diff options
author | Herbert Xu <herbert@gondor.apana.org.au> | 2014-11-12 14:11:15 (GMT) |
---|---|---|
committer | Herbert Xu <herbert@gondor.apana.org.au> | 2014-11-12 14:11:15 (GMT) |
commit | 4c7912e9198b141b6cd85999d28b48cb5a037aa0 (patch) | |
tree | 901b2bc822976f6092fd06c709876e96d78bd50d /arch/powerpc | |
parent | bdcf83b7831e41f666b50ee6cd946c733bbea1ef (diff) | |
parent | 206c5f60a3d902bc4b56dab2de3e88de5eb06108 (diff) | |
download | linux-4c7912e9198b141b6cd85999d28b48cb5a037aa0.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux
Merging 3.18-rc4 in order to pick up the memzero_explicit helper.
Diffstat (limited to 'arch/powerpc')
42 files changed, 432 insertions, 230 deletions
diff --git a/arch/powerpc/configs/pseries_le_defconfig b/arch/powerpc/configs/pseries_le_defconfig index 63392f4..d200888 100644 --- a/arch/powerpc/configs/pseries_le_defconfig +++ b/arch/powerpc/configs/pseries_le_defconfig @@ -48,7 +48,6 @@ CONFIG_KEXEC=y CONFIG_IRQ_ALL_CPUS=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y -CONFIG_CMA=y CONFIG_PPC_64K_PAGES=y CONFIG_PPC_SUBPAGE_PROT=y CONFIG_SCHED_SMT=y @@ -138,6 +137,7 @@ CONFIG_NETCONSOLE=y CONFIG_NETPOLL_TRAP=y CONFIG_TUN=m CONFIG_VIRTIO_NET=m +CONFIG_VHOST_NET=m CONFIG_VORTEX=y CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y @@ -303,4 +303,9 @@ CONFIG_CRYPTO_LZO=m # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m +CONFIG_VIRTUALIZATION=y +CONFIG_KVM_BOOK3S_64=m +CONFIG_KVM_BOOK3S_64_HV=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 3b260ef..ca07f9c 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -71,9 +71,10 @@ struct device_node; #define EEH_PE_ISOLATED (1 << 0) /* Isolated PE */ #define EEH_PE_RECOVERING (1 << 1) /* Recovering PE */ -#define EEH_PE_RESET (1 << 2) /* PE reset in progress */ +#define EEH_PE_CFG_BLOCKED (1 << 2) /* Block config access */ #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ +#define EEH_PE_CFG_RESTRICTED (1 << 9) /* Block config on error */ struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index a677456..493e72f 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -70,39 +70,39 @@ #define CPU_UNKNOWN (~((u32)0)) /* Utility macros */ -#define SKIP_TO_NEXT_CPU(reg_entry) \ -({ \ - while (reg_entry->reg_id != REG_ID("CPUEND")) \ - reg_entry++; \ - reg_entry++; \ +#define SKIP_TO_NEXT_CPU(reg_entry) \ +({ \ + while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) \ + reg_entry++; \ + reg_entry++; \ }) /* Kernel Dump section info */ struct fadump_section { - u32 request_flag; - u16 source_data_type; - u16 error_flags; - u64 source_address; - u64 source_len; - u64 bytes_dumped; - u64 destination_address; + __be32 request_flag; + __be16 source_data_type; + __be16 error_flags; + __be64 source_address; + __be64 source_len; + __be64 bytes_dumped; + __be64 destination_address; }; /* ibm,configure-kernel-dump header. */ struct fadump_section_header { - u32 dump_format_version; - u16 dump_num_sections; - u16 dump_status_flag; - u32 offset_first_dump_section; + __be32 dump_format_version; + __be16 dump_num_sections; + __be16 dump_status_flag; + __be32 offset_first_dump_section; /* Fields for disk dump option. */ - u32 dd_block_size; - u64 dd_block_offset; - u64 dd_num_blocks; - u32 dd_offset_disk_path; + __be32 dd_block_size; + __be64 dd_block_offset; + __be64 dd_num_blocks; + __be32 dd_offset_disk_path; /* Maximum time allowed to prevent an automatic dump-reboot. */ - u32 max_time_auto; + __be32 max_time_auto; }; /* @@ -174,15 +174,15 @@ static inline u64 str_to_u64(const char *str) /* Register save area header. */ struct fadump_reg_save_area_header { - u64 magic_number; - u32 version; - u32 num_cpu_offset; + __be64 magic_number; + __be32 version; + __be32 num_cpu_offset; }; /* Register entry. */ struct fadump_reg_entry { - u64 reg_id; - u64 reg_value; + __be64 reg_id; + __be64 reg_value; }; /* fadump crash info structure */ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 623f297..766b77d 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -71,7 +71,7 @@ pte_t *huge_pte_offset_and_shift(struct mm_struct *mm, void flush_dcache_icache_hugepage(struct page *page); -#if defined(CONFIG_PPC_MM_SLICES) || defined(CONFIG_PPC_SUBPAGE_PROT) +#if defined(CONFIG_PPC_MM_SLICES) int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len); #else diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 0bb2372..8bf1b63 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -34,7 +34,7 @@ do { \ (regs)->result = 0; \ (regs)->nip = __ip; \ - (regs)->gpr[1] = *(unsigned long *)__get_SP(); \ + (regs)->gpr[1] = current_stack_pointer(); \ asm volatile("mfmsr %0" : "=r" ((regs)->msr)); \ } while (0) #endif diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index fe3f948..c998279 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1265,8 +1265,7 @@ static inline unsigned long mfvtb (void) #define proc_trap() asm volatile("trap") -#define __get_SP() ({unsigned long sp; \ - asm volatile("mr %0,1": "=r" (sp)); sp;}) +extern unsigned long current_stack_pointer(void); extern unsigned long scom970_read(unsigned int address); extern void scom970_write(unsigned int address, unsigned long value); diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 6fa2708..6240698 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -19,7 +19,7 @@ /* ftrace syscalls requires exporting the sys_call_table */ #ifdef CONFIG_FTRACE_SYSCALLS -extern const unsigned long *sys_call_table; +extern const unsigned long sys_call_table[]; #endif /* CONFIG_FTRACE_SYSCALLS */ static inline long syscall_get_nr(struct task_struct *task, diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 7d8a6006..ce9577d 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -365,3 +365,4 @@ SYSCALL_SPU(renameat2) SYSCALL_SPU(seccomp) SYSCALL_SPU(getrandom) SYSCALL_SPU(memfd_create) +SYSCALL_SPU(bpf) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 4e9af3f..e0da021 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define __NR_syscalls 361 +#define __NR_syscalls 362 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 0688fc0..f55351f 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -383,5 +383,6 @@ #define __NR_seccomp 358 #define __NR_getrandom 359 #define __NR_memfd_create 360 +#define __NR_bpf 361 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index adac9dc..484b2d4 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -53,9 +53,16 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size, #else struct page *page; int node = dev_to_node(dev); +#ifdef CONFIG_FSL_SOC u64 pfn = get_pfn_limit(dev); int zone; + /* + * This code should be OK on other platforms, but we have drivers that + * don't set coherent_dma_mask. As a workaround we just ifdef it. This + * whole routine needs some serious cleanup. + */ + zone = dma_pfn_limit_to_zone(pfn); if (zone < 0) { dev_err(dev, "%s: No suitable zone for pfn %#llx\n", @@ -73,6 +80,7 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size, break; #endif }; +#endif /* CONFIG_FSL_SOC */ /* ignore region specifiers */ flag &= ~(__GFP_HIGHMEM); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index d543e41..2248a19 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -257,6 +257,13 @@ static void *eeh_dump_pe_log(void *data, void *flag) struct eeh_dev *edev, *tmp; size_t *plen = flag; + /* If the PE's config space is blocked, 0xFF's will be + * returned. It's pointless to collect the log in this + * case. + */ + if (pe->state & EEH_PE_CFG_BLOCKED) + return NULL; + eeh_pe_for_each_dev(pe, edev, tmp) *plen += eeh_dump_dev_log(edev, pci_regs_buf + *plen, EEH_PCI_REGS_LOG_LEN - *plen); @@ -673,18 +680,18 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat switch (state) { case pcie_deassert_reset: eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); - eeh_pe_state_clear(pe, EEH_PE_RESET); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); break; case pcie_hot_reset: - eeh_pe_state_mark(pe, EEH_PE_RESET); + eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_HOT); break; case pcie_warm_reset: - eeh_pe_state_mark(pe, EEH_PE_RESET); + eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); break; default: - eeh_pe_state_clear(pe, EEH_PE_RESET); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); return -EINVAL; }; @@ -1523,7 +1530,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option) switch (option) { case EEH_RESET_DEACTIVATE: ret = eeh_ops->reset(pe, option); - eeh_pe_state_clear(pe, EEH_PE_RESET); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); if (ret) break; @@ -1538,7 +1545,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option) */ eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); - eeh_pe_state_mark(pe, EEH_PE_RESET); + eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); ret = eeh_ops->reset(pe, option); break; default: diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 3fd514f..6535936 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -528,13 +528,13 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) eeh_pe_dev_traverse(pe, eeh_report_error, &result); /* Issue reset */ - eeh_pe_state_mark(pe, EEH_PE_RESET); + eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); ret = eeh_reset_pe(pe); if (ret) { - eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_RESET); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_CFG_BLOCKED); return ret; } - eeh_pe_state_clear(pe, EEH_PE_RESET); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); /* Unfreeze the PE */ ret = eeh_clear_pe_frozen_state(pe, true); @@ -601,10 +601,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) * config accesses. So we prefer to block them. However, controlled * PCI config accesses initiated from EEH itself are allowed. */ - eeh_pe_state_mark(pe, EEH_PE_RESET); + eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); rc = eeh_reset_pe(pe); if (rc) { - eeh_pe_state_clear(pe, EEH_PE_RESET); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); return rc; } @@ -613,7 +613,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) /* Restore PE */ eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); - eeh_pe_state_clear(pe, EEH_PE_RESET); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); /* Clear frozen state */ rc = eeh_clear_pe_frozen_state(pe, false); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 53dd091..5a63e2b0 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -525,7 +525,7 @@ static void *__eeh_pe_state_mark(void *data, void *flag) pe->state |= state; /* Offline PCI devices if applicable */ - if (state != EEH_PE_ISOLATED) + if (!(state & EEH_PE_ISOLATED)) return NULL; eeh_pe_for_each_dev(pe, edev, tmp) { @@ -534,6 +534,10 @@ static void *__eeh_pe_state_mark(void *data, void *flag) pdev->error_state = pci_channel_io_frozen; } + /* Block PCI config access if required */ + if (pe->state & EEH_PE_CFG_RESTRICTED) + pe->state |= EEH_PE_CFG_BLOCKED; + return NULL; } @@ -611,6 +615,10 @@ static void *__eeh_pe_state_clear(void *data, void *flag) pdev->error_state = pci_channel_io_normal; } + /* Unblock PCI config access if required */ + if (pe->state & EEH_PE_CFG_RESTRICTED) + pe->state &= ~EEH_PE_CFG_BLOCKED; + return NULL; } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 5bbd1bc..0905c8d 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -659,7 +659,13 @@ _GLOBAL(ret_from_except_lite) 3: #endif bl save_nvgprs + /* + * Use a non volatile GPR to save and restore our thread_info flags + * across the call to restore_interrupts. + */ + mr r30,r4 bl restore_interrupts + mr r4,r30 addi r3,r1,STACK_FRAME_OVERHEAD bl do_notify_resume b ret_from_except diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 050f79a..72e783e 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1270,11 +1270,6 @@ hmi_exception_early: 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 diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 742694c..26d091a 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -58,7 +58,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, const __be32 *sections; int i, num_sections; int size; - const int *token; + const __be32 *token; if (depth != 1 || strcmp(uname, "rtas") != 0) return 0; @@ -72,7 +72,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, return 1; fw_dump.fadump_supported = 1; - fw_dump.ibm_configure_kernel_dump = *token; + fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token); /* * The 'ibm,kernel-dump' rtas node is present only if there is @@ -147,11 +147,11 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm, memset(fdm, 0, sizeof(struct fadump_mem_struct)); addr = addr & PAGE_MASK; - fdm->header.dump_format_version = 0x00000001; - fdm->header.dump_num_sections = 3; + fdm->header.dump_format_version = cpu_to_be32(0x00000001); + fdm->header.dump_num_sections = cpu_to_be16(3); fdm->header.dump_status_flag = 0; fdm->header.offset_first_dump_section = - (u32)offsetof(struct fadump_mem_struct, cpu_state_data); + cpu_to_be32((u32)offsetof(struct fadump_mem_struct, cpu_state_data)); /* * Fields for disk dump option. @@ -167,27 +167,27 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm, /* Kernel dump sections */ /* cpu state data section. */ - fdm->cpu_state_data.request_flag = FADUMP_REQUEST_FLAG; - fdm->cpu_state_data.source_data_type = FADUMP_CPU_STATE_DATA; + fdm->cpu_state_data.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG); + fdm->cpu_state_data.source_data_type = cpu_to_be16(FADUMP_CPU_STATE_DATA); fdm->cpu_state_data.source_address = 0; - fdm->cpu_state_data.source_len = fw_dump.cpu_state_data_size; - fdm->cpu_state_data.destination_address = addr; + fdm->cpu_state_data.source_len = cpu_to_be64(fw_dump.cpu_state_data_size); + fdm->cpu_state_data.destination_address = cpu_to_be64(addr); addr += fw_dump.cpu_state_data_size; /* hpte region section */ - fdm->hpte_region.request_flag = FADUMP_REQUEST_FLAG; - fdm->hpte_region.source_data_type = FADUMP_HPTE_REGION; + fdm->hpte_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG); + fdm->hpte_region.source_data_type = cpu_to_be16(FADUMP_HPTE_REGION); fdm->hpte_region.source_address = 0; - fdm->hpte_region.source_len = fw_dump.hpte_region_size; - fdm->hpte_region.destination_address = addr; + fdm->hpte_region.source_len = cpu_to_be64(fw_dump.hpte_region_size); + fdm->hpte_region.destination_address = cpu_to_be64(addr); addr += fw_dump.hpte_region_size; /* RMA region section */ - fdm->rmr_region.request_flag = FADUMP_REQUEST_FLAG; - fdm->rmr_region.source_data_type = FADUMP_REAL_MODE_REGION; - fdm->rmr_region.source_address = RMA_START; - fdm->rmr_region.source_len = fw_dump.boot_memory_size; - fdm->rmr_region.destination_address = addr; + fdm->rmr_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG); + fdm->rmr_region.source_data_type = cpu_to_be16(FADUMP_REAL_MODE_REGION); + fdm->rmr_region.source_address = cpu_to_be64(RMA_START); + fdm->rmr_region.source_len = cpu_to_be64(fw_dump.boot_memory_size); + fdm->rmr_region.destination_address = cpu_to_be64(addr); addr += fw_dump.boot_memory_size; return addr; @@ -272,7 +272,7 @@ int __init fadump_reserve_mem(void) * first kernel. */ if (fdm_active) - fw_dump.boot_memory_size = fdm_active->rmr_region.source_len; + fw_dump.boot_memory_size = be64_to_cpu(fdm_active->rmr_region.source_len); else fw_dump.boot_memory_size = fadump_calculate_reserve_size(); @@ -314,8 +314,8 @@ int __init fadump_reserve_mem(void) (unsigned long)(base >> 20)); fw_dump.fadumphdr_addr = - fdm_active->rmr_region.destination_address + - fdm_active->rmr_region.source_len; + be64_to_cpu(fdm_active->rmr_region.destination_address) + + be64_to_cpu(fdm_active->rmr_region.source_len); pr_debug("fadumphdr_addr = %p\n", (void *) fw_dump.fadumphdr_addr); } else { @@ -472,9 +472,9 @@ fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs) { memset(regs, 0, sizeof(struct pt_regs)); - while (reg_entry->reg_id != REG_ID("CPUEND")) { - fadump_set_regval(regs, reg_entry->reg_id, - reg_entry->reg_value); + while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) { + fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id), + be64_to_cpu(reg_entry->reg_value)); reg_entry++; } reg_entry++; @@ -603,20 +603,20 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) if (!fdm->cpu_state_data.bytes_dumped) return -EINVAL; - addr = fdm->cpu_state_data.destination_address; + addr = be64_to_cpu(fdm->cpu_state_data.destination_address); vaddr = __va(addr); reg_header = vaddr; - if (reg_header->magic_number != REGSAVE_AREA_MAGIC) { + if (be64_to_cpu(reg_header->magic_number) != REGSAVE_AREA_MAGIC) { printk(KERN_ERR "Unable to read register save area.\n"); return -ENOENT; } pr_debug("--------CPU State Data------------\n"); - pr_debug("Magic Number: %llx\n", reg_header->magic_number); - pr_debug("NumCpuOffset: %x\n", reg_header->num_cpu_offset); + pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number)); + pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset)); - vaddr += reg_header->num_cpu_offset; - num_cpus = *((u32 *)(vaddr)); + vaddr += be32_to_cpu(reg_header->num_cpu_offset); + num_cpus = be32_to_cpu(*((__be32 *)(vaddr))); pr_debug("NumCpus : %u\n", num_cpus); vaddr += sizeof(u32); reg_entry = (struct fadump_reg_entry *)vaddr; @@ -639,13 +639,13 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) fdh = __va(fw_dump.fadumphdr_addr); for (i = 0; i < num_cpus; i++) { - if (reg_entry->reg_id != REG_ID("CPUSTRT")) { + if (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUSTRT")) { printk(KERN_ERR "Unable to read CPU state data\n"); rc = -ENOENT; goto error_out; } /* Lower 4 bytes of reg_value contains logical cpu id */ - cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK; + cpu = be64_to_cpu(reg_entry->reg_value) & FADUMP_CPU_ID_MASK; if (fdh && !cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) { SKIP_TO_NEXT_CPU(reg_entry); continue; @@ -692,7 +692,7 @@ static int __init process_fadump(const struct fadump_mem_struct *fdm_active) return -EINVAL; /* Check if the dump data is valid. */ - if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) || + if ((be16_to_cpu(fdm_active->header.dump_status_flag) == FADUMP_ERROR_FLAG) || (fdm_active->cpu_state_data.error_flags != 0) || (fdm_active->rmr_region.error_flags != 0)) { printk(KERN_ERR "Dump taken by platform is not valid\n"); @@ -828,7 +828,7 @@ static void fadump_setup_crash_memory_ranges(void) static inline unsigned long fadump_relocate(unsigned long paddr) { if (paddr > RMA_START && paddr < fw_dump.boot_memory_size) - return fdm.rmr_region.destination_address + paddr; + return be64_to_cpu(fdm.rmr_region.destination_address) + paddr; else return paddr; } @@ -902,7 +902,7 @@ static int fadump_create_elfcore_headers(char *bufp) * to the specified destination_address. Hence set * the correct offset. */ - phdr->p_offset = fdm.rmr_region.destination_address; + phdr->p_offset = be64_to_cpu(fdm.rmr_region.destination_address); } phdr->p_paddr = mbase; @@ -951,7 +951,7 @@ static void register_fadump(void) fadump_setup_crash_memory_ranges(); - addr = fdm.rmr_region.destination_address + fdm.rmr_region.source_len; + addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len); /* Initialize fadump crash info header. */ addr = init_fadump_header(addr); vaddr = __va(addr); @@ -1023,7 +1023,7 @@ void fadump_cleanup(void) /* Invalidate the registration only if dump is active. */ if (fw_dump.dump_active) { init_fadump_mem_struct(&fdm, - fdm_active->cpu_state_data.destination_address); + be64_to_cpu(fdm_active->cpu_state_data.destination_address)); fadump_invalidate_dump(&fdm); } } @@ -1063,7 +1063,7 @@ static void fadump_invalidate_release_mem(void) return; } - destination_address = fdm_active->cpu_state_data.destination_address; + destination_address = be64_to_cpu(fdm_active->cpu_state_data.destination_address); fadump_cleanup(); mutex_unlock(&fadump_mutex); @@ -1183,31 +1183,31 @@ static int fadump_region_show(struct seq_file *m, void *private) seq_printf(m, "CPU : [%#016llx-%#016llx] %#llx bytes, " "Dumped: %#llx\n", - fdm_ptr->cpu_state_data.destination_address, - fdm_ptr->cpu_state_data.destination_address + - fdm_ptr->cpu_state_data.source_len - 1, - fdm_ptr->cpu_state_data.source_len, - fdm_ptr->cpu_state_data.bytes_dumped); + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address), + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) + + be64_to_cpu(fdm_ptr->cpu_state_data.source_len) - 1, + be64_to_cpu(fdm_ptr->cpu_state_data.source_len), + be64_to_cpu(fdm_ptr->cpu_state_data.bytes_dumped)); seq_printf(m, "HPTE: [%#016llx-%#016llx] %#llx bytes, " "Dumped: %#llx\n", - fdm_ptr->hpte_region.destination_address, - fdm_ptr->hpte_region.destination_address + - fdm_ptr->hpte_region.source_len - 1, - fdm_ptr->hpte_region.source_len, - fdm_ptr->hpte_region.bytes_dumped); + be64_to_cpu(fdm_ptr->hpte_region.destination_address), + be64_to_cpu(fdm_ptr->hpte_region.destination_address) + + be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1, + be64_to_cpu(fdm_ptr->hpte_region.source_len), + be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped)); seq_printf(m, "DUMP: [%#016llx-%#016llx] %#llx bytes, " "Dumped: %#llx\n", - fdm_ptr->rmr_region.destination_address, - fdm_ptr->rmr_region.destination_address + - fdm_ptr->rmr_region.source_len - 1, - fdm_ptr->rmr_region.source_len, - fdm_ptr->rmr_region.bytes_dumped); + be64_to_cpu(fdm_ptr->rmr_region.destination_address), + be64_to_cpu(fdm_ptr->rmr_region.destination_address) + + be64_to_cpu(fdm_ptr->rmr_region.source_len) - 1, + be64_to_cpu(fdm_ptr->rmr_region.source_len), + be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped)); if (!fdm_active || (fw_dump.reserve_dump_area_start == - fdm_ptr->cpu_state_data.destination_address)) + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address))) goto out; /* Dump is active. Show reserved memory region. */ @@ -1215,10 +1215,10 @@ static int fadump_region_show(struct seq_file *m, void *private) " : [%#016llx-%#016llx] %#llx bytes, " "Dumped: %#llx\n", (unsigned long long)fw_dump.reserve_dump_area_start, - fdm_ptr->cpu_state_data.destination_address - 1, - fdm_ptr->cpu_state_data.destination_address - + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - 1, + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - fw_dump.reserve_dump_area_start, - fdm_ptr->cpu_state_data.destination_address - + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - fw_dump.reserve_dump_area_start); out: if (fdm_active) diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 8eb857f..c143835 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -466,7 +466,7 @@ static inline void check_stack_overflow(void) #ifdef CONFIG_DEBUG_STACKOVERFLOW long sp; - sp = __get_SP() & (THREAD_SIZE-1); + sp = current_stack_pointer() & (THREAD_SIZE-1); /* check for stack overflow: is there less than 2KB free? */ if (unlikely(sp < (sizeof(struct thread_info) + 2048))) { diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 7ce26d4..0d43219 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -114,3 +114,7 @@ _GLOBAL(longjmp) mtlr r0 mr r3,r4 blr + +_GLOBAL(current_stack_pointer) + PPC_LL r3,0(r1) + blr diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index c4dfff6..202963e 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -41,3 +41,5 @@ EXPORT_SYMBOL(giveup_spe); #ifdef CONFIG_EPAPR_PARAVIRT EXPORT_SYMBOL(epapr_hypercall_start); #endif + +EXPORT_SYMBOL(current_stack_pointer); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index aa1df89..923cd2d 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1545,7 +1545,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) tsk = current; if (sp == 0) { if (tsk == current) - asm("mr %0,1" : "=r" (sp)); + sp = current_stack_pointer(); else sp = tsk->thread.ksp; } diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index c168337..7c55b86 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -66,6 +66,11 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val) return PCIBIOS_DEVICE_NOT_FOUND; if (!config_access_valid(pdn, where)) return PCIBIOS_BAD_REGISTER_NUMBER; +#ifdef CONFIG_EEH + if (pdn->edev && pdn->edev->pe && + (pdn->edev->pe->state & EEH_PE_CFG_BLOCKED)) + return PCIBIOS_SET_FAILED; +#endif addr = rtas_config_addr(pdn->busno, pdn->devfn, where); buid = pdn->phb->buid; @@ -90,9 +95,6 @@ static int rtas_pci_read_config(struct pci_bus *bus, struct device_node *busdn, *dn; struct pci_dn *pdn; bool found = false; -#ifdef CONFIG_EEH - struct eeh_dev *edev; -#endif int ret; /* Search only direct children of the bus */ @@ -109,11 +111,6 @@ static int rtas_pci_read_config(struct pci_bus *bus, if (!found) return PCIBIOS_DEVICE_NOT_FOUND; -#ifdef CONFIG_EEH - edev = of_node_to_eeh_dev(dn); - if (edev && edev->pe && edev->pe->state & EEH_PE_RESET) - return PCIBIOS_DEVICE_NOT_FOUND; -#endif ret = rtas_read_config(pdn, where, size, val); if (*val == EEH_IO_ERROR_VALUE(size) && @@ -132,6 +129,11 @@ int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val) return PCIBIOS_DEVICE_NOT_FOUND; if (!config_access_valid(pdn, where)) return PCIBIOS_BAD_REGISTER_NUMBER; +#ifdef CONFIG_EEH + if (pdn->edev && pdn->edev->pe && + (pdn->edev->pe->state & EEH_PE_CFG_BLOCKED)) + return PCIBIOS_SET_FAILED; +#endif addr = rtas_config_addr(pdn->busno, pdn->devfn, where); buid = pdn->phb->buid; @@ -155,10 +157,6 @@ static int rtas_pci_write_config(struct pci_bus *bus, struct device_node *busdn, *dn; struct pci_dn *pdn; bool found = false; -#ifdef CONFIG_EEH - struct eeh_dev *edev; -#endif - int ret; /* Search only direct children of the bus */ busdn = pci_bus_to_OF_node(bus); @@ -173,14 +171,8 @@ static int rtas_pci_write_config(struct pci_bus *bus, if (!found) return PCIBIOS_DEVICE_NOT_FOUND; -#ifdef CONFIG_EEH - edev = of_node_to_eeh_dev(dn); - if (edev && edev->pe && (edev->pe->state & EEH_PE_RESET)) - return PCIBIOS_DEVICE_NOT_FOUND; -#endif - ret = rtas_write_config(pdn, where, size, val); - return ret; + return rtas_write_config(pdn, where, size, val); } static struct pci_ops rtas_pci_ops = { diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index cd07d79..4f3cfe1 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -522,36 +522,36 @@ void __init setup_system(void) smp_release_cpus(); #endif - printk("Starting Linux PPC64 %s\n", init_utsname()->version); + pr_info("Starting Linux PPC64 %s\n", init_utsname()->version); - printk("-----------------------------------------------------\n"); - printk("ppc64_pft_size = 0x%llx\n", ppc64_pft_size); - printk("phys_mem_size = 0x%llx\n", memblock_phys_mem_size()); + pr_info("-----------------------------------------------------\n"); + pr_info("ppc64_pft_size = 0x%llx\n", ppc64_pft_size); + pr_info("phys_mem_size = 0x%llx\n", memblock_phys_mem_size()); if (ppc64_caches.dline_size != 0x80) - printk("dcache_line_size = 0x%x\n", ppc64_caches.dline_size); + pr_info("dcache_line_size = 0x%x\n", ppc64_caches.dline_size); if (ppc64_caches.iline_size != 0x80) - printk("icache_line_size = 0x%x\n", ppc64_caches.iline_size); + pr_info("icache_line_size = 0x%x\n", ppc64_caches.iline_size); - printk("cpu_features = 0x%016lx\n", cur_cpu_spec->cpu_features); - printk(" possible = 0x%016lx\n", CPU_FTRS_POSSIBLE); - printk(" always = 0x%016lx\n", CPU_FTRS_ALWAYS); - printk("cpu_user_features = 0x%08x 0x%08x\n", cur_cpu_spec->cpu_user_features, + pr_info("cpu_features = 0x%016lx\n", cur_cpu_spec->cpu_features); + pr_info(" possible = 0x%016lx\n", CPU_FTRS_POSSIBLE); + pr_info(" always = 0x%016lx\n", CPU_FTRS_ALWAYS); + pr_info("cpu_user_features = 0x%08x 0x%08x\n", cur_cpu_spec->cpu_user_features, cur_cpu_spec->cpu_user_features2); - printk("mmu_features = 0x%08x\n", cur_cpu_spec->mmu_features); - printk("firmware_features = 0x%016lx\n", powerpc_firmware_features); + pr_info("mmu_features = 0x%08x\n", cur_cpu_spec->mmu_features); + pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features); #ifdef CONFIG_PPC_STD_MMU_64 if (htab_address) - printk("htab_address = 0x%p\n", htab_address); + pr_info("htab_address = 0x%p\n", htab_address); - printk("htab_hash_mask = 0x%lx\n", htab_hash_mask); + pr_info("htab_hash_mask = 0x%lx\n", htab_hash_mask); #endif if (PHYSICAL_START > 0) - printk("physical_start = 0x%llx\n", + pr_info("physical_start = 0x%llx\n", (unsigned long long)PHYSICAL_START); - printk("-----------------------------------------------------\n"); + pr_info("-----------------------------------------------------\n"); DBG(" <- setup_system()\n"); } diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 3d30ef1..ea43a34 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -50,7 +50,7 @@ void save_stack_trace(struct stack_trace *trace) { unsigned long sp; - asm("mr %0,1" : "=r" (sp)); + sp = current_stack_pointer(); save_context_stack(trace, sp, current, 1); } diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index 0f9939e..5a236f0 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -99,8 +99,6 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb) u64 vsid; int psize, ssize; - slb->esid = (ea & ESID_MASK) | SLB_ESID_V; - switch (REGION_ID(ea)) { case USER_REGION_ID: pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea); @@ -133,6 +131,7 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb) vsid |= mmu_psize_defs[psize].sllp | ((ssize == MMU_SEGSIZE_1T) ? SLB_VSID_B_1T : 0); + slb->esid = (ea & (ssize == MMU_SEGSIZE_1T ? ESID_MASK_1T : ESID_MASK)) | SLB_ESID_V; slb->vsid = vsid; return 0; diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index cad68ff..415a51b 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -103,7 +103,7 @@ unsigned long __max_low_memory = MAX_LOW_MEM; /* * Check for command-line options that affect what MMU_init will do. */ -void MMU_setup(void) +void __init MMU_setup(void) { /* Check for nobats option (used in mapin_ram). */ if (strstr(boot_command_line, "nobats")) { diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 649666d..b9d1dfd 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -8,6 +8,8 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "numa: " fmt + #include <linux/threads.h> #include <linux/bootmem.h> #include <linux/init.h> @@ -1153,6 +1155,22 @@ static int __init early_numa(char *p) } early_param("numa", early_numa); +static bool topology_updates_enabled = true; + +static int __init early_topology_updates(char *p) +{ + if (!p) + return 0; + + if (!strcmp(p, "off")) { + pr_info("Disabling topology updates\n"); + topology_updates_enabled = false; + } + + return 0; +} +early_param("topology_updates", early_topology_updates); + #ifdef CONFIG_MEMORY_HOTPLUG /* * Find the node associated with a hot added memory section for @@ -1442,8 +1460,11 @@ static long hcall_vphn(unsigned long cpu, __be32 *associativity) long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; u64 flags = 1; int hwcpu = get_hard_smp_processor_id(cpu); + int i; rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu); + for (i = 0; i < 6; i++) + retbuf[i] = cpu_to_be64(retbuf[i]); vphn_unpack_associativity(retbuf, associativity); return rc; @@ -1488,11 +1509,14 @@ static int update_cpu_topology(void *data) cpu = smp_processor_id(); for (update = data; update; update = update->next) { + int new_nid = update->new_nid; if (cpu != update->cpu) continue; - unmap_cpu_from_node(update->cpu); - map_cpu_to_node(update->cpu, update->new_nid); + unmap_cpu_from_node(cpu); + map_cpu_to_node(cpu, new_nid); + set_cpu_numa_node(cpu, new_nid); + set_cpu_numa_mem(cpu, local_memory_node(new_nid)); vdso_getcpu_init(); } @@ -1539,6 +1563,9 @@ int arch_update_cpu_topology(void) struct device *dev; int weight, new_nid, i = 0; + if (!prrn_enabled && !vphn_enabled) + return 0; + weight = cpumask_weight(&cpu_associativity_changes_mask); if (!weight) return 0; @@ -1592,6 +1619,15 @@ int arch_update_cpu_topology(void) cpu = cpu_last_thread_sibling(cpu); } + pr_debug("Topology update for the following CPUs:\n"); + if (cpumask_weight(&updated_cpus)) { + for (ud = &updates[0]; ud; ud = ud->next) { + pr_debug("cpu %d moving from node %d " + "to %d\n", ud->cpu, + ud->old_nid, ud->new_nid); + } + } + /* * In cases where we have nothing to update (because the updates list * is too short or because the new topology is same as the old one), @@ -1800,8 +1836,12 @@ static const struct file_operations topology_ops = { static int topology_update_init(void) { - start_topology_update(); - proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops); + /* Do not poll for changes if disabled at boot */ + if (topology_updates_enabled) + start_topology_update(); + + if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops)) + return -ENOMEM; return 0; } diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 8d7bda9..ded0ea1 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -682,6 +682,7 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start, slice_convert(mm, mask, psize); } +#ifdef CONFIG_HUGETLB_PAGE /* * is_hugepage_only_range() is used by generic code to verify whether * a normal mmap mapping (non hugetlbfs) is valid on a given area. @@ -726,4 +727,4 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, #endif return !slice_check_fit(mask, available); } - +#endif diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 6c8710d..dba3408 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -417,11 +417,6 @@ static int h_24x7_event_add(struct perf_event *event, int flags) return 0; } -static int h_24x7_event_idx(struct perf_event *event) -{ - return 0; -} - static struct pmu h_24x7_pmu = { .task_ctx_nr = perf_invalid_context, @@ -433,7 +428,6 @@ static struct pmu h_24x7_pmu = { .start = h_24x7_event_start, .stop = h_24x7_event_stop, .read = h_24x7_event_update, - .event_idx = h_24x7_event_idx, }; static int hv_24x7_init(void) diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 15fc76c..a051fe9 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -246,11 +246,6 @@ static int h_gpci_event_init(struct perf_event *event) return 0; } -static int h_gpci_event_idx(struct perf_event *event) -{ - return 0; -} - static struct pmu h_gpci_pmu = { .task_ctx_nr = perf_invalid_context, @@ -262,7 +257,6 @@ static struct pmu h_gpci_pmu = { .start = h_gpci_event_start, .stop = h_gpci_event_stop, .read = h_gpci_event_update, - .event_idx = h_gpci_event_idx, }; static int hv_gpci_init(void) diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index 426814a..eba9cb1 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -373,7 +373,7 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe) * moving forward, we have to return operational * state during PE reset. */ - if (pe->state & EEH_PE_RESET) { + if (pe->state & EEH_PE_CFG_BLOCKED) { result = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE | EEH_STATE_MMIO_ENABLED | diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 3e89cbf..1d19e79 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -169,6 +169,26 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) } /* + * If the PE contains any one of following adapters, the + * PCI config space can't be accessed when dumping EEH log. + * Otherwise, we will run into fenced PHB caused by shortage + * of outbound credits in the adapter. The PCI config access + * should be blocked until PE reset. MMIO access is dropped + * by hardware certainly. In order to drop PCI config requests, + * one more flag (EEH_PE_CFG_RESTRICTED) is introduced, which + * will be checked in the backend for PE state retrival. If + * the PE becomes frozen for the first time and the flag has + * been set for the PE, we will set EEH_PE_CFG_BLOCKED for + * that PE to block its config space. + * + * Broadcom Austin 4-ports NICs (14e4:1657) + * Broadcom Shiner 2-ports 10G NICs (14e4:168e) + */ + if ((dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x1657) || + (dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x168e)) + edev->pe->state |= EEH_PE_CFG_RESTRICTED; + + /* * Cache the PE primary bus, which can't be fetched when * full hotplug is in progress. In that case, all child * PCI devices of the PE are expected to be removed prior @@ -383,6 +403,39 @@ static int powernv_eeh_err_inject(struct eeh_pe *pe, int type, int func, return ret; } +static inline bool powernv_eeh_cfg_blocked(struct device_node *dn) +{ + struct eeh_dev *edev = of_node_to_eeh_dev(dn); + + if (!edev || !edev->pe) + return false; + + if (edev->pe->state & EEH_PE_CFG_BLOCKED) + return true; + + return false; +} + +static int powernv_eeh_read_config(struct device_node *dn, + int where, int size, u32 *val) +{ + if (powernv_eeh_cfg_blocked(dn)) { + *val = 0xFFFFFFFF; + return PCIBIOS_SET_FAILED; + } + + return pnv_pci_cfg_read(dn, where, size, val); +} + +static int powernv_eeh_write_config(struct device_node *dn, + int where, int size, u32 val) +{ + if (powernv_eeh_cfg_blocked(dn)) + return PCIBIOS_SET_FAILED; + + return pnv_pci_cfg_write(dn, where, size, val); +} + /** * powernv_eeh_next_error - Retrieve next EEH error to handle * @pe: Affected PE @@ -440,8 +493,8 @@ static struct eeh_ops powernv_eeh_ops = { .get_log = powernv_eeh_get_log, .configure_bridge = powernv_eeh_configure_bridge, .err_inject = powernv_eeh_err_inject, - .read_config = pnv_pci_cfg_read, - .write_config = pnv_pci_cfg_write, + .read_config = powernv_eeh_read_config, + .write_config = powernv_eeh_write_config, .next_error = powernv_eeh_next_error, .restore_config = powernv_eeh_restore_config }; diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c index dd2c285..e4169d6 100644 --- a/arch/powerpc/platforms/powernv/opal-lpc.c +++ b/arch/powerpc/platforms/powernv/opal-lpc.c @@ -191,7 +191,6 @@ static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf, { struct lpc_debugfs_entry *lpc = filp->private_data; u32 data, pos, len, todo; - __be32 bedata; int rc; if (!access_ok(VERIFY_WRITE, ubuf, count)) @@ -214,18 +213,57 @@ static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf, len = 2; } rc = opal_lpc_read(opal_lpc_chip_id, lpc->lpc_type, pos, - &bedata, len); + &data, len); if (rc) return -ENXIO; - data = be32_to_cpu(bedata); + + /* + * Now there is some trickery with the data returned by OPAL + * as it's the desired data right justified in a 32-bit BE + * word. + * + * This is a very bad interface and I'm to blame for it :-( + * + * So we can't just apply a 32-bit swap to what comes from OPAL, + * because user space expects the *bytes* to be in their proper + * respective positions (ie, LPC position). + * + * So what we really want to do here is to shift data right + * appropriately on a LE kernel. + * + * IE. If the LPC transaction has bytes B0, B1, B2 and B3 in that + * order, we have in memory written to by OPAL at the "data" + * pointer: + * + * Bytes: OPAL "data" LE "data" + * 32-bit: B0 B1 B2 B3 B0B1B2B3 B3B2B1B0 + * 16-bit: B0 B1 0000B0B1 B1B00000 + * 8-bit: B0 000000B0 B0000000 + * + * So a BE kernel will have the leftmost of the above in the MSB + * and rightmost in the LSB and can just then "cast" the u32 "data" + * down to the appropriate quantity and write it. + * + * However, an LE kernel can't. It doesn't need to swap because a + * load from data followed by a store to user are going to preserve + * the byte ordering which is the wire byte order which is what the + * user wants, but in order to "crop" to the right size, we need to + * shift right first. + */ switch(len) { case 4: rc = __put_user((u32)data, (u32 __user *)ubuf); break; case 2: +#ifdef __LITTLE_ENDIAN__ + data >>= 16; +#endif rc = __put_user((u16)data, (u16 __user *)ubuf); break; default: +#ifdef __LITTLE_ENDIAN__ + data >>= 24; +#endif rc = __put_user((u8)data, (u8 __user *)ubuf); break; } @@ -265,12 +303,31 @@ static ssize_t lpc_debug_write(struct file *filp, const char __user *ubuf, else if (todo > 1 && (pos & 1) == 0) len = 2; } + + /* + * Similarly to the read case, we have some trickery here but + * it's different to handle. We need to pass the value to OPAL in + * a register whose layout depends on the access size. We want + * to reproduce the memory layout of the user, however we aren't + * doing a load from user and a store to another memory location + * which would achieve that. Here we pass the value to OPAL via + * a register which is expected to contain the "BE" interpretation + * of the byte sequence. IE: for a 32-bit access, byte 0 should be + * in the MSB. So here we *do* need to byteswap on LE. + * + * User bytes: LE "data" OPAL "data" + * 32-bit: B0 B1 B2 B3 B3B2B1B0 B0B1B2B3 + * 16-bit: B0 B1 0000B1B0 0000B0B1 + * 8-bit: B0 000000B0 000000B0 + */ switch(len) { case 4: rc = __get_user(data, (u32 __user *)ubuf); + data = cpu_to_be32(data); break; case 2: rc = __get_user(data, (u16 __user *)ubuf); + data = cpu_to_be16(data); break; default: rc = __get_user(data, (u8 __user *)ubuf); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index e9e2450..feb549a 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -58,7 +58,7 @@ END_FTR_SECTION(0, 1); \ */ #define OPAL_CALL(name, token) \ - _GLOBAL(name); \ + _GLOBAL_TOC(name); \ mflr r0; \ std r0,16(r1); \ li r0,token; \ diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index b642b05..d019b08 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -194,6 +194,27 @@ static int __init opal_register_exception_handlers(void) * fwnmi area at 0x7000 to provide the glue space to OPAL */ glue = 0x7000; + + /* + * Check if we are running on newer firmware that exports + * OPAL_HANDLE_HMI token. If yes, then don't ask OPAL to patch + * the HMI interrupt and we catch it directly in Linux. + * + * For older firmware (i.e currently released POWER8 System Firmware + * as of today <= SV810_087), we fallback to old behavior and let OPAL + * patch the HMI vector and handle it inside OPAL firmware. + * + * For newer firmware (in development/yet to be released) we will + * start catching/handling HMI directly in Linux. + */ + if (!opal_check_token(OPAL_HANDLE_HMI)) { + pr_info("opal: Old firmware detected, OPAL handles HMIs.\n"); + opal_register_exception_handler( + OPAL_HYPERVISOR_MAINTENANCE_HANDLER, + 0, glue); + glue += 128; + } + opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue); #endif diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b3ca77d..b2187d0 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -505,7 +505,7 @@ static bool pnv_pci_cfg_check(struct pci_controller *hose, edev = of_node_to_eeh_dev(dn); if (edev) { if (edev->pe && - (edev->pe->state & EEH_PE_RESET)) + (edev->pe->state & EEH_PE_CFG_BLOCKED)) return false; if (edev->mode & EEH_DEV_REMOVED) diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index fdf01b6..c22bb1b 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -25,11 +25,11 @@ #include <asm/rtas.h> struct cc_workarea { - u32 drc_index; - u32 zero; - u32 name_offset; - u32 prop_length; - u32 prop_offset; + __be32 drc_index; + __be32 zero; + __be32 name_offset; + __be32 prop_length; + __be32 prop_offset; }; void dlpar_free_cc_property(struct property *prop) @@ -49,11 +49,11 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa) if (!prop) return NULL; - name = (char *)ccwa + ccwa->name_offset; + name = (char *)ccwa + be32_to_cpu(ccwa->name_offset); prop->name = kstrdup(name, GFP_KERNEL); - prop->length = ccwa->prop_length; - value = (char *)ccwa + ccwa->prop_offset; + prop->length = be32_to_cpu(ccwa->prop_length); + value = (char *)ccwa + be32_to_cpu(ccwa->prop_offset); prop->value = kmemdup(value, prop->length, GFP_KERNEL); if (!prop->value) { dlpar_free_cc_property(prop); @@ -79,7 +79,7 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa, if (!dn) return NULL; - name = (char *)ccwa + ccwa->name_offset; + name = (char *)ccwa + be32_to_cpu(ccwa->name_offset); dn->full_name = kasprintf(GFP_KERNEL, "%s/%s", path, name); if (!dn->full_name) { kfree(dn); @@ -126,7 +126,7 @@ void dlpar_free_cc_nodes(struct device_node *dn) #define CALL_AGAIN -2 #define ERR_CFG_USE -9003 -struct device_node *dlpar_configure_connector(u32 drc_index, +struct device_node *dlpar_configure_connector(__be32 drc_index, struct device_node *parent) { struct device_node *dn; @@ -382,7 +382,7 @@ static int dlpar_online_cpu(struct device_node *dn) BUG_ON(get_cpu_current_state(cpu) != CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_up(cpu); + rc = device_online(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); @@ -414,7 +414,7 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count) if (!parent) return -ENODEV; - dn = dlpar_configure_connector(drc_index, parent); + dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent); if (!dn) return -EINVAL; @@ -467,7 +467,7 @@ static int dlpar_offline_cpu(struct device_node *dn) if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_down(cpu); + rc = device_offline(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index b174fa7..5c375f9 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -247,7 +247,7 @@ static int pseries_add_processor(struct device_node *np) unsigned int cpu; cpumask_var_t candidate_mask, tmp; int err = -ENOSPC, len, nthreads, i; - const u32 *intserv; + const __be32 *intserv; intserv = of_get_property(np, "ibm,ppc-interrupt-server#s", &len); if (!intserv) @@ -293,7 +293,7 @@ static int pseries_add_processor(struct device_node *np) for_each_cpu(cpu, tmp) { BUG_ON(cpu_present(cpu)); set_cpu_present(cpu, true); - set_hard_smp_processor_id(cpu, *intserv++); + set_hard_smp_processor_id(cpu, be32_to_cpu(*intserv++)); } err = 0; out_unlock: diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index de1ec54..e32e009 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -30,7 +30,6 @@ #include <linux/mm.h> #include <linux/memblock.h> #include <linux/spinlock.h> -#include <linux/sched.h> /* for show_stack */ #include <linux/string.h> #include <linux/pci.h> #include <linux/dma-mapping.h> @@ -168,7 +167,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, printk("\tindex = 0x%llx\n", (u64)tbl->it_index); printk("\ttcenum = 0x%llx\n", (u64)tcenum); printk("\ttce val = 0x%llx\n", tce ); - show_stack(current, (unsigned long *)__get_SP()); + dump_stack(); } tcenum++; @@ -257,7 +256,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, printk("\tindex = 0x%llx\n", (u64)tbl->it_index); printk("\tnpages = 0x%llx\n", (u64)npages); printk("\ttce[0] val = 0x%llx\n", tcep[0]); - show_stack(current, (unsigned long *)__get_SP()); + dump_stack(); } return ret; } @@ -273,7 +272,7 @@ static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc); printk("\tindex = 0x%llx\n", (u64)tbl->it_index); printk("\ttcenum = 0x%llx\n", (u64)tcenum); - show_stack(current, (unsigned long *)__get_SP()); + dump_stack(); } tcenum++; @@ -292,7 +291,7 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n printk("\trc = %lld\n", rc); printk("\tindex = 0x%llx\n", (u64)tbl->it_index); printk("\tnpages = 0x%llx\n", (u64)npages); - show_stack(current, (unsigned long *)__get_SP()); + dump_stack(); } } @@ -307,7 +306,7 @@ static unsigned long tce_get_pSeriesLP(struct iommu_table *tbl, long tcenum) printk("tce_get_pSeriesLP: plpar_tce_get failed. rc=%lld\n", rc); printk("\tindex = 0x%llx\n", (u64)tbl->it_index); printk("\ttcenum = 0x%llx\n", (u64)tcenum); - show_stack(current, (unsigned long *)__get_SP()); + dump_stack(); } return tce_ret; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 8c509d5..f6880d2 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -43,6 +43,7 @@ #include <asm/trace.h> #include <asm/firmware.h> #include <asm/plpar_wrappers.h> +#include <asm/fadump.h> #include "pseries.h" @@ -247,8 +248,17 @@ static void pSeries_lpar_hptab_clear(void) } #ifdef __LITTLE_ENDIAN__ - /* Reset exceptions to big endian */ - if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* + * Reset exceptions to big endian. + * + * FIXME this is a hack for kexec, we need to reset the exception + * endian before starting the new kernel and this is a convenient place + * to do it. + * + * This is also called on boot when a fadump happens. In that case we + * must not change the exception endian mode. + */ + if (firmware_has_feature(FW_FEATURE_SET_MODE) && !is_fadump_active()) { long rc; rc = pseries_big_endian_exceptions(); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 361add6..1796c54 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -56,7 +56,8 @@ extern void hvc_vio_init_early(void); /* Dynamic logical Partitioning/Mobility */ extern void dlpar_free_cc_nodes(struct device_node *); extern void dlpar_free_cc_property(struct property *); -extern struct device_node *dlpar_configure_connector(u32, struct device_node *); +extern struct device_node *dlpar_configure_connector(__be32, + struct device_node *); extern int dlpar_attach_node(struct device_node *); extern int dlpar_detach_node(struct device_node *); diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index 0c75214..73b64c7 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -145,59 +145,64 @@ void msi_bitmap_free(struct msi_bitmap *bmp) #ifdef CONFIG_MSI_BITMAP_SELFTEST -#define check(x) \ - if (!(x)) printk("msi_bitmap: test failed at line %d\n", __LINE__); - static void __init test_basics(void) { struct msi_bitmap bmp; - int i, size = 512; + int rc, i, size = 512; /* Can't allocate a bitmap of 0 irqs */ - check(msi_bitmap_alloc(&bmp, 0, NULL) != 0); + WARN_ON(msi_bitmap_alloc(&bmp, 0, NULL) == 0); /* of_node may be NULL */ - check(0 == msi_bitmap_alloc(&bmp, size, NULL)); + WARN_ON(msi_bitmap_alloc(&bmp, size, NULL)); /* Should all be free by default */ - check(0 == bitmap_find_free_region(bmp.bitmap, size, - get_count_order(size))); + WARN_ON(bitmap_find_free_region(bmp.bitmap, size, get_count_order(size))); bitmap_release_region(bmp.bitmap, 0, get_count_order(size)); /* With no node, there's no msi-available-ranges, so expect > 0 */ - check(msi_bitmap_reserve_dt_hwirqs(&bmp) > 0); + WARN_ON(msi_bitmap_reserve_dt_hwirqs(&bmp) <= 0); /* Should all still be free */ - check(0 == bitmap_find_free_region(bmp.bitmap, size, - get_count_order(size))); + WARN_ON(bitmap_find_free_region(bmp.bitmap, size, get_count_order(size))); bitmap_release_region(bmp.bitmap, 0, get_count_order(size)); /* Check we can fill it up and then no more */ for (i = 0; i < size; i++) - check(msi_bitmap_alloc_hwirqs(&bmp, 1) >= 0); + WARN_ON(msi_bitmap_alloc_hwirqs(&bmp, 1) < 0); - check(msi_bitmap_alloc_hwirqs(&bmp, 1) < 0); + WARN_ON(msi_bitmap_alloc_hwirqs(&bmp, 1) >= 0); /* Should all be allocated */ - check(bitmap_find_free_region(bmp.bitmap, size, 0) < 0); + WARN_ON(bitmap_find_free_region(bmp.bitmap, size, 0) >= 0); /* And if we free one we can then allocate another */ msi_bitmap_free_hwirqs(&bmp, size / 2, 1); - check(msi_bitmap_alloc_hwirqs(&bmp, 1) == size / 2); + WARN_ON(msi_bitmap_alloc_hwirqs(&bmp, 1) != size / 2); + + /* Free most of them for the alignment tests */ + msi_bitmap_free_hwirqs(&bmp, 3, size - 3); /* Check we get a naturally aligned offset */ - check(msi_bitmap_alloc_hwirqs(&bmp, 2) % 2 == 0); - check(msi_bitmap_alloc_hwirqs(&bmp, 4) % 4 == 0); - check(msi_bitmap_alloc_hwirqs(&bmp, 8) % 8 == 0); - check(msi_bitmap_alloc_hwirqs(&bmp, 9) % 16 == 0); - check(msi_bitmap_alloc_hwirqs(&bmp, 3) % 4 == 0); - check(msi_bitmap_alloc_hwirqs(&bmp, 7) % 8 == 0); - check(msi_bitmap_alloc_hwirqs(&bmp, 121) % 128 == 0); + rc = msi_bitmap_alloc_hwirqs(&bmp, 2); + WARN_ON(rc < 0 && rc % 2 != 0); + rc = msi_bitmap_alloc_hwirqs(&bmp, 4); + WARN_ON(rc < 0 && rc % 4 != 0); + rc = msi_bitmap_alloc_hwirqs(&bmp, 8); + WARN_ON(rc < 0 && rc % 8 != 0); + rc = msi_bitmap_alloc_hwirqs(&bmp, 9); + WARN_ON(rc < 0 && rc % 16 != 0); + rc = msi_bitmap_alloc_hwirqs(&bmp, 3); + WARN_ON(rc < 0 && rc % 4 != 0); + rc = msi_bitmap_alloc_hwirqs(&bmp, 7); + WARN_ON(rc < 0 && rc % 8 != 0); + rc = msi_bitmap_alloc_hwirqs(&bmp, 121); + WARN_ON(rc < 0 && rc % 128 != 0); msi_bitmap_free(&bmp); - /* Clients may check bitmap == NULL for "not-allocated" */ - check(bmp.bitmap == NULL); + /* Clients may WARN_ON bitmap == NULL for "not-allocated" */ + WARN_ON(bmp.bitmap != NULL); kfree(bmp.bitmap); } @@ -219,14 +224,13 @@ static void __init test_of_node(void) of_node_init(&of_node); of_node.full_name = node_name; - check(0 == msi_bitmap_alloc(&bmp, size, &of_node)); + WARN_ON(msi_bitmap_alloc(&bmp, size, &of_node)); /* No msi-available-ranges, so expect > 0 */ - check(msi_bitmap_reserve_dt_hwirqs(&bmp) > 0); + WARN_ON(msi_bitmap_reserve_dt_hwirqs(&bmp) <= 0); /* Should all still be free */ - check(0 == bitmap_find_free_region(bmp.bitmap, size, - get_count_order(size))); + WARN_ON(bitmap_find_free_region(bmp.bitmap, size, get_count_order(size))); bitmap_release_region(bmp.bitmap, 0, get_count_order(size)); /* Now create a fake msi-available-ranges property */ @@ -240,11 +244,11 @@ static void __init test_of_node(void) of_node.properties = ∝ /* msi-available-ranges, so expect == 0 */ - check(msi_bitmap_reserve_dt_hwirqs(&bmp) == 0); + WARN_ON(msi_bitmap_reserve_dt_hwirqs(&bmp)); /* Check we got the expected result */ - check(0 == bitmap_parselist(expected_str, expected, size)); - check(bitmap_equal(expected, bmp.bitmap, size)); + WARN_ON(bitmap_parselist(expected_str, expected, size)); + WARN_ON(!bitmap_equal(expected, bmp.bitmap, size)); msi_bitmap_free(&bmp); kfree(bmp.bitmap); |