data area reserved for FWNMI option. diff --git a/kernel/arch/powerpc/kernel/ibmebus.c b/kernel/arch/powerpc/kernel/ibmebus.c index ac86c53e2..e524a775f 100644 --- a/kernel/arch/powerpc/kernel/ibmebus.c +++ b/kernel/arch/powerpc/kernel/ibmebus.c @@ -180,6 +180,7 @@ static int ibmebus_create_device(struct device_node *dn) static int ibmebus_create_devices(const struct of_device_id *matches) { struct device_node *root, *child; + struct device *dev; int ret = 0; root = of_find_node_by_path("/"); @@ -188,9 +189,12 @@ static int ibmebus_create_devices(const struct of_device_id *matches) if (!of_match_node(matches, child)) continue; - if (bus_find_device(&ibmebus_bus_type, NULL, child, - ibmebus_match_node)) + dev = bus_find_device(&ibmebus_bus_type, NULL, child, + ibmebus_match_node); + if (dev) { + put_device(dev); continue; + } ret = ibmebus_create_device(child); if (ret) { @@ -262,6 +266,7 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus, const char *buf, size_t count) { struct device_node *dn = NULL; + struct device *dev; char *path; ssize_t rc = 0; @@ -269,8 +274,10 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus, if (!path) return -ENOMEM; - if (bus_find_device(&ibmebus_bus_type, NULL, path, - ibmebus_match_path)) { + dev = bus_find_device(&ibmebus_bus_type, NULL, path, + ibmebus_match_path); + if (dev) { + put_device(dev); printk(KERN_WARNING "%s: %s has already been probed\n", __func__, path); rc = -EEXIST; @@ -307,6 +314,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus, if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path, ibmebus_match_path))) { of_device_unregister(to_platform_device(dev)); + put_device(dev); kfree(path); return count; diff --git a/kernel/arch/powerpc/kernel/idle_power7.S b/kernel/arch/powerpc/kernel/idle_power7.S index 112ccf497..73f638789 100644 --- a/kernel/arch/powerpc/kernel/idle_power7.S +++ b/kernel/arch/powerpc/kernel/idle_power7.S @@ -44,7 +44,7 @@ std r0,0(r1); \ ptesync; \ ld r0,0(r1); \ -1: cmp cr0,r0,r0; \ +1: cmpd cr0,r0,r0; \ bne 1b; \ IDLE_INST; \ b . diff --git a/kernel/arch/powerpc/kernel/misc_32.S b/kernel/arch/powerpc/kernel/misc_32.S index 8b261416c..9cb0c2f6e 100644 --- a/kernel/arch/powerpc/kernel/misc_32.S +++ b/kernel/arch/powerpc/kernel/misc_32.S @@ -315,7 +315,7 @@ _GLOBAL(flush_instruction_cache) lis r3, KERNELBASE@h iccci 0,r3 #endif -#elif CONFIG_FSL_BOOKE +#elif defined(CONFIG_FSL_BOOKE) BEGIN_FTR_SECTION mfspr r3,SPRN_L1CSR0 ori r3,r3,L1CSR0_CFI|L1CSR0_CLFC diff --git a/kernel/arch/powerpc/kernel/nvram_64.c b/kernel/arch/powerpc/kernel/nvram_64.c index 32e26526f..1eb698f65 100644 --- a/kernel/arch/powerpc/kernel/nvram_64.c +++ b/kernel/arch/powerpc/kernel/nvram_64.c @@ -969,7 +969,7 @@ int __init nvram_remove_partition(const char *name, int sig, /* Make partition a free partition */ part->header.signature = NVRAM_SIG_FREE; - strncpy(part->header.name, "wwwwwwwwwwww", 12); + memset(part->header.name, 'w', 12); part->header.checksum = nvram_checksum(&part->header); rc = nvram_write_header(part); if (rc <= 0) { @@ -987,8 +987,8 @@ int __init nvram_remove_partition(const char *name, int sig, } if (prev) { prev->header.length += part->header.length; - prev->header.checksum = nvram_checksum(&part->header); - rc = nvram_write_header(part); + prev->header.checksum = nvram_checksum(&prev->header); + rc = nvram_write_header(prev); if (rc <= 0) { printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc); return rc; diff --git a/kernel/arch/powerpc/kernel/process.c b/kernel/arch/powerpc/kernel/process.c index ef2ad2d68..cf788d7d7 100644 --- a/kernel/arch/powerpc/kernel/process.c +++ b/kernel/arch/powerpc/kernel/process.c @@ -569,24 +569,6 @@ static void tm_reclaim_thread(struct thread_struct *thr, if (!MSR_TM_SUSPENDED(mfmsr())) return; - /* - * Use the current MSR TM suspended bit to track if we have - * checkpointed state outstanding. - * On signal delivery, we'd normally reclaim the checkpointed - * state to obtain stack pointer (see:get_tm_stackpointer()). - * This will then directly return to userspace without going - * through __switch_to(). However, if the stack frame is bad, - * we need to exit this thread which calls __switch_to() which - * will again attempt to reclaim the already saved tm state. - * Hence we need to check that we've not already reclaimed - * this state. - * We do this using the current MSR, rather tracking it in - * some specific thread_struct bit, as it has the additional - * benifit of checking for a potential TM bad thing exception. - */ - if (!MSR_TM_SUSPENDED(mfmsr())) - return; - tm_reclaim(thr, thr->regs->msr, cause); /* Having done the reclaim, we now have the checkpointed @@ -1257,6 +1239,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.regs = regs - 1; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Clear any transactional state, we're exec()ing. The cause is + * not important as there will never be a recheckpoint so it's not + * user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); +#endif + memset(regs->gpr, 0, sizeof(regs->gpr)); regs->ctr = 0; regs->link = 0; diff --git a/kernel/arch/powerpc/kernel/prom.c b/kernel/arch/powerpc/kernel/prom.c index 7030b0359..a15fe1d4e 100644 --- a/kernel/arch/powerpc/kernel/prom.c +++ b/kernel/arch/powerpc/kernel/prom.c @@ -148,23 +148,25 @@ static struct ibm_pa_feature { unsigned long cpu_features; /* CPU_FTR_xxx bit */ unsigned long mmu_features; /* MMU_FTR_xxx bit */ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ + unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */ unsigned char pabyte; /* byte number in ibm,pa-features */ unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ } ibm_pa_features[] __initdata = { - {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, - {0, 0, PPC_FEATURE_HAS_FPU, 0, 1, 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}, - {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, - {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, + {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0, 0}, + {0, 0, PPC_FEATURE_HAS_FPU, 0, 0, 1, 0}, + {CPU_FTR_CTRL, 0, 0, 0, 0, 3, 0}, + {CPU_FTR_NOEXECUTE, 0, 0, 0, 0, 6, 0}, + {CPU_FTR_NODSISRALIGN, 0, 0, 0, 1, 1, 1}, + {0, MMU_FTR_CI_LARGE_PAGE, 0, 0, 1, 2, 0}, + {CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0}, /* - * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n), - * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP - * which is 0 if the kernel doesn't support TM. + * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n), + * we don't want to turn on TM here, so we use the *_COMP versions + * which are 0 if the kernel doesn't support TM. */ - {CPU_FTR_TM_COMP, 0, 0, 22, 0, 0}, + {CPU_FTR_TM_COMP, 0, 0, + PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -195,10 +197,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs, if (bit ^ fp->invert) { cur_cpu_spec->cpu_features |= fp->cpu_features; cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features |= fp->mmu_features; } else { cur_cpu_spec->cpu_features &= ~fp->cpu_features; cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features &= ~fp->mmu_features; } } diff --git a/kernel/arch/powerpc/kernel/prom_init.c b/kernel/arch/powerpc/kernel/prom_init.c index 92dea8df6..313953364 100644 --- a/kernel/arch/powerpc/kernel/prom_init.c +++ b/kernel/arch/powerpc/kernel/prom_init.c @@ -655,6 +655,7 @@ unsigned char ibm_architecture_vec[] = { W(0xffff0000), W(0x003e0000), /* POWER6 */ W(0xffff0000), W(0x003f0000), /* POWER7 */ W(0xffff0000), W(0x004b0000), /* POWER8E */ + W(0xffff0000), W(0x004c0000), /* POWER8NVL */ W(0xffff0000), W(0x004d0000), /* POWER8 */ W(0xffffffff), W(0x0f000004), /* all 2.07-compliant */ W(0xffffffff), W(0x0f000003), /* all 2.06-compliant */ @@ -693,7 +694,7 @@ unsigned char ibm_architecture_vec[] = { OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */ /* option vector 5: PAPR/OF options */ - VECTOR_LENGTH(18), /* length */ + VECTOR_LENGTH(21), /* length */ 0, /* don't ignore, don't halt */ OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) | OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) | @@ -717,15 +718,18 @@ unsigned char ibm_architecture_vec[] = { * must match by the macro below. Update the definition if * the structure layout changes. */ -#define IBM_ARCH_VEC_NRCORES_OFFSET 125 +#define IBM_ARCH_VEC_NRCORES_OFFSET 133 W(NR_CPUS), /* number of cores supported */ 0, 0, 0, 0, OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | - OV5_FEAT(OV5_PFO_HW_842), - OV5_FEAT(OV5_SUB_PROCESSORS), + OV5_FEAT(OV5_PFO_HW_842), /* Byte 17 */ + 0, /* Byte 18 */ + 0, /* Byte 19 */ + 0, /* Byte 20 */ + OV5_FEAT(OV5_SUB_PROCESSORS), /* Byte 21 */ /* option vector 6: IBM PAPR hints */ VECTOR_LENGTH(3), /* length */ @@ -2660,6 +2664,9 @@ static void __init prom_find_boot_cpu(void) cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu); + if (!PHANDLE_VALID(cpu_pkg)) + return; + prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval)); prom.cpu = be32_to_cpu(rval); diff --git a/kernel/arch/powerpc/kernel/ptrace.c b/kernel/arch/powerpc/kernel/ptrace.c index 737c0d0b5..b38fd081b 100644 --- a/kernel/arch/powerpc/kernel/ptrace.c +++ b/kernel/arch/powerpc/kernel/ptrace.c @@ -376,7 +376,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != - offsetof(struct thread_fp_state, fpr[32][0])); + offsetof(struct thread_fp_state, fpr[32])); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); @@ -404,7 +404,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, return 0; #else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != - offsetof(struct thread_fp_state, fpr[32][0])); + offsetof(struct thread_fp_state, fpr[32])); return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); diff --git a/kernel/arch/powerpc/kernel/tm.S b/kernel/arch/powerpc/kernel/tm.S index bf8f34a58..b7019b559 100644 --- a/kernel/arch/powerpc/kernel/tm.S +++ b/kernel/arch/powerpc/kernel/tm.S @@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) - /* We need to setup MSR for VSX register save instructions. Here we - * also clear the MSR RI since when we do the treclaim, we won't have a - * valid kernel pointer for a while. We clear RI here as it avoids - * adding another mtmsr closer to the treclaim. This makes the region - * maked as non-recoverable wider than it needs to be but it saves on - * inserting another mtmsrd later. - */ + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 ori r15, r15, MSR_FP - li r16, MSR_RI + li r16, 0 ori r16, r16, MSR_EE /* IRQs hard off */ andc r15, r15, r16 oris r15, r15, MSR_VEC@h @@ -176,7 +170,17 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 - /* The moment we treclaim, ALL of our GPRs will switch + /* Clear MSR RI since we are about to change r1, EE is already off. */ + li r4, 0 + mtmsrd r4, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + * + * The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. */ @@ -197,6 +201,11 @@ dont_backup_fp: /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + + /* Reset MSR RI so we can take SLB faults again */ + li r11, MSR_RI + mtmsrd r11, 1 + mfspr r11, SPRN_PPR HMT_MEDIUM @@ -397,11 +406,6 @@ restore_gprs: ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) - /* Clear the MSR RI since we are about to change R1. EE is already off - */ - li r4, 0 - mtmsrd r4, 1 - REST_GPR(0, r7) /* GPR0 */ REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ @@ -439,10 +443,33 @@ restore_gprs: ld r6, _CCR(r7) mtcr r6 - REST_GPR(1, r7) /* GPR1 */ - REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) - ld r7, GPR7(r7) + + /* + * Store r1 and r5 on the stack so that we can access them + * after we clear MSR RI. + */ + + REST_GPR(5, r7) + std r5, -8(r1) + ld r5, GPR1(r7) + std r5, -16(r1) + + REST_GPR(7, r7) + + /* Clear MSR RI since we are about to change r1. EE is already off */ + li r5, 0 + mtmsrd r5, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + */ + + ld r5, -8(r1) + ld r1, -16(r1) /* Commit register state as checkpointed state: */ TRECHKPT diff --git a/kernel/arch/powerpc/kernel/vdso64/datapage.S b/kernel/arch/powerpc/kernel/vdso64/datapage.S index 2f01c4a0d..7612eeb31 100644 --- a/kernel/arch/powerpc/kernel/vdso64/datapage.S +++ b/kernel/arch/powerpc/kernel/vdso64/datapage.S @@ -59,7 +59,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) bl V_LOCAL_FUNC(__get_datapage) mtlr r12 addi r3,r3,CFG_SYSCALL_MAP64 - cmpli cr0,r4,0 + cmpldi cr0,r4,0 crclr cr0*4+so beqlr li r0,__NR_syscalls diff --git a/kernel/arch/powerpc/kernel/vdso64/gettimeofday.S b/kernel/arch/powerpc/kernel/vdso64/gettimeofday.S index a76b4af37..382021324 100644 --- a/kernel/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/kernel/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -145,7 +145,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) bne cr0,99f li r3,0 - cmpli cr0,r4,0 + cmpldi cr0,r4,0 crclr cr0*4+so beqlr lis r5,CLOCK_REALTIME_RES@h diff --git a/kernel/arch/powerpc/kvm/book3s_emulate.c b/kernel/arch/powerpc/kvm/book3s_emulate.c index 2afdb9c09..729f8faa9 100644 --- a/kernel/arch/powerpc/kvm/book3s_emulate.c +++ b/kernel/arch/powerpc/kvm/book3s_emulate.c @@ -498,6 +498,7 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) case SPRN_MMCR0: case SPRN_MMCR1: case SPRN_MMCR2: + case SPRN_UMMCR2: #endif break; unprivileged: @@ -640,6 +641,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val case SPRN_MMCR0: case SPRN_MMCR1: case SPRN_MMCR2: + case SPRN_UMMCR2: case SPRN_TIR: #endif *spr_val = 0; diff --git a/kernel/arch/powerpc/kvm/book3s_hv.c b/kernel/arch/powerpc/kvm/book3s_hv.c index df34a6432..2ac7a8b10 100644 --- a/kernel/arch/powerpc/kvm/book3s_hv.c +++ b/kernel/arch/powerpc/kvm/book3s_hv.c @@ -1186,6 +1186,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_TM_CR: *val = get_reg_val(id, vcpu->arch.cr_tm); break; + case KVM_REG_PPC_TM_XER: + *val = get_reg_val(id, vcpu->arch.xer_tm); + break; case KVM_REG_PPC_TM_LR: *val = get_reg_val(id, vcpu->arch.lr_tm); break; @@ -1393,6 +1396,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_TM_CR: vcpu->arch.cr_tm = set_reg_val(id, *val); break; + case KVM_REG_PPC_TM_XER: + vcpu->arch.xer_tm = set_reg_val(id, *val); + break; case KVM_REG_PPC_TM_LR: vcpu->arch.lr_tm = set_reg_val(id, *val); break; diff --git a/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 91700518b..d509ff5c8 100644 --- a/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/kernel/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -653,6 +653,8 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, HPTE_V_ABSENT); do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true); + /* Don't lose R/C bit updates done by hardware */ + r |= be64_to_cpu(hpte[1]) & (HPTE_R_R | HPTE_R_C); hpte[1] = cpu_to_be64(r); } } diff --git a/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 463af88c9..1a743f87b 100644 --- a/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/kernel/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -655,112 +655,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BEGIN_FTR_SECTION - b skip_tm -END_FTR_SECTION_IFCLR(CPU_FTR_TM) - - /* Turn on TM/FP/VSX/VMX so we can restore them. */ - mfmsr r5 - li r6, MSR_TM >> 32 - sldi r6, r6, 32 - or r5, r5, r6 - ori r5, r5, MSR_FP - oris r5, r5, (MSR_VEC | MSR_VSX)@h - mtmsrd r5 - - /* - * The user may change these outside of a transaction, so they must - * always be context switched. - */ - ld r5, VCPU_TFHAR(r4) - ld r6, VCPU_TFIAR(r4) - ld r7, VCPU_TEXASR(r4) - mtspr SPRN_TFHAR, r5 - mtspr SPRN_TFIAR, r6 - mtspr SPRN_TEXASR, r7 - - ld r5, VCPU_MSR(r4) - rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 - beq skip_tm /* TM not active in guest */ - - /* Make sure the failure summary is set, otherwise we'll program check - * when we trechkpt. It's possible that this might have been not set - * on a kvmppc_set_one_reg() call but we shouldn't let this crash the - * host. - */ - oris r7, r7, (TEXASR_FS)@h - mtspr SPRN_TEXASR, r7 - - /* - * We need to load up the checkpointed state for the guest. - * We need to do this early as it will blow away any GPRs, VSRs and - * some SPRs. - */ - - mr r31, r4 - addi r3, r31, VCPU_FPRS_TM - bl load_fp_state - addi r3, r31, VCPU_VRS_TM - bl load_vr_state - mr r4, r31 - lwz r7, VCPU_VRSAVE_TM(r4) - mtspr SPRN_VRSAVE, r7 - - ld r5, VCPU_LR_TM(r4) - lwz r6, VCPU_CR_TM(r4) - ld r7, VCPU_CTR_TM(r4) - ld r8, VCPU_AMR_TM(r4) - ld r9, VCPU_TAR_TM(r4) - mtlr r5 - mtcr r6 - mtctr r7 - mtspr SPRN_AMR, r8 - mtspr SPRN_TAR, r9 - - /* - * Load up PPR and DSCR values but don't put them in the actual SPRs - * till the last moment to avoid running with userspace PPR and DSCR for - * too long. - */ - ld r29, VCPU_DSCR_TM(r4) - ld r30, VCPU_PPR_TM(r4) - - std r2, PACATMSCRATCH(r13) /* Save TOC */ - - /* Clear the MSR RI since r1, r13 are all going to be foobar. */ - li r5, 0 - mtmsrd r5, 1 - - /* Load GPRs r0-r28 */ - reg = 0 - .rept 29 - ld reg, VCPU_GPRS_TM(reg)(r31) - reg = reg + 1 - .endr - - mtspr SPRN_DSCR, r29 - mtspr SPRN_PPR, r30 - - /* Load final GPRs */ - ld 29, VCPU_GPRS_TM(29)(r31) - ld 30, VCPU_GPRS_TM(30)(r31) - ld 31, VCPU_GPRS_TM(31)(r31) - - /* TM checkpointed state is now setup. All GPRs are now volatile. */ - TRECHKPT - - /* Now let's get back the state we need. */ - HMT_MEDIUM - GET_PACA(r13) - ld r29, HSTATE_DSCR(r13) - mtspr SPRN_DSCR, r29 - ld r4, HSTATE_KVM_VCPU(r13) - ld r1, HSTATE_HOST_R1(r13) - ld r2, PACATMSCRATCH(r13) - - /* Set the MSR RI since we have our registers back. */ - li r5, MSR_RI - mtmsrd r5, 1 -skip_tm: + bl kvmppc_restore_tm +END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif /* Load guest PMU registers */ @@ -841,12 +737,6 @@ BEGIN_FTR_SECTION /* Skip next section on POWER7 */ b 8f END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) - /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */ - mfmsr r8 - li r0, 1 - rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r8 - /* Load up POWER8-specific registers */ ld r5, VCPU_IAMR(r4) lwz r6, VCPU_PSPB(r4) @@ -1436,106 +1326,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BEGIN_FTR_SECTION - b 2f -END_FTR_SECTION_IFCLR(CPU_FTR_TM) - /* Turn on TM. */ - mfmsr r8 - li r0, 1 - rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r8 - - ld r5, VCPU_MSR(r9) - rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 - beq 1f /* TM not active in guest. */ - - li r3, TM_CAUSE_KVM_RESCHED - - /* Clear the MSR RI since r1, r13 are all going to be foobar. */ - li r5, 0 - mtmsrd r5, 1 - - /* All GPRs are volatile at this point. */ - TRECLAIM(R3) - - /* Temporarily store r13 and r9 so we have some regs to play with */ - SET_SCRATCH0(r13) - GET_PACA(r13) - std r9, PACATMSCRATCH(r13) - ld r9, HSTATE_KVM_VCPU(r13) - - /* Get a few more GPRs free. */ - std r29, VCPU_GPRS_TM(29)(r9) - std r30, VCPU_GPRS_TM(30)(r9) - std r31, VCPU_GPRS_TM(31)(r9) - - /* Save away PPR and DSCR soon so don't run with user values. */ - mfspr r31, SPRN_PPR - HMT_MEDIUM - mfspr r30, SPRN_DSCR - ld r29, HSTATE_DSCR(r13) - mtspr SPRN_DSCR, r29 - - /* Save all but r9, r13 & r29-r31 */ - reg = 0 - .rept 29 - .if (reg != 9) && (reg != 13) - std reg, VCPU_GPRS_TM(reg)(r9) - .endif - reg = reg + 1 - .endr - /* ... now save r13 */ - GET_SCRATCH0(r4) - std r4, VCPU_GPRS_TM(13)(r9) - /* ... and save r9 */ - ld r4, PACATMSCRATCH(r13) - std r4, VCPU_GPRS_TM(9)(r9) - - /* Reload stack pointer and TOC. */ - ld r1, HSTATE_HOST_R1(r13) - ld r2, PACATOC(r13) - - /* Set MSR RI now we have r1 and r13 back. */ - li r5, MSR_RI - mtmsrd r5, 1 - - /* Save away checkpinted SPRs. */ - std r31, VCPU_PPR_TM(r9) - std r30, VCPU_DSCR_TM(r9) - mflr r5 - mfcr r6 - mfctr r7 - mfspr r8, SPRN_AMR - mfspr r10, SPRN_TAR - std r5, VCPU_LR_TM(r9) - stw r6, VCPU_CR_TM(r9) - std r7, VCPU_CTR_TM(r9) - std r8, VCPU_AMR_TM(r9) - std r10, VCPU_TAR_TM(r9) - - /* Restore r12 as trap number. */ - lwz r12, VCPU_TRAP(r9) - - /* Save FP/VSX. */ - addi r3, r9, VCPU_FPRS_TM - bl store_fp_state - addi r3, r9, VCPU_VRS_TM - bl store_vr_state - mfspr r6, SPRN_VRSAVE - stw r6, VCPU_VRSAVE_TM(r9) -1: - /* - * We need to save these SPRs after the treclaim so that the software - * error code is recorded correctly in the TEXASR. Also the user may - * change these outside of a transaction, so they must always be - * context switched. - */ - mfspr r5, SPRN_TFHAR - mfspr r6, SPRN_TFIAR - mfspr r7, SPRN_TEXASR - std r5, VCPU_TFHAR(r9) - std r6, VCPU_TFIAR(r9) - std r7, VCPU_TEXASR(r9) -2: + bl kvmppc_save_tm +END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif /* Increment yield count if they have a VPA */ @@ -2245,6 +2037,13 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */ /* save FP state */ bl kvmppc_save_fp +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +BEGIN_FTR_SECTION + ld r9, HSTATE_KVM_VCPU(r13) + bl kvmppc_save_tm +END_FTR_SECTION_IFSET(CPU_FTR_TM) +#endif + /* * Set DEC to the smaller of DEC and HDEC, so that we wake * no later than the end of our timeslice (HDEC interrupts @@ -2321,6 +2120,12 @@ kvm_end_cede: bl kvmhv_accumulate_time #endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +BEGIN_FTR_SECTION + bl kvmppc_restore_tm +END_FTR_SECTION_IFSET(CPU_FTR_TM) +#endif + /* load up FP state */ bl kvmppc_load_fp @@ -2629,6 +2434,243 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mr r4,r31 blr +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +/* + * Save transactional state and TM-related registers. + * Called with r9 pointing to the vcpu struct. + * This can modify all checkpointed registers, but + * restores r1, r2 and r9 (vcpu pointer) before exit. + */ +kvmppc_save_tm: + mflr r0 + std r0, PPC_LR_STKOFF(r1) + + /* Turn on TM. */ + mfmsr r8 + li r0, 1 + rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG + mtmsrd r8 + + ld r5, VCPU_MSR(r9) + rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 + beq 1f /* TM not active in guest. */ + + std r1, HSTATE_HOST_R1(r13) + li r3, TM_CAUSE_KVM_RESCHED + + /* Clear the MSR RI since r1, r13 are all going to be foobar. */ + li r5, 0 + mtmsrd r5, 1 + + /* All GPRs are volatile at this point. */ + TRECLAIM(R3) + + /* Temporarily store r13 and r9 so we have some regs to play with */ + SET_SCRATCH0(r13) + GET_PACA(r13) + std r9, PACATMSCRATCH(r13) + ld r9, HSTATE_KVM_VCPU(r13) + + /* Get a few more GPRs free. */ + std r29, VCPU_GPRS_TM(29)(r9) + std r30, VCPU_GPRS_TM(30)(r9) + std r31, VCPU_GPRS_TM(31)(r9) + + /* Save away PPR and DSCR soon so don't run with user values. */ + mfspr r31, SPRN_PPR + HMT_MEDIUM + mfspr r30, SPRN_DSCR + ld r29, HSTATE_DSCR(r13) + mtspr SPRN_DSCR, r29 + + /* Save all but r9, r13 & r29-r31 */ + reg = 0 + .rept 29 + .if (reg != 9) && (reg != 13) + std reg, VCPU_GPRS_TM(reg)(r9) + .endif + reg = reg + 1 + .endr + /* ... now save r13 */ + GET_SCRATCH0(r4) + std r4, VCPU_GPRS_TM(13)(r9) + /* ... and save r9 */ + ld r4, PACATMSCRATCH(r13) + std r4, VCPU_GPRS_TM(9)(r9) + + /* Reload stack pointer and TOC. */ + ld r1, HSTATE_HOST_R1(r13) + ld r2, PACATOC(r13) + + /* Set MSR RI now we have r1 and r13 back. */ + li r5, MSR_RI + mtmsrd r5, 1 + + /* Save away checkpinted SPRs. */ + std r31, VCPU_PPR_TM(r9) + std r30, VCPU_DSCR_TM(r9) + mflr r5 + mfcr r6 + mfctr r7 + mfspr r8, SPRN_AMR + mfspr r10, SPRN_TAR + mfxer r11 + std r5, VCPU_LR_TM(r9) + stw r6, VCPU_CR_TM(r9) + std r7, VCPU_CTR_TM(r9) + std r8, VCPU_AMR_TM(r9) + std r10, VCPU_TAR_TM(r9) + std r11, VCPU_XER_TM(r9) + + /* Restore r12 as trap number. */ + lwz r12, VCPU_TRAP(r9) + + /* Save FP/VSX. */ + addi r3, r9, VCPU_FPRS_TM + bl store_fp_state + addi r3, r9, VCPU_VRS_TM + bl store_vr_state + mfspr r6, SPRN_VRSAVE + stw r6, VCPU_VRSAVE_TM(r9) +1: + /* + * We need to save these SPRs after the treclaim so that the software + * error code is recorded correctly in the TEXASR. Also the user may + * change these outside of a transaction, so they must always be + * context switched. + */ + mfspr r5, SPRN_TFHAR + mfspr r6, SPRN_TFIAR + mfspr r7, SPRN_TEXASR + std r5, VCPU_TFHAR(r9) + std r6, VCPU_TFIAR(r9) + std r7, VCPU_TEXASR(r9) + + ld r0, PPC_LR_STKOFF(r1) + mtlr r0 + blr + +/* + * Restore transactional state and TM-related registers. + * Called with r4 pointing to the vcpu struct. + * This potentially modifies all checkpointed registers. + * It restores r1, r2, r4 from the PACA. + */ +kvmppc_restore_tm: + mflr r0 + std r0, PPC_LR_STKOFF(r1) + + /* Turn on TM/FP/VSX/VMX so we can restore them. */ + mfmsr r5 + li r6, MSR_TM >> 32 + sldi r6, r6, 32 + or r5, r5, r6 + ori r5, r5, MSR_FP + oris r5, r5, (MSR_VEC | MSR_VSX)@h + mtmsrd r5 + + /* + * The user may change these outside of a transaction, so they must + * always be context switched. + */ + ld r5, VCPU_TFHAR(r4) + ld r6, VCPU_TFIAR(r4) + ld r7, VCPU_TEXASR(r4) + mtspr SPRN_TFHAR, r5 + mtspr SPRN_TFIAR, r6 + mtspr SPRN_TEXASR, r7 + + ld r5, VCPU_MSR(r4) + rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 + beqlr /* TM not active in guest */ + std r1, HSTATE_HOST_R1(r13) + + /* Make sure the failure summary is set, otherwise we'll program check + * when we trechkpt. It's possible that this might have been not set + * on a kvmppc_set_one_reg() call but we shouldn't let this crash the + * host. + */ + oris r7, r7, (TEXASR_FS)@h + mtspr SPRN_TEXASR, r7 + + /* + * We need to load up the checkpointed state for the guest. + * We need to do this early as it will blow away any GPRs, VSRs and + * some SPRs. + */ + + mr r31, r4 + addi r3, r31, VCPU_FPRS_TM + bl load_fp_state + addi r3, r31, VCPU_VRS_TM + bl load_vr_state + mr r4, r31 + lwz r7, VCPU_VRSAVE_TM(r4) + mtspr SPRN_VRSAVE, r7 + + ld r5, VCPU_LR_TM(r4) + lwz r6, VCPU_CR_TM(r4) + ld r7, VCPU_CTR_TM(r4) + ld r8, VCPU_AMR_TM(r4) + ld r9, VCPU_TAR_TM(r4) + ld r10, VCPU_XER_TM(r4) + mtlr r5 + mtcr r6 + mtctr r7 + mtspr SPRN_AMR, r8 + mtspr SPRN_TAR, r9 + mtxer r10 + + /* + * Load up PPR and DSCR values but don't put them in the actual SPRs + * till the last moment to avoid running with userspace PPR and DSCR for + * too long. + */ + ld r29, VCPU_DSCR_TM(r4) + ld r30, VCPU_PPR_TM(r4) + + std r2, PACATMSCRATCH(r13) /* Save TOC */ + + /* Clear the MSR RI since r1, r13 are all going to be foobar. */ + li r5, 0 + mtmsrd r5, 1 + + /* Load GPRs r0-r28 */ + reg = 0 + .rept 29 + ld reg, VCPU_GPRS_TM(reg)(r31) + reg = reg + 1 + .endr + + mtspr SPRN_DSCR, r29 + mtspr SPRN_PPR, r30 + + /* Load final GPRs */ + ld 29, VCPU_GPRS_TM(29)(r31) + ld 30, VCPU_GPRS_TM(30)(r31) + ld 31, VCPU_GPRS_TM(31)(r31) + + /* TM checkpointed state is now setup. All GPRs are now volatile. */ + TRECHKPT + + /* Now let's get back the state we need. */ + HMT_MEDIUM + GET_PACA(r13) + ld r29, HSTATE_DSCR(r13) + mtspr SPRN_DSCR, r29 + ld r4, HSTATE_KVM_VCPU(r13) + ld r1, HSTATE_HOST_R1(r13) + ld r2, PACATMSCRATCH(r13) + + /* Set the MSR RI since we have our registers back. */ + li r5, MSR_RI + mtmsrd r5, 1 + + ld r0, PPC_LR_STKOFF(r1) + mtlr r0 + blr +#endif + /* * We come here if we get any exception or interrupt while we are * executing host real mode code while in guest MMU context. diff --git a/kernel/arch/powerpc/kvm/booke.c b/kernel/arch/powerpc/kvm/booke.c index fd5875179..6d63cd67b 100644 --- a/kernel/arch/powerpc/kvm/booke.c +++ b/kernel/arch/powerpc/kvm/booke.c @@ -2033,7 +2033,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, if (type == KVMPPC_DEBUG_NONE) continue; - if (type & !(KVMPPC_DEBUG_WATCH_READ | + if (type & ~(KVMPPC_DEBUG_WATCH_READ | KVMPPC_DEBUG_WATCH_WRITE | KVMPPC_DEBUG_BREAKPOINT)) return -EINVAL; diff --git a/kernel/arch/powerpc/lib/copyuser_64.S b/kernel/arch/powerpc/lib/copyuser_64.S index f09899e35..7b22624f3 100644 --- a/kernel/arch/powerpc/lib/copyuser_64.S +++ b/kernel/arch/powerpc/lib/copyuser_64.S @@ -359,6 +359,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) addi r3,r3,8 171: 177: +179: addi r3,r3,8 370: 372: @@ -373,7 +374,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD) 173: 174: 175: -179: 181: 184: 186: diff --git a/kernel/arch/powerpc/mm/copro_fault.c b/kernel/arch/powerpc/mm/copro_fault.c index 6527882ce..ddfd2740a 100644 --- a/kernel/arch/powerpc/mm/copro_fault.c +++ b/kernel/arch/powerpc/mm/copro_fault.c @@ -106,6 +106,8 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb) switch (REGION_ID(ea)) { case USER_REGION_ID: pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea); + if (mm == NULL) + return 1; psize = get_slice_psize(mm, ea); ssize = user_segment_size(ea); vsid = get_vsid(mm->context.id, ea, ssize); diff --git a/kernel/arch/powerpc/mm/hugetlbpage.c b/kernel/arch/powerpc/mm/hugetlbpage.c index 9833fee49..807f15947 100644 --- a/kernel/arch/powerpc/mm/hugetlbpage.c +++ b/kernel/arch/powerpc/mm/hugetlbpage.c @@ -486,13 +486,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) { struct hugepd_freelist **batchp; - batchp = this_cpu_ptr(&hugepd_freelist_cur); + batchp = &get_cpu_var(hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))) { kmem_cache_free(hugepte_cache, hugepte); - put_cpu_var(hugepd_freelist_cur); + put_cpu_var(hugepd_freelist_cur); return; } diff --git a/kernel/arch/powerpc/mm/slb_low.S b/kernel/arch/powerpc/mm/slb_low.S index 736d18b3c..4c48b4876 100644 --- a/kernel/arch/powerpc/mm/slb_low.S +++ b/kernel/arch/powerpc/mm/slb_low.S @@ -113,7 +113,12 @@ BEGIN_FTR_SECTION END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) b slb_finish_load_1T -0: +0: /* + * For userspace addresses, make sure this is region 0. + */ + cmpdi r9, 0 + bne 8f + /* when using slices, we extract the psize off the slice bitmaps * and then we need to get the sllp encoding off the mmu_psize_defs * array. diff --git a/kernel/arch/powerpc/platforms/powernv/eeh-powernv.c b/kernel/arch/powerpc/platforms/powernv/eeh-powernv.c index 2ba602591..92736851c 100644 --- a/kernel/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/kernel/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -956,6 +956,11 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option) } bus = eeh_pe_bus_get(pe); + if (!bus) { + pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n", + __func__, pe->phb->global_number, pe->addr); + return -EIO; + } if (pci_is_root_bus(bus) || pci_is_root_bus(bus->parent)) ret = pnv_eeh_root_reset(hose, option); @@ -1163,7 +1168,7 @@ static void pnv_eeh_get_and_dump_hub_diag(struct pci_controller *hose) return; } - switch (data->type) { + switch (be16_to_cpu(data->type)) { case OPAL_P7IOC_DIAG_TYPE_RGC: pr_info("P7IOC diag-data for RGC\n\n"); pnv_eeh_dump_hub_diag_common(data); @@ -1395,7 +1400,7 @@ static int pnv_eeh_next_error(struct eeh_pe **pe) /* Try best to clear it */ opal_pci_eeh_freeze_clear(phb->opal_id, - frozen_pe_no, + be64_to_cpu(frozen_pe_no), OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); ret = EEH_NEXT_ERR_NONE; } else if ((*pe)->state & EEH_PE_ISOLATED || diff --git a/kernel/arch/powerpc/platforms/powernv/opal-dump.c b/kernel/arch/powerpc/platforms/powernv/opal-dump.c index 2ee96431f..4c827826c 100644 --- a/kernel/arch/powerpc/platforms/powernv/opal-dump.c +++ b/kernel/arch/powerpc/platforms/powernv/opal-dump.c @@ -370,6 +370,7 @@ static irqreturn_t process_dump(int irq, void *data) uint32_t dump_id, dump_size, dump_type; struct dump_obj *dump; char name[22]; + struct kobject *kobj; rc = dump_read_info(&dump_id, &dump_size, &dump_type); if (rc != OPAL_SUCCESS) @@ -381,8 +382,12 @@ static irqreturn_t process_dump(int irq, void *data) * that gracefully and not create two conflicting * entries. */ - if (kset_find_obj(dump_kset, name)) + kobj = kset_find_obj(dump_kset, name); + if (kobj) { + /* Drop reference added by kset_find_obj() */ + kobject_put(kobj); return 0; + } dump = create_dump_obj(dump_id, dump_size, dump_type); if (!dump) diff --git a/kernel/arch/powerpc/platforms/powernv/opal-elog.c b/kernel/arch/powerpc/platforms/powernv/opal-elog.c index 37f959bf3..f2344cbd2 100644 --- a/kernel/arch/powerpc/platforms/powernv/opal-elog.c +++ b/kernel/arch/powerpc/platforms/powernv/opal-elog.c @@ -247,6 +247,7 @@ static irqreturn_t elog_event(int irq, void *data) uint64_t elog_type; int rc; char name[2+16+1]; + struct kobject *kobj; rc = opal_get_elog_size(&id, &size, &type); if (rc != OPAL_SUCCESS) { @@ -269,8 +270,12 @@ static irqreturn_t elog_event(int irq, void *data) * that gracefully and not create two conflicting * entries. */ - if (kset_find_obj(elog_kset, name)) + kobj = kset_find_obj(elog_kset, name); + if (kobj) { + /* Drop reference added by kset_find_obj() */ + kobject_put(kobj); return IRQ_HANDLED; + } create_elog_obj(log_id, elog_size, elog_type); diff --git a/kernel/arch/powerpc/platforms/powernv/pci.c b/kernel/arch/powerpc/platforms/powernv/pci.c index ad8c3f4a5..dd5e0f3b1 100644 --- a/kernel/arch/powerpc/platforms/powernv/pci.c +++ b/kernel/arch/powerpc/platforms/powernv/pci.c @@ -197,8 +197,8 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose, be64_to_cpu(data->dma1ErrorLog1)); for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) { - if ((data->pestA[i] >> 63) == 0 && - (data->pestB[i] >> 63) == 0) + if ((be64_to_cpu(data->pestA[i]) >> 63) == 0 && + (be64_to_cpu(data->pestB[i]) >> 63) == 0) continue; pr_info("PE[%3d] A/B: %016llx %016llx\n", diff --git a/kernel/arch/powerpc/platforms/pseries/eeh_pseries.c b/kernel/arch/powerpc/platforms/pseries/eeh_pseries.c index ac3ffd97e..405baaf96 100644 --- a/kernel/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/kernel/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -615,29 +615,50 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { int config_addr; int ret; + /* Waiting 0.2s maximum before skipping configuration */ + int max_wait = 200; /* Figure out the PE address */ config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; - /* Use new configure-pe function, if supported */ - if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_pe, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else { - return -EFAULT; - } + while (max_wait > 0) { + /* Use new configure-pe function, if supported */ + if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { + ret = rtas_call(ibm_configure_pe, 3, 1, NULL, + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); + } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { + ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); + } else { + return -EFAULT; + } - if (ret) - pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", - __func__, pe->phb->global_number, pe->addr, ret); + if (!ret) + return ret; + + /* + * If RTAS returns a delay value that's above 100ms, cut it + * down to 100ms in case firmware made a mistake. For more + * on how these delay values work see rtas_busy_delay_time + */ + if (ret > RTAS_EXTENDED_DELAY_MIN+2 && + ret <= RTAS_EXTENDED_DELAY_MAX) + ret = RTAS_EXTENDED_DELAY_MIN+2; + + max_wait -= rtas_busy_delay_time(ret); + + if (max_wait < 0) + break; + + rtas_busy_delay(ret); + } + pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", + __func__, pe->phb->global_number, pe->addr, ret); return ret; } diff --git a/kernel/arch/powerpc/platforms/pseries/iommu.c b/kernel/arch/powerpc/platforms/pseries/iommu.c index bd98ce2be..3e8865b18 100644 --- a/kernel/arch/powerpc/platforms/pseries/iommu.c +++ b/kernel/arch/powerpc/platforms/pseries/iommu.c @@ -912,7 +912,8 @@ machine_arch_initcall(pseries, find_existing_ddw_windows); static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_query_response *query) { - struct eeh_dev *edev; + struct device_node *dn; + struct pci_dn *pdn; u32 cfg_addr; u64 buid; int ret; @@ -923,11 +924,10 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, * Retrieve them from the pci device, not the node with the * dma-window property */ - edev = pci_dev_to_eeh_dev(dev); - cfg_addr = edev->config_addr; - if (edev->pe_config_addr) - cfg_addr = edev->pe_config_addr; - buid = edev->phb->buid; + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + buid = pdn->phb->buid; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, cfg_addr, BUID_HI(buid), BUID_LO(buid)); @@ -941,7 +941,8 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_create_response *create, int page_shift, int window_shift) { - struct eeh_dev *edev; + struct device_node *dn; + struct pci_dn *pdn; u32 cfg_addr; u64 buid; int ret; @@ -952,11 +953,10 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, * Retrieve them from the pci device, not the node with the * dma-window property */ - edev = pci_dev_to_eeh_dev(dev); - cfg_addr = edev->config_addr; - if (edev->pe_config_addr) - cfg_addr = edev->pe_config_addr; - buid = edev->phb->buid; + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + buid = pdn->phb->buid; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ diff --git a/kernel/arch/powerpc/platforms/pseries/lpar.c b/kernel/arch/powerpc/platforms/pseries/lpar.c index b7a67e3d2..3ae432824 100644 --- a/kernel/arch/powerpc/platforms/pseries/lpar.c +++ b/kernel/arch/powerpc/platforms/pseries/lpar.c @@ -406,7 +406,7 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot, unsigned long *vpn, int count, int psize, int ssize) { - unsigned long param[8]; + unsigned long param[PLPAR_HCALL9_BUFSIZE]; int i = 0, pix = 0, rc; unsigned long flags = 0; int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); @@ -523,7 +523,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) unsigned long flags = 0; struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch); int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); - unsigned long param[9]; + unsigned long param[PLPAR_HCALL9_BUFSIZE]; unsigned long hash, index, shift, hidx, slot; real_pte_t pte; int psize, ssize; |