diff options
83 files changed, 2206 insertions, 687 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index b44b52c0a8f0..f0a893142cee 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -209,9 +209,6 @@ config DEFAULT_UIMAGE Used to allow a board to specify it wants a uImage built by default default n -config REDBOOT - bool - config ARCH_HIBERNATION_POSSIBLE bool default y @@ -379,6 +376,12 @@ config ARCH_HAS_WALK_MEMORY config ARCH_ENABLE_MEMORY_HOTREMOVE def_bool y +config PPC64_SUPPORTS_MEMORY_FAILURE + bool "Add support for memory hwpoison" + depends on PPC_BOOK3S_64 + default "y" if PPC_POWERNV + select ARCH_SUPPORTS_MEMORY_FAILURE + config KEXEC bool "kexec system call" depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP)) diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore index 554734ff302e..d61c03525777 100644 --- a/arch/powerpc/boot/.gitignore +++ b/arch/powerpc/boot/.gitignore @@ -16,6 +16,7 @@ mktree uImage cuImage.* dtbImage.* +*.dtb treeImage.* zImage zImage.initrd diff --git a/arch/powerpc/boot/dts/kilauea.dts b/arch/powerpc/boot/dts/kilauea.dts index 1613d6e4049e..5ba7f01e2a29 100644 --- a/arch/powerpc/boot/dts/kilauea.dts +++ b/arch/powerpc/boot/dts/kilauea.dts @@ -406,7 +406,7 @@ MSI: ppc4xx-msi@C10000000 { compatible = "amcc,ppc4xx-msi", "ppc4xx-msi"; - reg = < 0x0 0xEF620000 0x100>; + reg = <0xEF620000 0x100>; sdr-base = <0x4B0>; msi-data = <0x00000000>; msi-mask = <0x44440000>; diff --git a/arch/powerpc/boot/dts/virtex440-ml507.dts b/arch/powerpc/boot/dts/virtex440-ml507.dts index fc7073bc547e..391a4e299783 100644 --- a/arch/powerpc/boot/dts/virtex440-ml507.dts +++ b/arch/powerpc/boot/dts/virtex440-ml507.dts @@ -257,6 +257,8 @@ #size-cells = <1>; compatible = "xlnx,compound"; ethernet@81c00000 { + #address-cells = <1>; + #size-cells = <0>; compatible = "xlnx,xps-ll-temac-1.01.b"; device_type = "network"; interrupt-parent = <&xps_intc_0>; diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 910194e9a1e2..a5e9a7d494d8 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -46,6 +46,11 @@ #include <asm/asm-compat.h> #include <asm/synch.h> +/* PPC bit number conversion */ +#define PPC_BITLSHIFT(be) (BITS_PER_LONG - 1 - (be)) +#define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit)) +#define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs)) + /* * clear_bit doesn't imply a memory barrier */ diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 9e495c9a6a88..ed0afc1e44a4 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -41,8 +41,20 @@ struct ppc64_caches { extern struct ppc64_caches ppc64_caches; #endif /* __powerpc64__ && ! __ASSEMBLY__ */ -#if !defined(__ASSEMBLY__) +#if defined(__ASSEMBLY__) +/* + * For a snooping icache, we still need a dummy icbi to purge all the + * prefetched instructions from the ifetch buffers. We also need a sync + * before the icbi to order the the actual stores to memory that might + * have modified instructions with the icbi. + */ +#define PURGE_PREFETCHED_INS \ + sync; \ + icbi 0,r3; \ + sync; \ + isync +#else #define __read_mostly __attribute__((__section__(".data..read_mostly"))) #ifdef CONFIG_6xx diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index a6f8c7a5cbb7..97e02f985df8 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -34,6 +34,13 @@ int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr); unsigned long branch_target(const unsigned int *instr); unsigned int translate_branch(const unsigned int *dest, const unsigned int *src); +#ifdef CONFIG_PPC_BOOK3E_64 +void __patch_exception(int exc, unsigned long addr); +#define patch_exception(exc, name) do { \ + extern unsigned int name; \ + __patch_exception((exc), (unsigned long)&name); \ +} while (0) +#endif static inline unsigned long ppc_function_entry(void *func) { diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 0d4939ba48e7..617cc767c076 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -90,6 +90,18 @@ struct cpu_spec { * if the error is fatal, 1 if it was fully recovered and 0 to * pass up (not CPU originated) */ int (*machine_check)(struct pt_regs *regs); + + /* + * Processor specific early machine check handler which is + * called in real mode to handle SLB and TLB errors. + */ + long (*machine_check_early)(struct pt_regs *regs); + + /* + * Processor specific routine to flush tlbs. + */ + void (*flush_tlb)(unsigned long inval_selector); + }; extern struct cpu_spec *cur_cpu_spec; diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 243ce69ad685..66830618cc19 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -301,9 +301,12 @@ do_kvm_##n: \ beq 4f; /* if from kernel mode */ \ ACCOUNT_CPU_USER_ENTRY(r9, r10); \ SAVE_PPR(area, r9, r10); \ -4: std r2,GPR2(r1); /* save r2 in stackframe */ \ - SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ - SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ +4: EXCEPTION_PROLOG_COMMON_2(area) \ + EXCEPTION_PROLOG_COMMON_3(n) \ + ACCOUNT_STOLEN_TIME + +/* Save original regs values from save area to stack frame. */ +#define EXCEPTION_PROLOG_COMMON_2(area) \ ld r9,area+EX_R9(r13); /* move r9, r10 to stackframe */ \ ld r10,area+EX_R10(r13); \ std r9,GPR9(r1); \ @@ -318,11 +321,16 @@ do_kvm_##n: \ ld r10,area+EX_CFAR(r13); \ std r10,ORIG_GPR3(r1); \ END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66); \ + GET_CTR(r10, area); \ + std r10,_CTR(r1); + +#define EXCEPTION_PROLOG_COMMON_3(n) \ + std r2,GPR2(r1); /* save r2 in stackframe */ \ + SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ + SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ mflr r9; /* Get LR, later save to stack */ \ ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ std r9,_LINK(r1); \ - GET_CTR(r10, area); \ - std r10,_CTR(r1); \ lbz r10,PACASOFTIRQEN(r13); \ mfspr r11,SPRN_XER; /* save XER in stackframe */ \ std r10,SOFTE(r1); \ @@ -332,8 +340,7 @@ do_kvm_##n: \ li r10,0; \ ld r11,exception_marker@toc(r2); \ std r10,RESULT(r1); /* clear regs->result */ \ - std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ \ - ACCOUNT_STOLEN_TIME + std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ /* * Exception vectors. diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index 3bdcfce2c42a..418fb654370d 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -6,7 +6,8 @@ typedef struct { unsigned int __softirq_pending; - unsigned int timer_irqs; + unsigned int timer_irqs_event; + unsigned int timer_irqs_others; unsigned int pmu_irqs; unsigned int mce_exceptions; unsigned int spurious_irqs; diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 575fbf81fad0..97d3869991ca 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -191,8 +191,24 @@ DEF_MMIO_OUT_D(out_le32, 32, stw); #endif /* __BIG_ENDIAN */ +/* + * Cache inhibitied accessors for use in real mode, you don't want to use these + * unless you know what you're doing. + * + * NB. These use the cpu byte ordering. + */ +DEF_MMIO_OUT_X(out_rm8, 8, stbcix); +DEF_MMIO_OUT_X(out_rm16, 16, sthcix); +DEF_MMIO_OUT_X(out_rm32, 32, stwcix); +DEF_MMIO_IN_X(in_rm8, 8, lbzcix); +DEF_MMIO_IN_X(in_rm16, 16, lhzcix); +DEF_MMIO_IN_X(in_rm32, 32, lwzcix); + #ifdef __powerpc64__ +DEF_MMIO_OUT_X(out_rm64, 64, stdcix); +DEF_MMIO_IN_X(in_rm64, 64, ldcix); + #ifdef __BIG_ENDIAN__ DEF_MMIO_OUT_D(out_be64, 64, std); DEF_MMIO_IN_D(in_be64, 64, ld); diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index c34656a8925e..f7a8036579b5 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -30,22 +30,19 @@ #include <asm/machdep.h> #include <asm/types.h> -#define IOMMU_PAGE_SHIFT 12 -#define IOMMU_PAGE_SIZE (ASM_CONST(1) << IOMMU_PAGE_SHIFT) -#define IOMMU_PAGE_MASK (~((1 << IOMMU_PAGE_SHIFT) - 1)) -#define IOMMU_PAGE_ALIGN(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE) +#define IOMMU_PAGE_SHIFT_4K 12 +#define IOMMU_PAGE_SIZE_4K (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K) +#define IOMMU_PAGE_MASK_4K (~((1 << IOMMU_PAGE_SHIFT_4K) - 1)) +#define IOMMU_PAGE_ALIGN_4K(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE_4K) + +#define IOMMU_PAGE_SIZE(tblptr) (ASM_CONST(1) << (tblptr)->it_page_shift) +#define IOMMU_PAGE_MASK(tblptr) (~((1 << (tblptr)->it_page_shift) - 1)) +#define IOMMU_PAGE_ALIGN(addr, tblptr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE(tblptr)) /* Boot time flags */ extern int iommu_is_off; extern int iommu_force_on; -/* Pure 2^n version of get_order */ -static __inline__ __attribute_const__ int get_iommu_order(unsigned long size) -{ - return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT) + 1; -} - - /* * IOMAP_MAX_ORDER defines the largest contiguous block * of dma space we can get. IOMAP_MAX_ORDER = 13 @@ -76,11 +73,20 @@ struct iommu_table { struct iommu_pool large_pool; struct iommu_pool pools[IOMMU_NR_POOLS]; unsigned long *it_map; /* A simple allocation bitmap for now */ + unsigned long it_page_shift;/* table iommu page size */ #ifdef CONFIG_IOMMU_API struct iommu_group *it_group; #endif }; +/* Pure 2^n version of get_order */ +static inline __attribute_const__ +int get_iommu_order(unsigned long size, struct iommu_table *tbl) +{ + return __ilog2((size - 1) >> tbl->it_page_shift) + 1; +} + + struct scatterlist; static inline void set_iommu_table_base(struct device *dev, void *base) @@ -101,8 +107,34 @@ extern void iommu_free_table(struct iommu_table *tbl, const char *node_name); */ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, int nid); +#ifdef CONFIG_IOMMU_API extern void iommu_register_group(struct iommu_table *tbl, int pci_domain_number, unsigned long pe_num); +extern int iommu_add_device(struct device *dev); +extern void iommu_del_device(struct device *dev); +#else +static inline void iommu_register_group(struct iommu_table *tbl, + int pci_domain_number, + unsigned long pe_num) +{ +} + +static inline int iommu_add_device(struct device *dev) +{ + return 0; +} + +static inline void iommu_del_device(struct device *dev) +{ +} +#endif /* !CONFIG_IOMMU_API */ + +static inline void set_iommu_table_base_and_group(struct device *dev, + void *base) +{ + set_iommu_table_base(dev, base); + iommu_add_device(dev); +} extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl, struct scatterlist *sglist, int nelems, diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 844c28de7ec0..d0a2a2f99564 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -132,8 +132,6 @@ struct slb_shadow { } save_area[SLB_NUM_BOLTED]; } ____cacheline_aligned; -extern struct slb_shadow slb_shadow[]; - /* * Layout of entries in the hypervisor's dispatch trace log buffer. */ diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h new file mode 100644 index 000000000000..a2b8c7b35fba --- /dev/null +++ b/arch/powerpc/include/asm/mce.h @@ -0,0 +1,198 @@ +/* + * Machine check exception header file. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright 2013 IBM Corporation + * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> + */ + +#ifndef __ASM_PPC64_MCE_H__ +#define __ASM_PPC64_MCE_H__ + +#include <linux/bitops.h> + +/* + * Machine Check bits on power7 and power8 + */ +#define P7_SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42)) /* P8 too */ + +/* SRR1 bits for machine check (On Power7 and Power8) */ +#define P7_SRR1_MC_IFETCH(srr1) ((srr1) & PPC_BITMASK(43, 45)) /* P8 too */ + +#define P7_SRR1_MC_IFETCH_UE (0x1 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_SLB_PARITY (0x2 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_SLB_MULTIHIT (0x3 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_SLB_BOTH (0x4 << PPC_BITLSHIFT(45)) +#define P7_SRR1_MC_IFETCH_TLB_MULTIHIT (0x5 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_UE_TLB_RELOAD (0x6 << PPC_BITLSHIFT(45)) /* P8 too */ +#define P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL (0x7 << PPC_BITLSHIFT(45)) + +/* SRR1 bits for machine check (On Power8) */ +#define P8_SRR1_MC_IFETCH_ERAT_MULTIHIT (0x4 << PPC_BITLSHIFT(45)) + +/* DSISR bits for machine check (On Power7 and Power8) */ +#define P7_DSISR_MC_UE (PPC_BIT(48)) /* P8 too */ +#define P7_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) /* P8 too */ +#define P7_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) /* P8 too */ +#define P7_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) /* P8 too */ +#define P7_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) /* P8 too */ +#define P7_DSISR_MC_SLB_MULTIHIT (PPC_BIT(56)) /* P8 too */ +#define P7_DSISR_MC_SLB_MULTIHIT_PARITY (PPC_BIT(57)) /* P8 too */ + +/* + * DSISR bits for machine check (Power8) in addition to above. + * Secondary DERAT Multihit + */ +#define P8_DSISR_MC_ERAT_MULTIHIT_SEC (PPC_BIT(54)) + +/* SLB error bits */ +#define P7_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_ERAT_MULTIHIT | \ + P7_DSISR_MC_SLB_PARITY_MFSLB | \ + P7_DSISR_MC_SLB_MULTIHIT | \ + P7_DSISR_MC_SLB_MULTIHIT_PARITY) + +#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \ + P8_DSISR_MC_ERAT_MULTIHIT_SEC) +enum MCE_Version { + MCE_V1 = 1, +}; + +enum MCE_Severity { + MCE_SEV_NO_ERROR = 0, + MCE_SEV_WARNING = 1, + MCE_SEV_ERROR_SYNC = 2, + MCE_SEV_FATAL = 3, +}; + +enum MCE_Disposition { + MCE_DISPOSITION_RECOVERED = 0, + MCE_DISPOSITION_NOT_RECOVERED = 1, +}; + +enum MCE_Initiator { + MCE_INITIATOR_UNKNOWN = 0, + MCE_INITIATOR_CPU = 1, +}; + +enum MCE_ErrorType { + MCE_ERROR_TYPE_UNKNOWN = 0, + MCE_ERROR_TYPE_UE = 1, + MCE_ERROR_TYPE_SLB = 2, + MCE_ERROR_TYPE_ERAT = 3, + MCE_ERROR_TYPE_TLB = 4, +}; + +enum MCE_UeErrorType { + MCE_UE_ERROR_INDETERMINATE = 0, + MCE_UE_ERROR_IFETCH = 1, + MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH = 2, + MCE_UE_ERROR_LOAD_STORE = 3, + MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 4, +}; + +enum MCE_SlbErrorType { + MCE_SLB_ERROR_INDETERMINATE = 0, + MCE_SLB_ERROR_PARITY = 1, + MCE_SLB_ERROR_MULTIHIT = 2, +}; + +enum MCE_EratErrorType { + MCE_ERAT_ERROR_INDETERMINATE = 0, + MCE_ERAT_ERROR_PARITY = 1, + MCE_ERAT_ERROR_MULTIHIT = 2, +}; + +enum MCE_TlbErrorType { + MCE_TLB_ERROR_INDETERMINATE = 0, + MCE_TLB_ERROR_PARITY = 1, + MCE_TLB_ERROR_MULTIHIT = 2, +}; + +struct machine_check_event { + enum MCE_Version version:8; /* 0x00 */ + uint8_t in_use; /* 0x01 */ + enum MCE_Severity severity:8; /* 0x02 */ + enum MCE_Initiator initiator:8; /* 0x03 */ + enum MCE_ErrorType error_type:8; /* 0x04 */ + enum MCE_Disposition disposition:8; /* 0x05 */ + uint8_t reserved_1[2]; /* 0x06 */ + uint64_t gpr3; /* 0x08 */ + uint64_t srr0; /* 0x10 */ + uint64_t srr1; /* 0x18 */ + union { /* 0x20 */ + struct { + enum MCE_UeErrorType ue_error_type:8; + uint8_t effective_address_provided; + uint8_t physical_address_provided; + uint8_t reserved_1[5]; + uint64_t effective_address; + uint64_t physical_address; + uint8_t reserved_2[8]; + } ue_error; + + struct { + enum MCE_SlbErrorType slb_error_type:8; + uint8_t effective_address_provided; + uint8_t reserved_1[6]; + uint64_t effective_address; + uint8_t reserved_2[16]; + } slb_error; + + struct { + enum MCE_EratErrorType erat_error_type:8; + uint8_t effective_address_provided; + uint8_t reserved_1[6]; + uint64_t effective_address; + uint8_t reserved_2[16]; + } erat_error; + + struct { + enum MCE_TlbErrorType tlb_error_type:8; + uint8_t effective_address_provided; + uint8_t reserved_1[6]; + uint64_t effective_address; + uint8_t reserved_2[16]; + } tlb_error; + } u; +}; + +struct mce_error_info { + enum MCE_ErrorType error_type:8; + union { + enum MCE_UeErrorType ue_error_type:8; + enum MCE_SlbErrorType slb_error_type:8; + enum MCE_EratErrorType erat_error_type:8; + enum MCE_TlbErrorType tlb_error_type:8; + } u; + uint8_t reserved[2]; +}; + +#define MAX_MC_EVT 100 + +/* Release flags for get_mce_event() */ +#define MCE_EVENT_RELEASE true +#define MCE_EVENT_DONTRELEASE false + +extern void save_mce_event(struct pt_regs *regs, long handled, + struct mce_error_info *mce_err, uint64_t addr); +extern int get_mce_event(struct machine_check_event *mce, bool release); +extern void release_mce_event(void); +extern void machine_check_queue_event(void); +extern void machine_check_process_queued_event(void); +extern void machine_check_print_event_info(struct machine_check_event *evt); +extern uint64_t get_mce_fault_addr(struct machine_check_event *evt); + +#endif /* __ASM_PPC64_MCE_H__ */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 7bdcf340016c..a4041e9ed550 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -33,6 +33,28 @@ struct opal_takeover_args { u64 rd_loc; /* r11 */ }; +/* + * SG entry + * + * WARNING: The current implementation requires each entry + * to represent a block that is 4k aligned *and* each block + * size except the last one in the list to be as well. + */ +struct opal_sg_entry { + void *data; + long length; +}; + +/* sg list */ +struct opal_sg_list { + unsigned long num_entries; + struct opal_sg_list *next; + struct opal_sg_entry entry[]; +}; + +/* We calculate number of sg entries based on PAGE_SIZE */ +#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry)) + extern long opal_query_takeover(u64 *hal_size, u64 *hal_align); extern long opal_do_takeover(struct opal_takeover_args *args); @@ -132,6 +154,8 @@ extern int opal_enter_rtas(struct rtas_args *args, #define OPAL_FLASH_VALIDATE 76 #define OPAL_FLASH_MANAGE 77 #define OPAL_FLASH_UPDATE 78 +#define OPAL_GET_MSG 85 +#define OPAL_CHECK_ASYNC_COMPLETION 86 #ifndef __ASSEMBLY__ @@ -211,7 +235,16 @@ enum OpalPendingState { OPAL_EVENT_ERROR_LOG = 0x40, OPAL_EVENT_EPOW = 0x80, OPAL_EVENT_LED_STATUS = 0x100, - OPAL_EVENT_PCI_ERROR = 0x200 + OPAL_EVENT_PCI_ERROR = 0x200, + OPAL_EVENT_MSG_PENDING = 0x800, +}; + +enum OpalMessageType { + OPAL_MSG_ASYNC_COMP = 0, + OPAL_MSG_MEM_ERR, + OPAL_MSG_EPOW, + OPAL_MSG_SHUTDOWN, + OPAL_MSG_TYPE_MAX, }; /* Machine check related definitions */ @@ -356,6 +389,12 @@ enum OpalLPCAddressType { OPAL_LPC_FW = 2, }; +struct opal_msg { + uint32_t msg_type; + uint32_t reserved; + uint64_t params[8]; +}; + struct opal_machine_check_event { enum OpalMCE_Version version:8; /* 0x00 */ uint8_t in_use; /* 0x01 */ @@ -404,6 +443,58 @@ struct opal_machine_check_event { } u; }; +/* FSP memory errors handling */ +enum OpalMemErr_Version { + OpalMemErr_V1 = 1, +}; + +enum OpalMemErrType { + OPAL_MEM_ERR_TYPE_RESILIENCE = 0, + OPAL_MEM_ERR_TYPE_DYN_DALLOC, + OPAL_MEM_ERR_TYPE_SCRUB, +}; + +/* Memory Reilience error type */ +enum OpalMemErr_ResilErrType { + OPAL_MEM_RESILIENCE_CE = 0, + OPAL_MEM_RESILIENCE_UE, + OPAL_MEM_RESILIENCE_UE_SCRUB, +}; + +/* Dynamic Memory Deallocation type */ +enum OpalMemErr_DynErrType { + OPAL_MEM_DYNAMIC_DEALLOC = 0, +}; + +/* OpalMemoryErrorData->flags */ +#define OPAL_MEM_CORRECTED_ERROR 0x0001 +#define OPAL_MEM_THRESHOLD_EXCEEDED 0x0002 +#define OPAL_MEM_ACK_REQUIRED 0x8000 + +struct OpalMemoryErrorData { + enum OpalMemErr_Version version:8; /* 0x00 */ + enum OpalMemErrType type:8; /* 0x01 */ + uint16_t flags; /* 0x02 */ + uint8_t reserved_1[4]; /* 0x04 */ + + union { + /* Memory Resilience corrected/uncorrected error info */ + struct { + enum OpalMemErr_ResilErrType resil_err_type:8; + uint8_t reserved_1[7]; + uint64_t physical_address_start; + uint64_t physical_address_end; + } resilience; + /* Dynamic memory deallocation error info */ + struct { + enum OpalMemErr_DynErrType dyn_err_type:8; + uint8_t reserved_1[7]; + uint64_t physical_address_start; + uint64_t physical_address_end; + } dyn_dealloc; + } u; +}; + enum { OPAL_P7IOC_DIAG_TYPE_NONE = 0, OPAL_P7IOC_DIAG_TYPE_RGC = 1, @@ -731,6 +822,9 @@ int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result); int64_t opal_manage_flash(uint8_t op); int64_t opal_update_flash(uint64_t blk_list); +int64_t opal_get_msg(uint64_t buffer, size_t size); +int64_t opal_check_completion(uint64_t buffer, size_t size, uint64_t token); + /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); @@ -744,6 +838,8 @@ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); extern int opal_notifier_register(struct notifier_block *nb); +extern int opal_message_notifier_register(enum OpalMessageType msg_type, + struct notifier_block *nb); extern void opal_notifier_enable(void); extern void opal_notifier_disable(void); extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val); diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index b6ea9e068c13..c3523d1dda58 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -152,6 +152,15 @@ struct paca_struct { */ struct opal_machine_check_event *opal_mc_evt; #endif +#ifdef CONFIG_PPC_BOOK3S_64 + /* Exclusive emergency stack pointer for machine check exception. */ + void *mc_emergency_sp; + /* + * Flag to check whether we are in machine check early handler + * and already using emergency stack. + */ + u16 in_mce; +#endif /* Stuff for accurate time accounting */ u64 user_time; /* accumulated usermode TB ticks */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 7d6eacf249cf..b999ca318985 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -3,6 +3,7 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ +#include <linux/mmdebug.h> #include <asm/processor.h> /* For TASK_SIZE */ #include <asm/mmu.h> #include <asm/page.h> @@ -33,10 +34,73 @@ static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } -static inline int pte_present(pte_t pte) { return pte_val(pte) & _PAGE_PRESENT; } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } +#ifdef CONFIG_NUMA_BALANCING + +static inline int pte_present(pte_t pte) +{ + return pte_val(pte) & (_PAGE_PRESENT | _PAGE_NUMA); +} + +#define pte_numa pte_numa +static inline int pte_numa(pte_t pte) +{ + return (pte_val(pte) & + (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA; +} + +#define pte_mknonnuma pte_mknonnuma +static inline pte_t pte_mknonnuma(pte_t pte) +{ + pte_val(pte) &= ~_PAGE_NUMA; + pte_val(pte) |= _PAGE_PRESENT | _PAGE_ACCESSED; + return pte; +} + +#define pte_mknuma pte_mknuma +static inline pte_t pte_mknuma(pte_t pte) +{ + /* + * We should not set _PAGE_NUMA on non present ptes. Also clear the + * present bit so that hash_page will return 1 and we collect this + * as numa fault. + */ + if (pte_present(pte)) { + pte_val(pte) |= _PAGE_NUMA; + pte_val(pte) &= ~_PAGE_PRESENT; + } else + VM_BUG_ON(1); + return pte; +} + +#define pmd_numa pmd_numa +static inline int pmd_numa(pmd_t pmd) +{ + return pte_numa(pmd_pte(pmd)); +} + +#define pmd_mknonnuma pmd_mknonnuma +static inline pmd_t pmd_mknonnuma(pmd_t pmd) +{ + return pte_pmd(pte_mknonnuma(pmd_pte(pmd))); +} + +#define pmd_mknuma pmd_mknuma +static inline pmd_t pmd_mknuma(pmd_t pmd) +{ + return pte_pmd(pte_mknuma(pmd_pte(pmd))); +} + +# else + +static inline int pte_present(pte_t pte) +{ + return pte_val(pte) & _PAGE_PRESENT; +} +#endif /* CONFIG_NUMA_BALANCING */ + /* Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * diff --git a/arch/powerpc/include/asm/pte-hash64.h b/arch/powerpc/include/asm/pte-hash64.h index 0419eeb53274..2505d8eab15c 100644 --- a/arch/powerpc/include/asm/pte-hash64.h +++ b/arch/powerpc/include/asm/pte-hash64.h @@ -19,7 +19,7 @@ #define _PAGE_FILE 0x0002 /* (!present only) software: pte holds file offset */ #define _PAGE_EXEC 0x0004 /* No execute on POWER4 and newer (we invert) */ #define _PAGE_GUARDED 0x0008 -#define _PAGE_COHERENT 0x0010 /* M: enforce memory coherence (SMP systems) */ +/* We can derive Memory coherence from _PAGE_NO_CACHE */ #define _PAGE_NO_CACHE 0x0020 /* I: cache inhibit */ #define _PAGE_WRITETHRU 0x0040 /* W: cache write-through */ #define _PAGE_DIRTY 0x0080 /* C: page changed */ @@ -27,6 +27,12 @@ #define _PAGE_RW 0x0200 /* software: user write access allowed */ #define _PAGE_BUSY 0x0800 /* software: PTE & hash are busy */ +/* + * Used for tracking numa faults + */ +#define _PAGE_NUMA 0x00000010 /* Gather numa placement stats */ + + /* No separate kernel read-only */ #define _PAGE_KERNEL_RW (_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */ #define _PAGE_KERNEL_RO _PAGE_KERNEL_RW diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 445cb6e39d5b..904d713366ff 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -39,6 +39,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o +obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj64-$(CONFIG_RELOCATABLE) += reloc_64.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC_A2) += cpu_setup_a2.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 2ea5cc033ec8..41a283956a29 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -232,6 +232,10 @@ int main(void) DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx)); #endif /* CONFIG_PPC_STD_MMU_64 */ DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp)); +#ifdef CONFIG_PPC_BOOK3S_64 + DEFINE(PACAMCEMERGSP, offsetof(struct paca_struct, mc_emergency_sp)); + DEFINE(PACA_IN_MCE, offsetof(struct paca_struct, in_mce)); +#endif DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime)); diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 18b5b9cf8e37..37d1bb002aa9 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -29,7 +29,7 @@ _GLOBAL(__setup_cpu_power7) mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR bl __init_LPCR - bl __init_TLB + bl __init_tlb_power7 mtlr r11 blr @@ -42,7 +42,7 @@ _GLOBAL(__restore_cpu_power7) mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR bl __init_LPCR - bl __init_TLB + bl __init_tlb_power7 mtlr r11 blr @@ -59,7 +59,7 @@ _GLOBAL(__setup_cpu_power8) oris r3, r3, LPCR_AIL_3@h bl __init_LPCR bl __init_HFSCR - bl __init_TLB + bl __init_tlb_power8 bl __init_PMU_HV mtlr r11 blr @@ -78,7 +78,7 @@ _GLOBAL(__restore_cpu_power8) oris r3, r3, LPCR_AIL_3@h bl __init_LPCR bl __init_HFSCR - bl __init_TLB + bl __init_tlb_power8 bl __init_PMU_HV mtlr r11 blr @@ -134,15 +134,31 @@ __init_HFSCR: mtspr SPRN_HFSCR,r3 blr -__init_TLB: - /* - * Clear the TLB using the "IS 3" form of tlbiel instruction - * (invalidate by congruence class). P7 has 128 CCs, P8 has 512 - * so we just always do 512 - */ +/* + * Clear the TLB using the specified IS form of tlbiel instruction + * (invalidate by congruence class). P7 has 128 CCs., P8 has 512. + * + * r3 = IS field + */ +__init_tlb_power7: + li r3,0xc00 /* IS field = 0b11 */ +_GLOBAL(__flush_tlb_power7) + li r6,128 + mtctr r6 + mr r7,r3 /* IS field */ + ptesync +2: tlbiel r7 + addi r7,r7,0x1000 + bdnz 2b + ptesync +1: blr + +__init_tlb_power8: + li r3,0xc00 /* IS field = 0b11 */ +_GLOBAL(__flush_tlb_power8) li r6,512 mtctr r6 - li r7,0xc00 /* IS field = 0b11 */ + mr r7,r3 /* IS field */ ptesync 2: tlbiel r7 addi r7,r7,0x1000 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 597d954e5860..6c8dd5da4de5 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -71,6 +71,10 @@ extern void __restore_cpu_power7(void); extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power8(void); extern void __restore_cpu_a2(void); +extern void __flush_tlb_power7(unsigned long inval_selector); +extern void __flush_tlb_power8(unsigned long inval_selector); +extern long __machine_check_early_realmode_p7(struct pt_regs *regs); +extern long __machine_check_early_realmode_p8(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -440,6 +444,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, + .flush_tlb = __flush_tlb_power7, + .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7", }, { /* 2.07-compliant processor, i.e. Power8 "architected" mode */ @@ -456,6 +462,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, { /* Power7 */ @@ -474,6 +482,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, + .flush_tlb = __flush_tlb_power7, + .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7", }, { /* Power7+ */ @@ -492,6 +502,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, + .flush_tlb = __flush_tlb_power7, + .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7+", }, { /* Power8E */ @@ -510,6 +522,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, { /* Power8 */ @@ -528,6 +542,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, + .flush_tlb = __flush_tlb_power8, + .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, { /* Cell Broadband Engine */ diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index e4897523de41..54d0116256f7 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -83,10 +83,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask) return 0; } - if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT)) { + if (tbl->it_offset > (mask >> tbl->it_page_shift)) { dev_info(dev, "Warning: IOMMU offset too big for device mask\n"); dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n", - mask, tbl->it_offset << IOMMU_PAGE_SHIFT); + mask, tbl->it_offset << tbl->it_page_shift); return 0; } else return 1; diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 4bd687d5e7aa..f4b7a227f183 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -84,7 +84,7 @@ #define EEH_MAX_FAILS 2100000 /* Time to wait for a PCI slot to report status, in milliseconds */ -#define PCI_BUS_RESET_WAIT_MSEC (60*1000) +#define PCI_BUS_RESET_WAIT_MSEC (5*60*1000) /* Platform dependent EEH operations */ struct eeh_ops *eeh_ops = NULL; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 36bed5a12750..4ef59c33777f 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -468,7 +468,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) /* The longest amount of time to wait for a pci device * to come back on line, in seconds. */ -#define MAX_WAIT_FOR_RECOVERY 150 +#define MAX_WAIT_FOR_RECOVERY 300 static void eeh_handle_normal_event(struct eeh_pe *pe) { diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index bbfb0294b354..770d6d65c47b 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -184,6 +184,11 @@ syscall_exit: bl .do_show_syscall_exit ld r3,RESULT(r1) #endif +#ifdef CONFIG_PPC_BOOK3S_64 +BEGIN_FTR_SECTION + bl .machine_check_process_queued_event +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) +#endif CURRENT_THREAD_INFO(r12, r1) ld r8,_MSR(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 9f905e40922e..38d507306a11 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -155,8 +155,30 @@ machine_check_pSeries_1: */ HMT_MEDIUM_PPR_DISCARD SET_SCRATCH0(r13) /* save r13 */ +#ifdef CONFIG_PPC_P7_NAP +BEGIN_FTR_SECTION + /* Running native on arch 2.06 or later, check if we are + * waking up from nap. We only handle no state loss and + * supervisor state loss. We do -not- handle hypervisor + * state loss at this time. + */ + mfspr r13,SPRN_SRR1 + rlwinm. r13,r13,47-31,30,31 + beq 9f + + /* waking up from powersave (nap) state */ + cmpwi cr1,r13,2 + /* Total loss of HV state is fatal. let's just stay stuck here */ + bgt cr1,. +9: +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) +#endif /* CONFIG_PPC_P7_NAP */ EXCEPTION_PROLOG_0(PACA_EXMC) +BEGIN_FTR_SECTION + b machine_check_pSeries_early +FTR_SECTION_ELSE b machine_check_pSeries_0 +ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) . = 0x300 .globl data_access_pSeries @@ -405,6 +427,64 @@ denorm_exception_hv: .align 7 /* moved from 0x200 */ +machine_check_pSeries_early: +BEGIN_FTR_SECTION + EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200) + /* + * Register contents: + * R13 = PACA + * R9 = CR + * Original R9 to R13 is saved on PACA_EXMC + * + * Switch to mc_emergency stack and handle re-entrancy (though we + * currently don't test for overflow). Save MCE registers srr1, + * srr0, dar and dsisr and then set ME=1 + * + * We use paca->in_mce to check whether this is the first entry or + * nested machine check. We increment paca->in_mce to track nested + * machine checks. + * + * If this is the first entry then set stack pointer to + * paca->mc_emergency_sp, otherwise r1 is already pointing to + * stack frame on mc_emergency stack. + * + * NOTE: We are here with MSR_ME=0 (off), which means we risk a + * checkstop if we get another machine check exception before we do + * rfid with MSR_ME=1. + */ + mr r11,r1 /* Save r1 */ + lhz r10,PACA_IN_MCE(r13) + cmpwi r10,0 /* Are we in nested machine check */ + bne 0f /* Yes, we are. */ + /* First machine check entry */ + ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */ +0: subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + addi r10,r10,1 /* increment paca->in_mce */ + sth r10,PACA_IN_MCE(r13) + std r11,GPR1(r1) /* Save r1 on the stack. */ + std r11,0(r1) /* make stack chain pointer */ + mfspr r11,SPRN_SRR0 /* Save SRR0 */ + std r11,_NIP(r1) + mfspr r11,SPRN_SRR1 /* Save SRR1 */ + std r11,_MSR(r1) + mfspr r11,SPRN_DAR /* Save DAR */ + std r11,_DAR(r1) + mfspr r11,SPRN_DSISR /* Save DSISR */ + std r11,_DSISR(r1) + std r9,_CCR(r1) /* Save CR in stackframe */ + /* Save r9 through r13 from EXMC save area to stack frame. */ + EXCEPTION_PROLOG_COMMON_2(PACA_EXMC) + mfmsr r11 /* get MSR value */ + ori r11,r11,MSR_ME /* turn on ME bit */ + ori r11,r11,MSR_RI /* turn on RI bit */ + ld r12,PACAKBASE(r13) /* get high part of &label */ + LOAD_HANDLER(r12, machine_check_handle_early) + mtspr SPRN_SRR0,r12 + mtspr SPRN_SRR1,r11 + rfid + b . /* prevent speculative execution */ +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) + machine_check_pSeries: .globl machine_check_fwnmi machine_check_fwnmi: @@ -688,30 +768,6 @@ kvmppc_skip_Hinterrupt: STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception) - /* - * Machine check is different because we use a different - * save area: PACA_EXMC instead of PACA_EXGEN. - */ - .align 7 - .globl machine_check_common -machine_check_common: - - mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) - FINISH_NAP - DISABLE_INTS - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) - std r3,_DAR(r1) - std r4,_DSISR(r1) - bl .save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - bl .machine_check_exception - b .ret_from_except - STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ) STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt) STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt) @@ -1080,6 +1136,30 @@ unrecov_user_slb: #endif /* __DISABLED__ */ + /* + * Machine check is different because we use a different + * save area: PACA_EXMC instead of PACA_EXGEN. + */ + .align 7 + .globl machine_check_common +machine_check_common: + + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) + FINISH_NAP + DISABLE_INTS + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + std r3,_DAR(r1) + std r4,_DSISR(r1) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .machine_check_exception + b .ret_from_except + .align 7 .globl alignment_common alignment_common: @@ -1263,6 +1343,120 @@ _GLOBAL(opal_mc_secondary_handler) #endif /* CONFIG_PPC_POWERNV */ +#define MACHINE_CHECK_HANDLER_WINDUP \ + /* 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 SRR0 and SRR1 into the respective regs */ \ + ld r9,_MSR(r1); \ + mtspr SPRN_SRR1,r9; \ + ld r3,_NIP(r1); \ + mtspr SPRN_SRR0,r3; \ + ld r9,_CTR(r1); \ + mtctr r9; \ + ld r9,_XER(r1); \ + mtxer r9; \ + ld r9,_LINK(r1); \ + mtlr r9; \ + REST_GPR(0, r1); \ + REST_8GPRS(2, r1); \ + REST_GPR(10, r1); \ + ld r11,_CCR(r1); \ + mtcr r11; \ + /* Decrement paca->in_mce. */ \ + lhz r12,PACA_IN_MCE(r13); \ + subi r12,r12,1; \ + sth r12,PACA_IN_MCE(r13); \ + REST_GPR(11, r1); \ + REST_2GPRS(12, r1); \ + /* restore original r1. */ \ + ld r1,GPR1(r1) + + /* + * Handle machine check early in real mode. We come here with + * ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack. + */ + .align 7 + .globl machine_check_handle_early +machine_check_handle_early: + std r0,GPR0(r1) /* Save r0 */ + EXCEPTION_PROLOG_COMMON_3(0x200) + bl .save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl .machine_check_early + ld r12,_MSR(r1) +#ifdef CONFIG_PPC_P7_NAP + /* + * Check if thread was in power saving mode. We come here when any + * of the following is true: + * a. thread wasn't in power saving mode + * b. thread was in power saving mode with no state loss or + * supervisor state loss + * + * Go back to nap again if (b) is true. + */ + rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */ + beq 4f /* No, it wasn;t */ + /* Thread was in power saving mode. Go back to nap again. */ + cmpwi r11,2 + bne 3f + /* Supervisor state loss */ + li r0,1 + stb r0,PACA_NAPSTATELOST(r13) +3: bl .machine_check_queue_event + MACHINE_CHECK_HANDLER_WINDUP + GET_PACA(r13) + ld r1,PACAR1(r13) + b .power7_enter_nap_mode +4: +#endif + /* + * Check if we are coming from hypervisor userspace. If yes then we + * continue in host kernel in V mode to deliver the MC event. + */ + rldicl. r11,r12,4,63 /* See if MC hit while in HV mode. */ + beq 5f + andi. r11,r12,MSR_PR /* See if coming from user. */ + bne 9f /* continue in V mode if we are. */ + +5: +#ifdef CONFIG_KVM_BOOK3S_64_HV + /* + * We are coming from kernel context. Check if we are coming from + * guest. if yes, then we can continue. We will fall through + * do_kvm_200->kvmppc_interrupt to deliver the MC event to guest. + */ + lbz r11,HSTATE_IN_GUEST(r13) + cmpwi r11,0 /* Check if coming from guest */ + bne 9f /* continue if we are. */ +#endif + /* + * At this point we are not sure about what context we come from. + * Queue up the MCE event and return from the interrupt. + * But before that, check if this is an un-recoverable exception. + * If yes, then stay on emergency stack and panic. + */ + andi. r11,r12,MSR_RI + bne 2f +1: addi r3,r1,STACK_FRAME_OVERHEAD + bl .unrecoverable_exception + b 1b +2: + /* + * Return from MC interrupt. + * Queue up the MCE event so that we can log it later, while + * returning from kernel or opal call. + */ + bl .machine_check_queue_event + MACHINE_CHECK_HANDLER_WINDUP + rfid +9: + /* Deliver the machine check to host kernel in V mode. */ + MACHINE_CHECK_HANDLER_WINDUP + b machine_check_pSeries + /* * r13 points to the PACA, r9 contains the saved CR, * r12 contain the saved SRR1, SRR0 is still ready for return diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 847e40e62fce..3fdef0f0c67f 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -84,6 +84,7 @@ _GLOBAL(power7_nap) std r9,_MSR(r1) std r1,PACAR1(r13) +_GLOBAL(power7_enter_nap_mode) #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* Tell KVM we're napping */ li r4,KVM_HWTHREAD_IN_NAP diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 572bb5b95f35..f58d8135aab2 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -251,14 +251,13 @@ again: if (dev) boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, - 1 << IOMMU_PAGE_SHIFT); + 1 << tbl->it_page_shift); else - boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT); + boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift); /* 4GB boundary for iseries_hv_alloc and iseries_hv_map */ - n = iommu_area_alloc(tbl->it_map, limit, start, npages, - tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT, - align_mask); + n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset, + boundary_size >> tbl->it_page_shift, align_mask); if (n == -1) { if (likely(pass == 0)) { /* First try the pool from the start */ @@ -320,12 +319,12 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, return DMA_ERROR_CODE; entry += tbl->it_offset; /* Offset into real TCE table */ - ret = entry << IOMMU_PAGE_SHIFT; /* Set the return dma address */ + ret = entry << tbl->it_page_shift; /* Set the return dma address */ /* Put the TCEs in the HW table */ build_fail = ppc_md.tce_build(tbl, entry, npages, - (unsigned long)page & IOMMU_PAGE_MASK, - direction, attrs); + (unsigned long)page & + IOMMU_PAGE_MASK(tbl), direction, attrs); /* ppc_md.tce_build() only returns non-zero for transient errors. * Clean up the table bitmap in this case and return @@ -352,7 +351,7 @@ static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr, { unsigned long entry, free_entry; - entry = dma_addr >> IOMMU_PAGE_SHIFT; + entry = dma_addr >> tbl->it_page_shift; free_entry = entry - tbl->it_offset; if (((free_entry + npages) > tbl->it_size) || @@ -401,7 +400,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, unsigned long flags; struct iommu_pool *pool; - entry = dma_addr >> IOMMU_PAGE_SHIFT; + entry = dma_addr >> tbl->it_page_shift; free_entry = entry - tbl->it_offset; pool = get_pool(tbl, free_entry); @@ -468,13 +467,13 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, } /* Allocate iommu entries for that segment */ vaddr = (unsigned long) sg_virt(s); - npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE); + npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE(tbl)); align = 0; - if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE && + if (tbl->it_page_shift < PAGE_SHIFT && slen >= PAGE_SIZE && (vaddr & ~PAGE_MASK) == 0) - align = PAGE_SHIFT - IOMMU_PAGE_SHIFT; + align = PAGE_SHIFT - tbl->it_page_shift; entry = iommu_range_alloc(dev, tbl, npages, &handle, - mask >> IOMMU_PAGE_SHIFT, align); + mask >> tbl->it_page_shift, align); DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen); @@ -489,16 +488,16 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Convert entry to a dma_addr_t */ entry += tbl->it_offset; - dma_addr = entry << IOMMU_PAGE_SHIFT; - dma_addr |= (s->offset & ~IOMMU_PAGE_MASK); + dma_addr = entry << tbl->it_page_shift; + dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl)); DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n", npages, entry, dma_addr); /* Insert into HW table */ build_fail = ppc_md.tce_build(tbl, entry, npages, - vaddr & IOMMU_PAGE_MASK, - direction, attrs); + vaddr & IOMMU_PAGE_MASK(tbl), + direction, attrs); if(unlikely(build_fail)) goto failure; @@ -559,9 +558,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, if (s->dma_length != 0) { unsigned long vaddr, npages; - vaddr = s->dma_address & IOMMU_PAGE_MASK; + vaddr = s->dma_address & IOMMU_PAGE_MASK(tbl); npages = iommu_num_pages(s->dma_address, s->dma_length, - IOMMU_PAGE_SIZE); + IOMMU_PAGE_SIZE(tbl)); __iommu_free(tbl, vaddr, npages); s->dma_address = DMA_ERROR_CODE; s->dma_length = 0; @@ -592,7 +591,7 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, if (sg->dma_length == 0) break; npages = iommu_num_pages(dma_handle, sg->dma_length, - IOMMU_PAGE_SIZE); + IOMMU_PAGE_SIZE(tbl)); __iommu_free(tbl, dma_handle, npages); sg = sg_next(sg); } @@ -676,7 +675,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) set_bit(0, tbl->it_map); /* We only split the IOMMU table if we have 1GB or more of space */ - if ((tbl->it_size << IOMMU_PAGE_SHIFT) >= (1UL * 1024 * 1024 * 1024)) + if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024)) tbl->nr_pools = IOMMU_NR_POOLS; else tbl->nr_pools = 1; @@ -768,16 +767,16 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, vaddr = page_address(page) + offset; uaddr = (unsigned long)vaddr; - npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE); + npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl)); if (tbl) { align = 0; - if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && size >= PAGE_SIZE && + if (tbl->it_page_shift < PAGE_SHIFT && size >= PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) - align = PAGE_SHIFT - IOMMU_PAGE_SHIFT; + align = PAGE_SHIFT - tbl->it_page_shift; dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction, - mask >> IOMMU_PAGE_SHIFT, align, + mask >> tbl->it_page_shift, align, attrs); if (dma_handle == DMA_ERROR_CODE) { if (printk_ratelimit()) { @@ -786,7 +785,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, npages); } } else - dma_handle |= (uaddr & ~IOMMU_PAGE_MASK); + dma_handle |= (uaddr & ~IOMMU_PAGE_MASK(tbl)); } return dma_handle; @@ -801,7 +800,8 @@ void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, BUG_ON(direction == DMA_NONE); if (tbl) { - npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE); + npages = iommu_num_pages(dma_handle, size, + IOMMU_PAGE_SIZE(tbl)); iommu_free(tbl, dma_handle, npages); } } @@ -845,10 +845,10 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> IOMMU_PAGE_SHIFT; - io_order = get_iommu_order(size); + nio_pages = size >> tbl->it_page_shift; + io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, - mask >> IOMMU_PAGE_SHIFT, io_order, NULL); + mask >> tbl->it_page_shift, io_order, NULL); if (mapping == DMA_ERROR_CODE) { free_pages((unsigned long)ret, order); return NULL; @@ -864,7 +864,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, unsigned int nio_pages; size = PAGE_ALIGN(size); - nio_pages = size >> IOMMU_PAGE_SHIFT; + nio_pages = size >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); @@ -935,10 +935,10 @@ int iommu_tce_clear_param_check(struct iommu_table *tbl, if (tce_value) return -EINVAL; - if (ioba & ~IOMMU_PAGE_MASK) + if (ioba & ~IOMMU_PAGE_MASK(tbl)) return -EINVAL; - ioba >>= IOMMU_PAGE_SHIFT; + ioba >>= tbl->it_page_shift; if (ioba < tbl->it_offset) return -EINVAL; @@ -955,13 +955,13 @@ int iommu_tce_put_param_check(struct iommu_table *tbl, if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ))) return -EINVAL; - if (tce & ~(IOMMU_PAGE_MASK | TCE_PCI_WRITE | TCE_PCI_READ)) + if (tce & ~(IOMMU_PAGE_MASK(tbl) | TCE_PCI_WRITE | TCE_PCI_READ)) return -EINVAL; - if (ioba & ~IOMMU_PAGE_MASK) + if (ioba & ~IOMMU_PAGE_MASK(tbl)) return -EINVAL; - ioba >>= IOMMU_PAGE_SHIFT; + ioba >>= tbl->it_page_shift; if (ioba < tbl->it_offset) return -EINVAL; @@ -1037,7 +1037,7 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry, /* if (unlikely(ret)) pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n", - __func__, hwaddr, entry << IOMMU_PAGE_SHIFT, + __func__, hwaddr, entry << IOMMU_PAGE_SHIFT(tbl), hwaddr, ret); */ return ret; @@ -1049,14 +1049,14 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, { int ret; struct page *page = NULL; - unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK & ~PAGE_MASK; + unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK; enum dma_data_direction direction = iommu_tce_direction(tce); ret = get_user_pages_fast(tce & PAGE_MASK, 1, direction != DMA_TO_DEVICE, &page); if (unlikely(ret != 1)) { /* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n", - tce, entry << IOMMU_PAGE_SHIFT, ret); */ + tce, entry << IOMMU_PAGE_SHIFT(tbl), ret); */ return -EFAULT; } hwaddr = (unsigned long) page_address(page) + offset; @@ -1067,7 +1067,7 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, if (ret < 0) pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n", - __func__, entry << IOMMU_PAGE_SHIFT, tce, ret); + __func__, entry << tbl->it_page_shift, tce, ret); return ret; } @@ -1105,7 +1105,7 @@ void iommu_release_ownership(struct iommu_table *tbl) } EXPORT_SYMBOL_GPL(iommu_release_ownership); -static int iommu_add_device(struct device *dev) +int iommu_add_device(struct device *dev) { struct iommu_table *tbl; int ret = 0; @@ -1127,6 +1127,12 @@ static int iommu_add_device(struct device *dev) pr_debug("iommu_tce: adding %s to iommu group %d\n", dev_name(dev), iommu_group_id(tbl->it_group)); + if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) { + pr_err("iommu_tce: unsupported iommu page size."); + pr_err("%s has not been added\n", dev_name(dev)); + return -EINVAL; + } + ret = iommu_group_add_device(tbl->it_group, dev); if (ret < 0) pr_err("iommu_tce: %s has not been added, ret=%d\n", @@ -1134,52 +1140,12 @@ static int iommu_add_device(struct device *dev) return ret; } +EXPORT_SYMBOL_GPL(iommu_add_device); -static void iommu_del_device(struct device *dev) +void iommu_del_device(struct device *dev) { iommu_group_remove_device(dev); } - -static int iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - return iommu_add_device(dev); - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = iommu_bus_notifier, -}; - -static int __init tce_iommu_init(void) -{ - struct pci_dev *pdev = NULL; - - BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE); - - for_each_pci_dev(pdev) - iommu_add_device(&pdev->dev); - - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} - -subsys_initcall_sync(tce_iommu_init); - -#else - -void iommu_register_group(struct iommu_table *tbl, - int pci_domain_number, unsigned long pe_num) -{ -} +EXPORT_SYMBOL_GPL(iommu_del_device); #endif /* CONFIG_IOMMU_API */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index ba0165615215..9729b23bfb0a 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -354,8 +354,13 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%*s: ", prec, "LOC"); for_each_online_cpu(j) - seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs); - seq_printf(p, " Local timer interrupts\n"); + seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event); + seq_printf(p, " Local timer interrupts for timer event device\n"); + + seq_printf(p, "%*s: ", prec, "LOC"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others); + seq_printf(p, " Local timer interrupts for others\n"); seq_printf(p, "%*s: ", prec, "SPU"); for_each_online_cpu(j) @@ -389,11 +394,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) */ u64 arch_irq_stat_cpu(unsigned int cpu) { - u64 sum = per_cpu(irq_stat, cpu).timer_irqs; + u64 sum = per_cpu(irq_stat, cpu).timer_irqs_event; sum += per_cpu(irq_stat, cpu).pmu_irqs; sum += per_cpu(irq_stat, cpu).mce_exceptions; sum += per_cpu(irq_stat, cpu).spurious_irqs; + sum += per_cpu(irq_stat, cpu).timer_irqs_others; #ifdef CONFIG_PPC_DOORBELL sum += per_cpu(irq_stat, cpu).doorbell_irqs; #endif diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c new file mode 100644 index 000000000000..c0c52ec1fca7 --- /dev/null +++ b/arch/powerpc/kernel/mce.c @@ -0,0 +1,345 @@ +/* + * Machine check exception handling. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright 2013 IBM Corporation + * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> + */ + +#undef DEBUG +#define pr_fmt(fmt) "mce: " fmt + +#include <linux/types.h> +#include <linux/ptrace.h> +#include <linux/percpu.h> +#include <linux/export.h> +#include <asm/mce.h> + +static DEFINE_PER_CPU(int, mce_nest_count); +static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event); + +/* Queue for delayed MCE events. */ +static DEFINE_PER_CPU(int, mce_queue_count); +static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue); + +static void mce_set_error_info(struct machine_check_event *mce, + struct mce_error_info *mce_err) +{ + mce->error_type = mce_err->error_type; + switch (mce_err->error_type) { + case MCE_ERROR_TYPE_UE: + mce->u.ue_error.ue_error_type = mce_err->u.ue_error_type; + break; + case MCE_ERROR_TYPE_SLB: + mce->u.slb_error.slb_error_type = mce_err->u.slb_error_type; + break; + case MCE_ERROR_TYPE_ERAT: + mce->u.erat_error.erat_error_type = mce_err->u.erat_error_type; + break; + case MCE_ERROR_TYPE_TLB: + mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type; + break; + case MCE_ERROR_TYPE_UNKNOWN: + default: + break; + } +} + +/* + * Decode and save high level MCE information into per cpu buffer which + * is an array of machine_check_event structure. + */ +void save_mce_event(struct pt_regs *regs, long handled, + struct mce_error_info *mce_err, + uint64_t addr) +{ + uint64_t srr1; + int index = __get_cpu_var(mce_nest_count)++; + struct machine_check_event *mce = &__get_cpu_var(mce_event[index]); + + /* + * Return if we don't have enough space to log mce event. + * mce_nest_count may go beyond MAX_MC_EVT but that's ok, + * the check below will stop buffer overrun. + */ + if (index >= MAX_MC_EVT) + return; + + /* Populate generic machine check info */ + mce->version = MCE_V1; + mce->srr0 = regs->nip; + mce->srr1 = regs->msr; + mce->gpr3 = regs->gpr[3]; + mce->in_use = 1; + + mce->initiator = MCE_INITIATOR_CPU; + if (handled) + mce->disposition = MCE_DISPOSITION_RECOVERED; + else + mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; + mce->severity = MCE_SEV_ERROR_SYNC; + + srr1 = regs->msr; + + /* + * Populate the mce error_type and type-specific error_type. + */ + mce_set_error_info(mce, mce_err); + + if (!addr) + return; + + if (mce->error_type == MCE_ERROR_TYPE_TLB) { + mce->u.tlb_error.effective_address_provided = true; + mce->u.tlb_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_SLB) { + mce->u.slb_error.effective_address_provided = true; + mce->u.slb_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_ERAT) { + mce->u.erat_error.effective_address_provided = true; + mce->u.erat_error.effective_address = addr; + } else if (mce->error_type == MCE_ERROR_TYPE_UE) { + mce->u.ue_error.effective_address_provided = true; + mce->u.ue_error.effective_address = addr; + } + return; +} + +/* + * get_mce_event: + * mce Pointer to machine_check_event structure to be filled. + * release Flag to indicate whether to free the event slot or not. + * 0 <= do not release the mce event. Caller will invoke + * release_mce_event() once event has been consumed. + * 1 <= release the slot. + * + * return 1 = success + * 0 = failure + * + * get_mce_event() will be called by platform specific machine check + * handle routine and in KVM. + * When we call get_mce_event(), we are still in interrupt context and + * preemption will not be scheduled until ret_from_expect() routine + * is called. + */ +int get_mce_event(struct machine_check_event *mce, bool release) +{ + int index = __get_cpu_var(mce_nest_count) - 1; + struct machine_check_event *mc_evt; + int ret = 0; + + /* Sanity check */ + if (index < 0) + return ret; + + /* Check if we have MCE info to process. */ + if (index < MAX_MC_EVT) { + mc_evt = &__get_cpu_var(mce_event[index]); + /* Copy the event structure and release the original */ + if (mce) + *mce = *mc_evt; + if (release) + mc_evt->in_use = 0; + ret = 1; + } + /* Decrement the count to free the slot. */ + if (release) + __get_cpu_var(mce_nest_count)--; + + return ret; +} + +void release_mce_event(void) +{ + get_mce_event(NULL, true); +} + +/* + * Queue up the MCE event which then can be handled later. + */ +void machine_check_queue_event(void) +{ + int index; + struct machine_check_event evt; + + if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) + return; + + index = __get_cpu_var(mce_queue_count)++; + /* If queue is full, just return for now. */ + if (index >= MAX_MC_EVT) { + __get_cpu_var(mce_queue_count)--; + return; + } + __get_cpu_var(mce_event_queue[index]) = evt; +} + +/* + * process pending MCE event from the mce event queue. This function will be + * called during syscall exit. + */ +void machine_check_process_queued_event(void) +{ + int index; + + preempt_disable(); + /* + * For now just print it to console. + * TODO: log this error event to FSP or nvram. + */ + while (__get_cpu_var(mce_queue_count) > 0) { + index = __get_cpu_var(mce_queue_count) - 1; + machine_check_print_event_info( + &__get_cpu_var(mce_event_queue[index])); + __get_cpu_var(mce_queue_count)--; + } + preempt_enable(); +} + +void machine_check_print_event_info(struct machine_check_event *evt) +{ + const char *level, *sevstr, *subtype; + static const char *mc_ue_types[] = { + "Indeterminate", + "Instruction fetch", + "Page table walk ifetch", + "Load/Store", + "Page table walk Load/Store", + }; + static const char *mc_slb_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + static const char *mc_erat_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + static const char *mc_tlb_types[] = { + "Indeterminate", + "Parity", + "Multihit", + }; + + /* Print things out */ + if (evt->version != MCE_V1) { + pr_err("Machine Check Exception, Unknown event version %d !\n", + evt->version); + return; + } + switch (evt->severity) { + case MCE_SEV_NO_ERROR: + level = KERN_INFO; + sevstr = "Harmless"; + break; + case MCE_SEV_WARNING: + level = KERN_WARNING; + sevstr = ""; + break; + case MCE_SEV_ERROR_SYNC: + level = KERN_ERR; + sevstr = "Severe"; + break; + case MCE_SEV_FATAL: + default: + level = KERN_ERR; + sevstr = "Fatal"; + break; + } + + printk("%s%s Machine check interrupt [%s]\n", level, sevstr, + evt->disposition == MCE_DISPOSITION_RECOVERED ? + "Recovered" : "[Not recovered"); + printk("%s Initiator: %s\n", level, + evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown"); + switch (evt->error_type) { + case MCE_ERROR_TYPE_UE: + subtype = evt->u.ue_error.ue_error_type < + ARRAY_SIZE(mc_ue_types) ? + mc_ue_types[evt->u.ue_error.ue_error_type] + : "Unknown"; + printk("%s Error type: UE [%s]\n", level, subtype); + if (evt->u.ue_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.ue_error.effective_address); + if (evt->u.ue_error.physical_address_provided) + printk("%s Physial address: %016llx\n", + level, evt->u.ue_error.physical_address); + break; + case MCE_ERROR_TYPE_SLB: + subtype = evt->u.slb_error.slb_error_type < + ARRAY_SIZE(mc_slb_types) ? + mc_slb_types[evt->u.slb_error.slb_error_type] + : "Unknown"; + printk("%s Error type: SLB [%s]\n", level, subtype); + if (evt->u.slb_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.slb_error.effective_address); + break; + case MCE_ERROR_TYPE_ERAT: + subtype = evt->u.erat_error.erat_error_type < + ARRAY_SIZE(mc_erat_types) ? + mc_erat_types[evt->u.erat_error.erat_error_type] + : "Unknown"; + printk("%s Error type: ERAT [%s]\n", level, subtype); + if (evt->u.erat_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.erat_error.effective_address); + break; + case MCE_ERROR_TYPE_TLB: + subtype = evt->u.tlb_error.tlb_error_type < + ARRAY_SIZE(mc_tlb_types) ? + mc_tlb_types[evt->u.tlb_error.tlb_error_type] + : "Unknown"; + printk("%s Error type: TLB [%s]\n", level, subtype); + if (evt->u.tlb_error.effective_address_provided) + printk("%s Effective address: %016llx\n", + level, evt->u.tlb_error.effective_address); + break; + default: + case MCE_ERROR_TYPE_UNKNOWN: + printk("%s Error type: Unknown\n", level); + break; + } +} + +uint64_t get_mce_fault_addr(struct machine_check_event *evt) +{ + switch (evt->error_type) { + case MCE_ERROR_TYPE_UE: + if (evt->u.ue_error.effective_address_provided) + return evt->u.ue_error.effective_address; + break; + case MCE_ERROR_TYPE_SLB: + if (evt->u.slb_error.effective_address_provided) + return evt->u.slb_error.effective_address; + break; + case MCE_ERROR_TYPE_ERAT: + if (evt->u.erat_error.effective_address_provided) + return evt->u.erat_error.effective_address; + break; + case MCE_ERROR_TYPE_TLB: + if (evt->u.tlb_error.effective_address_provided) + return evt->u.tlb_error.effective_address; + break; + default: + case MCE_ERROR_TYPE_UNKNOWN: + break; + } + return 0; +} +EXPORT_SYMBOL(get_mce_fault_addr); diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c new file mode 100644 index 000000000000..27c93f41166f --- /dev/null +++ b/arch/powerpc/kernel/mce_power.c @@ -0,0 +1,284 @@ +/* + * Machine check exception handling CPU-side for power7 and power8 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright 2013 IBM Corporation + * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> + */ + +#undef DEBUG +#define pr_fmt(fmt) "mce_power: " fmt + +#include <linux/types.h> +#include <linux/ptrace.h> +#include <asm/mmu.h> +#include <asm/mce.h> + +/* flush SLBs and reload */ +static void flush_and_reload_slb(void) +{ + struct slb_shadow *slb; + unsigned long i, n; + + /* Invalidate all SLBs */ + asm volatile("slbmte %0,%0; slbia" : : "r" (0)); + +#ifdef CONFIG_KVM_BOOK3S_HANDLER + /* + * If machine check is hit when in guest or in transition, we will + * only flush the SLBs and continue. + */ + if (get_paca()->kvm_hstate.in_guest) + return; +#endif + + /* For host kernel, reload the SLBs from shadow SLB buffer. */ + slb = get_slb_shadow(); + if (!slb) + return; + + n = min_t(u32, be32_to_cpu(slb->persistent), SLB_MIN_SIZE); + + /* Load up the SLB entries from shadow SLB */ + for (i = 0; i < n; i++) { + unsigned long rb = be64_to_cpu(slb->save_area[i].esid); + unsigned long rs = be64_to_cpu(slb->save_area[i].vsid); + + rb = (rb & ~0xFFFul) | i; + asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb)); + } +} + +static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) +{ + long handled = 1; + + /* + * flush and reload SLBs for SLB errors and flush TLBs for TLB errors. + * reset the error bits whenever we handle them so that at the end + * we can check whether we handled all of them or not. + * */ + if (dsisr & slb_error_bits) { + flush_and_reload_slb(); + /* reset error bits */ + dsisr &= ~(slb_error_bits); + } + if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) { + if (cur_cpu_spec && cur_cpu_spec->flush_tlb) + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + /* reset error bits */ + dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB; + } + /* Any other errors we don't understand? */ + if (dsisr & 0xffffffffUL) + handled = 0; + + return handled; +} + +static long mce_handle_derror_p7(uint64_t dsisr) +{ + return mce_handle_derror(dsisr, P7_DSISR_MC_SLB_ERRORS); +} + +static long mce_handle_common_ierror(uint64_t srr1) +{ + long handled = 0; + + switch (P7_SRR1_MC_IFETCH(srr1)) { + case 0: + break; + case P7_SRR1_MC_IFETCH_SLB_PARITY: + case P7_SRR1_MC_IFETCH_SLB_MULTIHIT: + /* flush and reload SLBs for SLB errors. */ + flush_and_reload_slb(); + handled = 1; + break; + case P7_SRR1_MC_IFETCH_TLB_MULTIHIT: + if (cur_cpu_spec && cur_cpu_spec->flush_tlb) { + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE); + handled = 1; + } + break; + default: + break; + } + + return handled; +} + +static long mce_handle_ierror_p7(uint64_t srr1) +{ + long handled = 0; + + handled = mce_handle_common_ierror(srr1); + + if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) { + flush_and_reload_slb(); + handled = 1; + } + return handled; +} + +static void mce_get_common_ierror(struct mce_error_info *mce_err, uint64_t srr1) +{ + switch (P7_SRR1_MC_IFETCH(srr1)) { + case P7_SRR1_MC_IFETCH_SLB_PARITY: + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY; + break; + case P7_SRR1_MC_IFETCH_SLB_MULTIHIT: + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT; + break; + case P7_SRR1_MC_IFETCH_TLB_MULTIHIT: + mce_err->error_type = MCE_ERROR_TYPE_TLB; + mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT; + break; + case P7_SRR1_MC_IFETCH_UE: + case P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL: + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH; + break; + case P7_SRR1_MC_IFETCH_UE_TLB_RELOAD: + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = + MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH; + break; + } +} + +static void mce_get_ierror_p7(struct mce_error_info *mce_err, uint64_t srr1) +{ + mce_get_common_ierror(mce_err, srr1); + if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE; + } +} + +static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr) +{ + if (dsisr & P7_DSISR_MC_UE) { + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE; + } else if (dsisr & P7_DSISR_MC_UE_TABLEWALK) { + mce_err->error_type = MCE_ERROR_TYPE_UE; + mce_err->u.ue_error_type = + MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE; + } else if (dsisr & P7_DSISR_MC_ERAT_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT; + } else if (dsisr & P7_DSISR_MC_SLB_PARITY_MFSLB) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY; + } else if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) { + mce_err->error_type = MCE_ERROR_TYPE_TLB; + mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT; + } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT_PARITY) { + mce_err->error_type = MCE_ERROR_TYPE_SLB; + mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE; + } +} + +long __machine_check_early_realmode_p7(struct pt_regs *regs) +{ + uint64_t srr1, addr; + long handled = 1; + struct mce_error_info mce_error_info = { 0 }; + + srr1 = regs->msr; + + /* + * Handle memory errors depending whether this was a load/store or + * ifetch exception. Also, populate the mce error_type and + * type-specific error_type from either SRR1 or DSISR, depending + * whether this was a load/store or ifetch exception + */ + if (P7_SRR1_MC_LOADSTORE(srr1)) { + handled = mce_handle_derror_p7(regs->dsisr); + mce_get_derror_p7(&mce_error_info, regs->dsisr); + addr = regs->dar; + } else { + handled = mce_handle_ierror_p7(srr1); + mce_get_ierror_p7(&mce_error_info, srr1); + addr = regs->nip; + } + + save_mce_event(regs, handled, &mce_error_info, addr); + return handled; +} + +static void mce_get_ierror_p8(struct mce_error_info *mce_err, uint64_t srr1) +{ + mce_get_common_ierror(mce_err, srr1); + if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } +} + +static void mce_get_derror_p8(struct mce_error_info *mce_err, uint64_t dsisr) +{ + mce_get_derror_p7(mce_err, dsisr); + if (dsisr & P8_DSISR_MC_ERAT_MULTIHIT_SEC) { + mce_err->error_type = MCE_ERROR_TYPE_ERAT; + mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + } +} + +static long mce_handle_ierror_p8(uint64_t srr1) +{ + long handled = 0; + + handled = mce_handle_common_ierror(srr1); + + if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) { + flush_and_reload_slb(); + handled = 1; + } + return handled; +} + +static long mce_handle_derror_p8(uint64_t dsisr) +{ + return mce_handle_derror(dsisr, P8_DSISR_MC_SLB_ERRORS); +} + +long __machine_check_early_realmode_p8(struct pt_regs *regs) +{ + uint64_t srr1, addr; + long handled = 1; + struct mce_error_info mce_error_info = { 0 }; + + srr1 = regs->msr; + + if (P7_SRR1_MC_LOADSTORE(srr1)) { + handled = mce_handle_derror_p8(regs->dsisr); + mce_get_derror_p8(&mce_error_info, regs->dsisr); + addr = regs->dar; + } else { + handled = mce_handle_ierror_p8(srr1); + mce_get_ierror_p8(&mce_error_info, srr1); + addr = regs->nip; + } + + save_mce_event(regs, handled, &mce_error_info, addr); + return handled; +} diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index e47d268727a4..879f09620f83 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -344,7 +344,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE) */ _KPROBE(flush_icache_range) BEGIN_FTR_SECTION - isync + PURGE_PREFETCHED_INS blr /* for 601, do nothing */ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) li r5,L1_CACHE_BYTES-1 @@ -448,6 +448,7 @@ _GLOBAL(invalidate_dcache_range) */ _GLOBAL(__flush_dcache_icache) BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS blr END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ @@ -489,6 +490,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_44x) */ _GLOBAL(__flush_dcache_icache_phys) BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS blr /* for 601, do nothing */ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) mfmsr r10 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 64bf8db12b15..3d0249599d52 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -67,6 +67,7 @@ PPC64_CACHES: _KPROBE(flush_icache_range) BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS blr END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) /* @@ -211,6 +212,11 @@ _GLOBAL(__flush_dcache_icache) * Different systems have different cache line sizes */ +BEGIN_FTR_SECTION + PURGE_PREFETCHED_INS + blr +END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) + /* Flush the dcache */ ld r7,PPC64_CACHES@toc(r2) clrrdi r3,r3,PAGE_SHIFT /* Page align */ diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 0620eaaaad45..623c356fe34f 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -99,12 +99,28 @@ static inline void free_lppacas(void) { } * 3 persistent SLBs are registered here. The buffer will be zero * initially, hence will all be invaild until we actually write them. */ -struct slb_shadow slb_shadow[] __cacheline_aligned = { - [0 ... (NR_CPUS-1)] = { - .persistent = cpu_to_be32(SLB_NUM_BOLTED), - .buffer_length = cpu_to_be32(sizeof(struct slb_shadow)), - }, -}; +static struct slb_shadow *slb_shadow; + +static void __init allocate_slb_shadows(int nr_cpus, int limit) +{ + int size = PAGE_ALIGN(sizeof(struct slb_shadow) * nr_cpus); + slb_shadow = __va(memblock_alloc_base(size, PAGE_SIZE, limit)); + memset(slb_shadow, 0, size); +} + +static struct slb_shadow * __init init_slb_shadow(int cpu) +{ + struct slb_shadow *s = &slb_shadow[cpu]; + + s->persistent = cpu_to_be32(SLB_NUM_BOLTED); + s->buffer_length = cpu_to_be32(sizeof(*s)); + + return s; +} + +#else /* CONFIG_PPC_STD_MMU_64 */ + +static void __init allocate_slb_shadows(int nr_cpus, int limit) { } #endif /* CONFIG_PPC_STD_MMU_64 */ @@ -142,7 +158,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->__current = &init_task; new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL; #ifdef CONFIG_PPC_STD_MMU_64 - new_paca->slb_shadow_ptr = &slb_shadow[cpu]; + new_paca->slb_shadow_ptr = init_slb_shadow(cpu); #endif /* CONFIG_PPC_STD_MMU_64 */ } @@ -190,6 +206,8 @@ void __init allocate_pacas(void) allocate_lppacas(nr_cpu_ids, limit); + allocate_slb_shadows(nr_cpu_ids, limit); + /* Can't use for_each_*_cpu, as they aren't functional yet */ for (cpu = 0; cpu < nr_cpu_ids; cpu++) initialise_paca(&paca[cpu], cpu); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 4085aaa9478f..2232aff66059 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -520,9 +520,6 @@ static void __init irqstack_early_init(void) #ifdef CONFIG_PPC_BOOK3E static void __init exc_lvl_early_init(void) { - extern unsigned int interrupt_base_book3e; - extern unsigned int exc_debug_debug_book3e; - unsigned int i; for_each_possible_cpu(i) { @@ -535,8 +532,7 @@ static void __init exc_lvl_early_init(void) } if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) - patch_branch(&interrupt_base_book3e + (0x040 / 4) + 1, - (unsigned long)&exc_debug_debug_book3e, 0); + patch_exception(0x040, exc_debug_debug_book3e); } #else #define exc_lvl_early_init() @@ -544,7 +540,8 @@ static void __init exc_lvl_early_init(void) /* * Stack space used when we detect a bad kernel stack pointer, and - * early in SMP boots before relocation is enabled. + * early in SMP boots before relocation is enabled. Exclusive emergency + * stack for machine checks. */ static void __init emergency_stack_init(void) { @@ -567,6 +564,13 @@ static void __init emergency_stack_init(void) sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); sp += THREAD_SIZE; paca[i].emergency_sp = __va(sp); + +#ifdef CONFIG_PPC_BOOK3S_64 + /* emergency stack for machine check exception handling. */ + sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); + sp += THREAD_SIZE; + paca[i].mc_emergency_sp = __va(sp); +#endif } } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index c1cf4a1522d9..ac2621af3154 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -369,13 +369,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid)); cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid)); - if (smp_ops) - if (smp_ops->probe) - max_cpus = smp_ops->probe(); - else - max_cpus = NR_CPUS; - else - max_cpus = 1; + if (smp_ops && smp_ops->probe) + smp_ops->probe(); } void smp_prepare_boot_cpu(void) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index b4e667663d9b..cad777eb613a 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -108,14 +108,14 @@ void ppc_enable_pmcs(void) } EXPORT_SYMBOL(ppc_enable_pmcs); -#define SYSFS_PMCSETUP(NAME, ADDRESS) \ +#define __SYSFS_SPRSETUP(NAME, ADDRESS, EXTRA) \ static void read_##NAME(void *val) \ { \ *(unsigned long *)val = mfspr(ADDRESS); \ } \ static void write_##NAME(void *val) \ { \ - ppc_enable_pmcs(); \ + EXTRA; \ mtspr(ADDRESS, *(unsigned long *)val); \ } \ static ssize_t show_##NAME(struct device *dev, \ @@ -140,6 +140,10 @@ static ssize_t __used \ return count; \ } +#define SYSFS_PMCSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP(NAME, ADDRESS, ppc_enable_pmcs()) +#define SYSFS_SPRSETUP(NAME, ADDRESS) \ + __SYSFS_SPRSETUP(NAME, ADDRESS, ) /* Let's define all possible registers, we'll only hook up the ones * that are implemented on the current processor @@ -175,10 +179,10 @@ SYSFS_PMCSETUP(pmc7, SPRN_PMC7); SYSFS_PMCSETUP(pmc8, SPRN_PMC8); SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); -SYSFS_PMCSETUP(purr, SPRN_PURR); -SYSFS_PMCSETUP(spurr, SPRN_SPURR); -SYSFS_PMCSETUP(dscr, SPRN_DSCR); -SYSFS_PMCSETUP(pir, SPRN_PIR); +SYSFS_SPRSETUP(purr, SPRN_PURR); +SYSFS_SPRSETUP(spurr, SPRN_SPURR); +SYSFS_SPRSETUP(dscr, SPRN_DSCR); +SYSFS_SPRSETUP(pir, SPRN_PIR); /* Lets only enable read for phyp resources and @@ -249,34 +253,34 @@ SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3); SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4); SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5); #ifdef CONFIG_DEBUG_KERNEL -SYSFS_PMCSETUP(hid0, SPRN_HID0); -SYSFS_PMCSETUP(hid1, SPRN_HID1); -SYSFS_PMCSETUP(hid4, SPRN_HID4); -SYSFS_PMCSETUP(hid5, SPRN_HID5); -SYSFS_PMCSETUP(ima0, SPRN_PA6T_IMA0); -SYSFS_PMCSETUP(ima1, SPRN_PA6T_IMA1); -SYSFS_PMCSETUP(ima2, SPRN_PA6T_IMA2); -SYSFS_PMCSETUP(ima3, SPRN_PA6T_IMA3); -SYSFS_PMCSETUP(ima4, SPRN_PA6T_IMA4); -SYSFS_PMCSETUP(ima5, SPRN_PA6T_IMA5); -SYSFS_PMCSETUP(ima6, SPRN_PA6T_IMA6); -SYSFS_PMCSETUP(ima7, SPRN_PA6T_IMA7); -SYSFS_PMCSETUP(ima8, SPRN_PA6T_IMA8); -SYSFS_PMCSETUP(ima9, SPRN_PA6T_IMA9); -SYSFS_PMCSETUP(imaat, SPRN_PA6T_IMAAT); -SYSFS_PMCSETUP(btcr, SPRN_PA6T_BTCR); -SYSFS_PMCSETUP(pccr, SPRN_PA6T_PCCR); -SYSFS_PMCSETUP(rpccr, SPRN_PA6T_RPCCR); -SYSFS_PMCSETUP(der, SPRN_PA6T_DER); -SYSFS_PMCSETUP(mer, SPRN_PA6T_MER); -SYSFS_PMCSETUP(ber, SPRN_PA6T_BER); -SYSFS_PMCSETUP(ier, SPRN_PA6T_IER); -SYSFS_PMCSETUP(sier, SPRN_PA6T_SIER); -SYSFS_PMCSETUP(siar, SPRN_PA6T_SIAR); -SYSFS_PMCSETUP(tsr0, SPRN_PA6T_TSR0); -SYSFS_PMCSETUP(tsr1, SPRN_PA6T_TSR1); -SYSFS_PMCSETUP(tsr2, SPRN_PA6T_TSR2); -SYSFS_PMCSETUP(tsr3, SPRN_PA6T_TSR3); +SYSFS_SPRSETUP(hid0, SPRN_HID0); +SYSFS_SPRSETUP(hid1, SPRN_HID1); +SYSFS_SPRSETUP(hid4, SPRN_HID4); +SYSFS_SPRSETUP(hid5, SPRN_HID5); +SYSFS_SPRSETUP(ima0, SPRN_PA6T_IMA0); +SYSFS_SPRSETUP(ima1, SPRN_PA6T_IMA1); +SYSFS_SPRSETUP(ima2, SPRN_PA6T_IMA2); +SYSFS_SPRSETUP(ima3, SPRN_PA6T_IMA3); +SYSFS_SPRSETUP(ima4, SPRN_PA6T_IMA4); +SYSFS_SPRSETUP(ima5, SPRN_PA6T_IMA5); +SYSFS_SPRSETUP(ima6, SPRN_PA6T_IMA6); +SYSFS_SPRSETUP(ima7, SPRN_PA6T_IMA7); +SYSFS_SPRSETUP(ima8, SPRN_PA6T_IMA8); +SYSFS_SPRSETUP(ima9, SPRN_PA6T_IMA9); +SYSFS_SPRSETUP(imaat, SPRN_PA6T_IMAAT); +SYSFS_SPRSETUP(btcr, SPRN_PA6T_BTCR); +SYSFS_SPRSETUP(pccr, SPRN_PA6T_PCCR); +SYSFS_SPRSETUP(rpccr, SPRN_PA6T_RPCCR); +SYSFS_SPRSETUP(der, SPRN_PA6T_DER); +SYSFS_SPRSETUP(mer, SPRN_PA6T_MER); +SYSFS_SPRSETUP(ber, SPRN_PA6T_BER); +SYSFS_SPRSETUP(ier, SPRN_PA6T_IER); +SYSFS_SPRSETUP(sier, SPRN_PA6T_SIER); +SYSFS_SPRSETUP(siar, SPRN_PA6T_SIAR); +SYSFS_SPRSETUP(tsr0, SPRN_PA6T_TSR0); +SYSFS_SPRSETUP(tsr1, SPRN_PA6T_TSR1); +SYSFS_SPRSETUP(tsr2, SPRN_PA6T_TSR2); +SYSFS_SPRSETUP(tsr3, SPRN_PA6T_TSR3); #endif /* CONFIG_DEBUG_KERNEL */ #endif /* HAS_PPC_PMC_PA6T */ diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index b3b144121cc9..afb1b56ef4fa 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -510,7 +510,6 @@ void timer_interrupt(struct pt_regs * regs) */ may_hard_irq_enable(); - __get_cpu_var(irq_stat).timer_irqs++; #if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) @@ -532,10 +531,12 @@ void timer_interrupt(struct pt_regs * regs) *next_tb = ~(u64)0; if (evt->event_handler) evt->event_handler(evt); + __get_cpu_var(irq_stat).timer_irqs_event++; } else { now = *next_tb - now; if (now <= DECREMENTER_MAX) set_dec((int)now); + __get_cpu_var(irq_stat).timer_irqs_others++; } #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 907a472f9a9e..330841766b09 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -285,6 +285,21 @@ void system_reset_exception(struct pt_regs *regs) /* What should we do here? We could issue a shutdown or hard reset. */ } + +/* + * This function is called in real mode. Strictly no printk's please. + * + * regs->nip and regs->msr contains srr0 and ssr1. + */ +long machine_check_early(struct pt_regs *regs) +{ + long handled = 0; + + if (cur_cpu_spec && cur_cpu_spec->machine_check_early) + handled = cur_cpu_spec->machine_check_early(regs); + return handled; +} + #endif /* diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 76a64821f4a2..826d8bd9e522 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -518,16 +518,18 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; dma_addr_t ret = DMA_ERROR_CODE; - if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE))) { + tbl = get_iommu_table_base(dev); + if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) { atomic_inc(&viodev->cmo.allocs_failed); return ret; } ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs); if (unlikely(dma_mapping_error(dev, ret))) { - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE)); + vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))); atomic_inc(&viodev->cmo.allocs_failed); } @@ -540,10 +542,12 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; + tbl = get_iommu_table_base(dev); dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs); - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE)); + vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))); } static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, @@ -551,12 +555,14 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; struct scatterlist *sgl; int ret, count = 0; size_t alloc_size = 0; + tbl = get_iommu_table_base(dev); for (sgl = sglist; count < nelems; count++, sgl++) - alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE); + alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl)); if (vio_cmo_alloc(viodev, alloc_size)) { atomic_inc(&viodev->cmo.allocs_failed); @@ -572,7 +578,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, } for (sgl = sglist, count = 0; count < ret; count++, sgl++) - alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE); + alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl)); if (alloc_size) vio_cmo_dealloc(viodev, alloc_size); @@ -585,12 +591,14 @@ static void vio_dma_iommu_unmap_sg(struct device *dev, struct dma_attrs *attrs) { struct vio_dev *viodev = to_vio_dev(dev); + struct iommu_table *tbl; struct scatterlist *sgl; size_t alloc_size = 0; int count = 0; + tbl = get_iommu_table_base(dev); for (sgl = sglist; count < nelems; count++, sgl++) - alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE); + alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl)); dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs); @@ -706,11 +714,14 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) { struct vio_cmo_dev_entry *dev_ent; struct device *dev = &viodev->dev; + struct iommu_table *tbl; struct vio_driver *viodrv = to_vio_driver(dev->driver); unsigned long flags; size_t size; bool dma_capable = false; + tbl = get_iommu_table_base(dev); + /* A device requires entitlement if it has a DMA window property */ switch (viodev->family) { case VDEVICE: @@ -736,7 +747,8 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev) return -EINVAL; } - viodev->cmo.desired = IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev)); + viodev->cmo.desired = + IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev), tbl); if (viodev->cmo.desired < VIO_CMO_MIN_ENT) viodev->cmo.desired = VIO_CMO_MIN_ENT; size = VIO_CMO_MIN_ENT; @@ -1176,9 +1188,10 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) &tbl->it_index, &offset, &size); /* TCE table size - measured in tce entries */ - tbl->it_size = size >> IOMMU_PAGE_SHIFT; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; + tbl->it_size = size >> tbl->it_page_shift; /* offset for VIO should always be 0 */ - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; + tbl->it_offset = offset >> tbl->it_page_shift; tbl->it_busno = 0; tbl->it_type = TCE_VB; tbl->it_blocksize = 16; diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index a353c485808c..768a9f977c00 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -12,6 +12,7 @@ #include <linux/kvm_host.h> #include <linux/kernel.h> #include <asm/opal.h> +#include <asm/mce.h> /* SRR1 bits for machine check on POWER7 */ #define SRR1_MC_LDSTERR (1ul << (63-42)) @@ -58,18 +59,6 @@ static void reload_slb(struct kvm_vcpu *vcpu) } } -/* POWER7 TLB flush */ -static void flush_tlb_power7(struct kvm_vcpu *vcpu) -{ - unsigned long i, rb; - - rb = TLBIEL_INVAL_SET_LPID; - for (i = 0; i < POWER7_TLB_SETS; ++i) { - asm volatile("tlbiel %0" : : "r" (rb)); - rb += 1 << TLBIEL_INVAL_SET_SHIFT; - } -} - /* * On POWER7, see if we can handle a machine check that occurred inside * the guest in real mode, without switching to the host partition. @@ -79,9 +68,7 @@ static void flush_tlb_power7(struct kvm_vcpu *vcpu) static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) { unsigned long srr1 = vcpu->arch.shregs.msr; -#ifdef CONFIG_PPC_POWERNV - struct opal_machine_check_event *opal_evt; -#endif + struct machine_check_event mce_evt; long handled = 1; if (srr1 & SRR1_MC_LDSTERR) { @@ -96,7 +83,8 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) DSISR_MC_SLB_PARITY | DSISR_MC_DERAT_MULTI); } if (dsisr & DSISR_MC_TLB_MULTI) { - flush_tlb_power7(vcpu); + if (cur_cpu_spec && cur_cpu_spec->flush_tlb) + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET_LPID); dsisr &= ~DSISR_MC_TLB_MULTI; } /* Any other errors we don't understand? */ @@ -113,28 +101,38 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) reload_slb(vcpu); break; case SRR1_MC_IFETCH_TLBMULTI: - flush_tlb_power7(vcpu); + if (cur_cpu_spec && cur_cpu_spec->flush_tlb) + cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET_LPID); break; default: handled = 0; } -#ifdef CONFIG_PPC_POWERNV /* - * See if OPAL has already handled the condition. - * We assume that if the condition is recovered then OPAL + * See if we have already handled the condition in the linux host. + * We assume that if the condition is recovered then linux host * will have generated an error log event that we will pick * up and log later. + * Don't release mce event now. In case if condition is not + * recovered we do guest exit and go back to linux host machine + * check handler. Hence we need make sure that current mce event + * is available for linux host to consume. */ - opal_evt = local_paca->opal_mc_evt; - if (opal_evt->version == OpalMCE_V1 && - (opal_evt->severity == OpalMCE_SEV_NO_ERROR || - opal_evt->disposition == OpalMCE_DISPOSITION_RECOVERED)) + if (!get_mce_event(&mce_evt, MCE_EVENT_DONTRELEASE)) + goto out; + + if (mce_evt.version == MCE_V1 && + (mce_evt.severity == MCE_SEV_NO_ERROR || + mce_evt.disposition == MCE_DISPOSITION_RECOVERED)) handled = 1; +out: + /* + * If we have handled the error, then release the mce event because + * we will be delivering machine check to guest. + */ if (handled) - opal_evt->in_use = 0; -#endif + release_mce_event(); return handled; } diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 17e5b2364312..d5edbeb8eb82 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -159,6 +159,21 @@ unsigned int translate_branch(const unsigned int *dest, const unsigned int *src) return 0; } +#ifdef CONFIG_PPC_BOOK3E_64 +void __patch_exception(int exc, unsigned long addr) +{ + extern unsigned int interrupt_base_book3e; + unsigned int *ibase = &interrupt_base_book3e; + + /* Our exceptions vectors start with a NOP and -then- a branch + * to deal with single stepping from userspace which stops on + * the second instruction. Thus we need to patch the second + * instruction of the exception, not the first one + */ + + patch_branch(ibase + (exc / 4) + 1, addr, 0); +} +#endif #ifdef CONFIG_CODE_PATCHING_SELFTEST diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index d3cbda62857b..1136d26a95ae 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -148,7 +148,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ andc r0,r30,r0 /* r0 = pte & ~r0 */ rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */ + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + ori r3,r3,HPTE_R_C | HPTE_R_M /* We eventually do the icache sync here (maybe inline that * code rather than call a C function...) @@ -457,7 +460,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ andc r0,r3,r0 /* r0 = pte & ~r0 */ rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */ + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + ori r3,r3,HPTE_R_C | HPTE_R_M /* We eventually do the icache sync here (maybe inline that * code rather than call a C function...) @@ -795,7 +801,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ andc r0,r30,r0 /* r0 = pte & ~r0 */ rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */ + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + ori r3,r3,HPTE_R_C | HPTE_R_M /* We eventually do the icache sync here (maybe inline that * code rather than call a C function...) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 6176b3cdf579..de6881259aef 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -169,9 +169,10 @@ static unsigned long htab_convert_pte_flags(unsigned long pteflags) if ((pteflags & _PAGE_USER) && !((pteflags & _PAGE_RW) && (pteflags & _PAGE_DIRTY))) rflags |= 1; - - /* Always add C */ - return rflags | HPTE_R_C; + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + return rflags | HPTE_R_C | HPTE_R_M; } int htab_bolt_mapping(unsigned long vstart, unsigned long vend, diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 34de9e0cdc34..826893fcb3a7 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -127,7 +127,11 @@ repeat: /* Add in WIMG bits */ rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | - _PAGE_COHERENT | _PAGE_GUARDED)); + _PAGE_GUARDED)); + /* + * enable the memory coherence always + */ + rflags |= HPTE_R_M; /* Insert into the hash table, primary slot */ slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index 0b7fb6761015..a5bcf9301196 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -99,6 +99,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, /* Add in WIMG bits */ rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT | _PAGE_GUARDED)); + /* + * enable the memory coherence always + */ + rflags |= HPTE_R_M; slot = hpte_insert_repeating(hash, vpn, pa, rflags, 0, mmu_psize, ssize); diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 841e0d00863c..ad90429bbd8b 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -174,7 +174,7 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { #ifdef CONFIG_DEBUG_VM - WARN_ON(pte_present(*ptep)); + WARN_ON(pte_val(*ptep) & _PAGE_PRESENT); #endif /* Note: mm->context.id might not yet have been assigned as * this context might not have been activated yet when this diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 9d95786aa80f..02e8681fb865 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -687,7 +687,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { #ifdef CONFIG_DEBUG_VM - WARN_ON(!pmd_none(*pmdp)); + WARN_ON(pmd_val(*pmdp) & _PAGE_PRESENT); assert_spin_locked(&mm->page_table_lock); WARN_ON(!pmd_trans_huge(pmd)); #endif diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index 358d74303138..8805b7b87dc6 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -518,25 +518,6 @@ static void setup_page_sizes(void) } } -static void __patch_exception(int exc, unsigned long addr) -{ - extern unsigned int interrupt_base_book3e; - unsigned int *ibase = &interrupt_base_book3e; - - /* Our exceptions vectors start with a NOP and -then- a branch - * to deal with single stepping from userspace which stops on - * the second instruction. Thus we need to patch the second - * instruction of the exception, not the first one - */ - - patch_branch(ibase + (exc / 4) + 1, addr, 0); -} - -#define patch_exception(exc, name) do { \ - extern unsigned int name; \ - __patch_exception((exc), (unsigned long)&name); \ -} while (0) - static void setup_mmu_htw(void) { /* Check if HW tablewalk is present, and if yes, enable it by: diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index 670a033264c0..2bdc8c862c46 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -99,7 +99,6 @@ config SBC834x config ASP834x bool "Analogue & Micro ASP 834x" select PPC_MPC834x - select REDBOOT help This enables support for the Analogue & Micro ASP 83xx board. diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig index 8dec3c0911ad..bd6f1a1cf922 100644 --- a/arch/powerpc/platforms/8xx/Kconfig +++ b/arch/powerpc/platforms/8xx/Kconfig @@ -45,7 +45,6 @@ config PPC_EP88XC config PPC_ADDER875 bool "Analogue & Micro Adder 875" select CPM1 - select REDBOOT help This enables support for the Analogue & Micro Adder 875 board. diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index bca2465a9c34..434fda39bf8b 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -72,6 +72,7 @@ config PPC_BOOK3S_64 select PPC_HAVE_PMU_SUPPORT select SYS_SUPPORTS_HUGETLBFS select HAVE_ARCH_TRANSPARENT_HUGEPAGE if PPC_64K_PAGES + select ARCH_SUPPORTS_NUMA_BALANCING config PPC_BOOK3E_64 bool "Embedded processors" diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c index c34ee4e60873..d4d245c0d787 100644 --- a/arch/powerpc/platforms/cell/beat_htab.c +++ b/arch/powerpc/platforms/cell/beat_htab.c @@ -111,7 +111,7 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group, DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); if (rflags & _PAGE_NO_CACHE) - hpte_r &= ~_PAGE_COHERENT; + hpte_r &= ~HPTE_R_M; raw_spin_lock(&beat_htab_lock); lpar_rc = beat_read_mask(hpte_group); @@ -337,7 +337,7 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group, DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r); if (rflags & _PAGE_NO_CACHE) - hpte_r &= ~_PAGE_COHERENT; + hpte_r &= ~HPTE_R_M; /* insert into not-volted entry */ lpar_rc = beat_insert_htab_entry3(0, hpte_group, hpte_v, hpte_r, diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index b53560660b72..2b90ff8a93be 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -197,7 +197,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); - for (i = 0; i < npages; i++, uaddr += IOMMU_PAGE_SIZE) + for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift) io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask); mb(); @@ -430,7 +430,7 @@ static void cell_iommu_setup_hardware(struct cbe_iommu *iommu, { cell_iommu_setup_stab(iommu, base, size, 0, 0); iommu->ptab = cell_iommu_alloc_ptab(iommu, base, size, 0, 0, - IOMMU_PAGE_SHIFT); + IOMMU_PAGE_SHIFT_4K); cell_iommu_enable_hardware(iommu); } @@ -487,8 +487,10 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np, window->table.it_blocksize = 16; window->table.it_base = (unsigned long)iommu->ptab; window->table.it_index = iommu->nid; - window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT) + pte_offset; - window->table.it_size = size >> IOMMU_PAGE_SHIFT; + window->table.it_page_shift = IOMMU_PAGE_SHIFT_4K; + window->table.it_offset = + (offset >> window->table.it_page_shift) + pte_offset; + window->table.it_size = size >> window->table.it_page_shift; iommu_init_table(&window->table, iommu->nid); @@ -773,7 +775,7 @@ static void __init cell_iommu_init_one(struct device_node *np, /* Setup the iommu_table */ cell_iommu_setup_window(iommu, np, base, size, - offset >> IOMMU_PAGE_SHIFT); + offset >> IOMMU_PAGE_SHIFT_4K); } static void __init cell_disable_iommus(void) @@ -1122,7 +1124,7 @@ static int __init cell_iommu_fixed_mapping_init(void) cell_iommu_setup_stab(iommu, dbase, dsize, fbase, fsize); iommu->ptab = cell_iommu_alloc_ptab(iommu, dbase, dsize, 0, 0, - IOMMU_PAGE_SHIFT); + IOMMU_PAGE_SHIFT_4K); cell_iommu_setup_fixed_ptab(iommu, np, dbase, dsize, fbase, fsize); cell_iommu_enable_hardware(iommu); diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 7d2d036754b5..2e576f2ae442 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -138,8 +138,11 @@ static void iommu_table_iobmap_setup(void) pr_debug(" -> %s\n", __func__); iommu_table_iobmap.it_busno = 0; iommu_table_iobmap.it_offset = 0; + iommu_table_iobmap.it_page_shift = IOBMAP_PAGE_SHIFT; + /* it_size is in number of entries */ - iommu_table_iobmap.it_size = 0x80000000 >> IOBMAP_PAGE_SHIFT; + iommu_table_iobmap.it_size = + 0x80000000 >> iommu_table_iobmap.it_page_shift; /* Initialize the common IOMMU code */ iommu_table_iobmap.it_base = (unsigned long)iob_l2_base; diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 9fced3f6d2dc..895e8a20a3fc 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -13,11 +13,6 @@ config PPC_POWERNV select ARCH_RANDOM default y -config POWERNV_MSI - bool "Support PCI MSI on PowerNV platform" - depends on PCI_MSI - default y - config PPC_POWERNV_RTAS depends on PPC_POWERNV bool "Support for RTAS based PowerNV platforms such as BML" diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 873fa1370dc4..8d767fde5a6a 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o obj-$(CONFIG_EEH) += eeh-ioda.o eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o +obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index d7ddcee7feb8..9b1db254898a 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -578,11 +578,8 @@ static int ioda_eeh_get_log(struct eeh_pe *pe, int severity, return -EIO; } - /* - * FIXME: We probably need log the error in somewhere. - * Lets make it up in future. - */ - /* pr_info("%s", phb->diag.blob); */ + /* The PHB diag-data is always indicative */ + pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); spin_unlock_irqrestore(&phb->lock, flags); @@ -670,143 +667,9 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose) } } -static void ioda_eeh_p7ioc_phb_diag(struct pci_controller *hose, - struct OpalIoPhbErrorCommon *common) -{ - struct OpalIoP7IOCPhbErrorData *data; - int i; - - data = (struct OpalIoP7IOCPhbErrorData *)common; - - pr_info("P7IOC PHB#%x Diag-data (Version: %d)\n\n", - hose->global_number, common->version); - - pr_info(" brdgCtl: %08x\n", data->brdgCtl); - - pr_info(" portStatusReg: %08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); - - pr_info(" deviceStatus: %08x\n", data->deviceStatus); - pr_info(" slotStatus: %08x\n", data->slotStatus); - pr_info(" linkStatus: %08x\n", data->linkStatus); - pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); - pr_info(" devSecStatus: %08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); - pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); - pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); - pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); - pr_info(" sourceId: %08x\n", data->sourceId); - - pr_info(" errorClass: %016llx\n", data->errorClass); - pr_info(" correlator: %016llx\n", data->correlator); - pr_info(" p7iocPlssr: %016llx\n", data->p7iocPlssr); - pr_info(" p7iocCsr: %016llx\n", data->p7iocCsr); - pr_info(" lemFir: %016llx\n", data->lemFir); - pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); - pr_info(" lemWOF: %016llx\n", data->lemWOF); - pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); - - for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) { - if ((data->pestA[i] >> 63) == 0 && - (data->pestB[i] >> 63) == 0) - continue; - - pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); - pr_info(" PESTB: %016llx\n", data->pestB[i]); - } -} - -static void ioda_eeh_phb3_phb_diag(struct pci_controller *hose, - struct OpalIoPhbErrorCommon *common) -{ - struct OpalIoPhb3ErrorData *data; - int i; - - data = (struct OpalIoPhb3ErrorData*)common; - pr_info("PHB3 PHB#%x Diag-data (Version: %d)\n\n", - hose->global_number, common->version); - - pr_info(" brdgCtl: %08x\n", data->brdgCtl); - - pr_info(" portStatusReg: %08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); - - pr_info(" deviceStatus: %08x\n", data->deviceStatus); - pr_info(" slotStatus: %08x\n", data->slotStatus); - pr_info(" linkStatus: %08x\n", data->linkStatus); - pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); - pr_info(" devSecStatus: %08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); - pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); - pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); - pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); - pr_info(" sourceId: %08x\n", data->sourceId); - pr_info(" errorClass: %016llx\n", data->errorClass); - pr_info(" correlator: %016llx\n", data->correlator); - pr_info(" nFir: %016llx\n", data->nFir); - pr_info(" nFirMask: %016llx\n", data->nFirMask); - pr_info(" nFirWOF: %016llx\n", data->nFirWOF); - pr_info(" PhbPlssr: %016llx\n", data->phbPlssr); - pr_info(" PhbCsr: %016llx\n", data->phbCsr); - pr_info(" lemFir: %016llx\n", data->lemFir); - pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); - pr_info(" lemWOF: %016llx\n", data->lemWOF); - pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); - - for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) { - if ((data->pestA[i] >> 63) == 0 && - (data->pestB[i] >> 63) == 0) - continue; - - pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); - pr_info(" PESTB: %016llx\n", data->pestB[i]); - } -} - static void ioda_eeh_phb_diag(struct pci_controller *hose) { struct pnv_phb *phb = hose->private_data; - struct OpalIoPhbErrorCommon *common; long rc; rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, @@ -817,18 +680,7 @@ static void ioda_eeh_phb_diag(struct pci_controller *hose) return; } - common = (struct OpalIoPhbErrorCommon *)phb->diag.blob; - switch (common->ioType) { - case OPAL_PHB_ERROR_DATA_TYPE_P7IOC: - ioda_eeh_p7ioc_phb_diag(hose, common); - break; - case OPAL_PHB_ERROR_DATA_TYPE_PHB3: - ioda_eeh_phb3_phb_diag(hose, common); - break; - default: - pr_warning("%s: Unrecognized I/O chip %d\n", - __func__, common->ioType); - } + pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); } static int ioda_eeh_get_phb_pe(struct pci_controller *hose, diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index 6ffa6b1ec5b7..4aeae4f36e1d 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -103,27 +103,6 @@ struct image_header_t { uint32_t size; }; -/* Scatter/gather entry */ -struct opal_sg_entry { - void *data; - long length; -}; - -/* We calculate number of entries based on PAGE_SIZE */ -#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry)) - -/* - * This struct is very similar but not identical to that - * needed by the opal flash update. All we need to do for - * opal is rewrite num_entries into a version/length and - * translate the pointers to absolute. - */ -struct opal_sg_list { - unsigned long num_entries; - struct opal_sg_list *next; - struct opal_sg_entry entry[SG_ENTRIES_PER_NODE]; -}; - struct validate_flash_t { int status; /* Return status */ void *buf; /* Candiate image buffer */ @@ -333,7 +312,7 @@ static struct opal_sg_list *image_data_to_sglist(void) addr = image_data.data; size = image_data.size; - sg1 = kzalloc((sizeof(struct opal_sg_list)), GFP_KERNEL); + sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!sg1) return NULL; @@ -351,8 +330,7 @@ static struct opal_sg_list *image_data_to_sglist(void) sg1->num_entries++; if (sg1->num_entries >= SG_ENTRIES_PER_NODE) { - sg1->next = kzalloc((sizeof(struct opal_sg_list)), - GFP_KERNEL); + sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!sg1->next) { pr_err("%s : Failed to allocate memory\n", __func__); @@ -402,7 +380,10 @@ static int opal_flash_update(int op) else sg->next = NULL; - /* Make num_entries into the version/length field */ + /* + * Convert num_entries to version/length format + * to satisfy OPAL. + */ sg->num_entries = (SG_LIST_VERSION << 56) | (sg->num_entries * sizeof(struct opal_sg_entry) + 16); } diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c new file mode 100644 index 000000000000..ec4132239cdf --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c @@ -0,0 +1,146 @@ +/* + * OPAL asynchronus Memory error handling support in PowreNV. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright 2013 IBM Corporation + * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> + */ + +#undef DEBUG + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of.h> +#include <linux/mm.h> +#include <linux/slab.h> + +#include <asm/opal.h> +#include <asm/cputable.h> + +static int opal_mem_err_nb_init; +static LIST_HEAD(opal_memory_err_list); +static DEFINE_SPINLOCK(opal_mem_err_lock); + +struct OpalMsgNode { + struct list_head list; + struct opal_msg msg; +}; + +static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt) +{ + uint64_t paddr_start, paddr_end; + + pr_debug("%s: Retrived memory error event, type: 0x%x\n", + __func__, merr_evt->type); + switch (merr_evt->type) { + case OPAL_MEM_ERR_TYPE_RESILIENCE: + paddr_start = merr_evt->u.resilience.physical_address_start; + paddr_end = merr_evt->u.resilience.physical_address_end; + break; + case OPAL_MEM_ERR_TYPE_DYN_DALLOC: + paddr_start = merr_evt->u.dyn_dealloc.physical_address_start; + paddr_end = merr_evt->u.dyn_dealloc.physical_address_end; + break; + default: + return; + } + + for (; paddr_start < paddr_end; paddr_start += PAGE_SIZE) { + memory_failure(paddr_start >> PAGE_SHIFT, 0, 0); + } +} + +static void handle_memory_error(void) +{ + unsigned long flags; + struct OpalMemoryErrorData *merr_evt; + struct OpalMsgNode *msg_node; + + spin_lock_irqsave(&opal_mem_err_lock, flags); + while (!list_empty(&opal_memory_err_list)) { + msg_node = list_entry(opal_memory_err_list.next, + struct OpalMsgNode, list); + list_del(&msg_node->list); + spin_unlock_irqrestore(&opal_mem_err_lock, flags); + + merr_evt = (struct OpalMemoryErrorData *) + &msg_node->msg.params[0]; + handle_memory_error_event(merr_evt); + kfree(msg_node); + spin_lock_irqsave(&opal_mem_err_lock, flags); + } + spin_unlock_irqrestore(&opal_mem_err_lock, flags); +} + +static void mem_error_handler(struct work_struct *work) +{ + handle_memory_error(); +} + +static DECLARE_WORK(mem_error_work, mem_error_handler); + +/* + * opal_memory_err_event - notifier handler that queues up the opal message + * to be preocessed later. + */ +static int opal_memory_err_event(struct notifier_block *nb, + unsigned long msg_type, void *msg) +{ + unsigned long flags; + struct OpalMsgNode *msg_node; + + if (msg_type != OPAL_MSG_MEM_ERR) + return 0; + + msg_node = kzalloc(sizeof(*msg_node), GFP_ATOMIC); + if (!msg_node) { + pr_err("MEMORY_ERROR: out of memory, Opal message event not" + "handled\n"); + return -ENOMEM; + } + memcpy(&msg_node->msg, msg, sizeof(struct opal_msg)); + + spin_lock_irqsave(&opal_mem_err_lock, flags); + list_add(&msg_node->list, &opal_memory_err_list); + spin_unlock_irqrestore(&opal_mem_err_lock, flags); + + schedule_work(&mem_error_work); + return 0; +} + +static struct notifier_block opal_mem_err_nb = { + .notifier_call = opal_memory_err_event, + .next = NULL, + .priority = 0, +}; + +static int __init opal_mem_err_init(void) +{ + int ret; + + if (!opal_mem_err_nb_init) { + ret = opal_message_notifier_register( + OPAL_MSG_MEM_ERR, &opal_mem_err_nb); + if (ret) { + pr_err("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + opal_mem_err_nb_init = 1; + } + return 0; +} +subsys_initcall(opal_mem_err_init); diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c index 7d07c7e80ec0..b1885db8fdf3 100644 --- a/arch/powerpc/platforms/powernv/opal-rtc.c +++ b/arch/powerpc/platforms/powernv/opal-rtc.c @@ -18,6 +18,7 @@ #include <asm/opal.h> #include <asm/firmware.h> +#include <asm/machdep.h> static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm) { @@ -48,8 +49,11 @@ unsigned long __init opal_get_boot_time(void) else mdelay(10); } - if (rc != OPAL_SUCCESS) + if (rc != OPAL_SUCCESS) { + ppc_md.get_rtc_time = NULL; + ppc_md.set_rtc_time = NULL; return 0; + } y_m_d = be32_to_cpu(__y_m_d); h_m_s_ms = be64_to_cpu(__h_m_s_ms); opal_to_tm(y_m_d, h_m_s_ms, &tm); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index e7806504e976..719aa5c325c6 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -126,3 +126,5 @@ OPAL_CALL(opal_return_cpu, OPAL_RETURN_CPU); OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE); OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE); OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE); +OPAL_CALL(opal_get_msg, OPAL_GET_MSG); +OPAL_CALL(opal_check_completion, OPAL_CHECK_ASYNC_COMPLETION); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 1c798cd55372..7a184a0ff183 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -18,9 +18,11 @@ #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/slab.h> +#include <linux/sched.h> #include <linux/kobject.h> #include <asm/opal.h> #include <asm/firmware.h> +#include <asm/mce.h> #include "powernv.h" @@ -38,6 +40,7 @@ extern u64 opal_mc_secondary_handler[]; static unsigned int *opal_irqs; static unsigned int opal_irq_count; static ATOMIC_NOTIFIER_HEAD(opal_notifier_head); +static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX]; static DEFINE_SPINLOCK(opal_notifier_lock); static uint64_t last_notified_mask = 0x0ul; static atomic_t opal_notifier_hold = ATOMIC_INIT(0); @@ -88,14 +91,10 @@ static int __init opal_register_exception_handlers(void) if (!(powerpc_firmware_features & FW_FEATURE_OPAL)) return -ENODEV; - /* Hookup some exception handlers. We use the fwnmi area at 0x7000 - * to provide the glue space to OPAL + /* Hookup some exception handlers except machine check. We use the + * fwnmi area at 0x7000 to provide the glue space to OPAL */ glue = 0x7000; - opal_register_exception_handler(OPAL_MACHINE_CHECK_HANDLER, - __pa(opal_mc_secondary_handler[0]), - glue); - glue += 128; opal_register_exception_handler(OPAL_HYPERVISOR_MAINTENANCE_HANDLER, 0, glue); glue += 128; @@ -169,6 +168,95 @@ void opal_notifier_disable(void) atomic_set(&opal_notifier_hold, 1); } +/* + * Opal message notifier based on message type. Allow subscribers to get + * notified for specific messgae type. + */ +int opal_message_notifier_register(enum OpalMessageType msg_type, + struct notifier_block *nb) +{ + if (!nb) { + pr_warning("%s: Invalid argument (%p)\n", + __func__, nb); + return -EINVAL; + } + if (msg_type > OPAL_MSG_TYPE_MAX) { + pr_warning("%s: Invalid message type argument (%d)\n", + __func__, msg_type); + return -EINVAL; + } + return atomic_notifier_chain_register( + &opal_msg_notifier_head[msg_type], nb); +} + +static void opal_message_do_notify(uint32_t msg_type, void *msg) +{ + /* notify subscribers */ + atomic_notifier_call_chain(&opal_msg_notifier_head[msg_type], + msg_type, msg); +} + +static void opal_handle_message(void) +{ + s64 ret; + /* + * TODO: pre-allocate a message buffer depending on opal-msg-size + * value in /proc/device-tree. + */ + static struct opal_msg msg; + + ret = opal_get_msg(__pa(&msg), sizeof(msg)); + /* No opal message pending. */ + if (ret == OPAL_RESOURCE) + return; + + /* check for errors. */ + if (ret) { + pr_warning("%s: Failed to retrive opal message, err=%lld\n", + __func__, ret); + return; + } + + /* Sanity check */ + if (msg.msg_type > OPAL_MSG_TYPE_MAX) { + pr_warning("%s: Unknown message type: %u\n", + __func__, msg.msg_type); + return; + } + opal_message_do_notify(msg.msg_type, (void *)&msg); +} + +static int opal_message_notify(struct notifier_block *nb, + unsigned long events, void *change) +{ + if (events & OPAL_EVENT_MSG_PENDING) + opal_handle_message(); + return 0; +} + +static struct notifier_block opal_message_nb = { + .notifier_call = opal_message_notify, + .next = NULL, + .priority = 0, +}; + +static int __init opal_message_init(void) +{ + int ret, i; + + for (i = 0; i < OPAL_MSG_TYPE_MAX; i++) + ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]); + + ret = opal_notifier_register(&opal_message_nb); + if (ret) { + pr_err("%s: Can't register OPAL event notifier (%d)\n", + __func__, ret); + return ret; + } + return 0; +} +early_initcall(opal_message_init); + int opal_get_chars(uint32_t vtermno, char *buf, int count) { s64 rc; @@ -254,119 +342,62 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) return written; } +static int opal_recover_mce(struct pt_regs *regs, + struct machine_check_event *evt) +{ + int recovered = 0; + uint64_t ea = get_mce_fault_addr(evt); + + if (!(regs->msr & MSR_RI)) { + /* If MSR_RI isn't set, we cannot recover */ + recovered = 0; + } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) { + /* Platform corrected itself */ + recovered = 1; + } else if (ea && !is_kernel_addr(ea)) { + /* + * Faulting address is not in kernel text. We should be fine. + * We need to find which process uses this address. + * For now, kill the task if we have received exception when + * in userspace. + * + * TODO: Queue up this address for hwpoisioning later. + */ + if (user_mode(regs) && !is_global_init(current)) { + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; + } else + recovered = 0; + } else if (user_mode(regs) && !is_global_init(current) && + evt->severity == MCE_SEV_ERROR_SYNC) { + /* + * If we have received a synchronous error when in userspace + * kill the task. + */ + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; + } + return recovered; +} + int opal_machine_check(struct pt_regs *regs) { - struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt; - struct opal_machine_check_event evt; - const char *level, *sevstr, *subtype; - static const char *opal_mc_ue_types[] = { - "Indeterminate", - "Instruction fetch", - "Page table walk ifetch", - "Load/Store", - "Page table walk Load/Store", - }; - static const char *opal_mc_slb_types[] = { - "Indeterminate", - "Parity", - "Multihit", - }; - static const char *opal_mc_erat_types[] = { - "Indeterminate", - "Parity", - "Multihit", - }; - static const char *opal_mc_tlb_types[] = { - "Indeterminate", - "Parity", - "Multihit", - }; - - /* Copy the event structure and release the original */ - evt = *opal_evt; - opal_evt->in_use = 0; + struct machine_check_event evt; + + if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) + return 0; /* Print things out */ - if (evt.version != OpalMCE_V1) { + if (evt.version != MCE_V1) { pr_err("Machine Check Exception, Unknown event version %d !\n", evt.version); return 0; } - switch(evt.severity) { - case OpalMCE_SEV_NO_ERROR: - level = KERN_INFO; - sevstr = "Harmless"; - break; - case OpalMCE_SEV_WARNING: - level = KERN_WARNING; - sevstr = ""; - break; - case OpalMCE_SEV_ERROR_SYNC: - level = KERN_ERR; - sevstr = "Severe"; - break; - case OpalMCE_SEV_FATAL: - default: - level = KERN_ERR; - sevstr = "Fatal"; - break; - } + machine_check_print_event_info(&evt); - printk("%s%s Machine check interrupt [%s]\n", level, sevstr, - evt.disposition == OpalMCE_DISPOSITION_RECOVERED ? - "Recovered" : "[Not recovered"); - printk("%s Initiator: %s\n", level, - evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown"); - switch(evt.error_type) { - case OpalMCE_ERROR_TYPE_UE: - subtype = evt.u.ue_error.ue_error_type < - ARRAY_SIZE(opal_mc_ue_types) ? - opal_mc_ue_types[evt.u.ue_error.ue_error_type] - : "Unknown"; - printk("%s Error type: UE [%s]\n", level, subtype); - if (evt.u.ue_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.ue_error.effective_address); - if (evt.u.ue_error.physical_address_provided) - printk("%s Physial address: %016llx\n", - level, evt.u.ue_error.physical_address); - break; - case OpalMCE_ERROR_TYPE_SLB: - subtype = evt.u.slb_error.slb_error_type < - ARRAY_SIZE(opal_mc_slb_types) ? - opal_mc_slb_types[evt.u.slb_error.slb_error_type] - : "Unknown"; - printk("%s Error type: SLB [%s]\n", level, subtype); - if (evt.u.slb_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.slb_error.effective_address); - break; - case OpalMCE_ERROR_TYPE_ERAT: - subtype = evt.u.erat_error.erat_error_type < - ARRAY_SIZE(opal_mc_erat_types) ? - opal_mc_erat_types[evt.u.erat_error.erat_error_type] - : "Unknown"; - printk("%s Error type: ERAT [%s]\n", level, subtype); - if (evt.u.erat_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.erat_error.effective_address); - break; - case OpalMCE_ERROR_TYPE_TLB: - subtype = evt.u.tlb_error.tlb_error_type < - ARRAY_SIZE(opal_mc_tlb_types) ? - opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type] - : "Unknown"; - printk("%s Error type: TLB [%s]\n", level, subtype); - if (evt.u.tlb_error.effective_address_provided) - printk("%s Effective address: %016llx\n", - level, evt.u.tlb_error.effective_address); - break; - default: - case OpalMCE_ERROR_TYPE_UNKNOWN: - printk("%s Error type: Unknown\n", level); - break; - } - return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1; + if (opal_recover_mce(regs, &evt)) + return 1; + return 0; } static irqreturn_t opal_interrupt(int irq, void *data) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 2c6d173842b2..f0e68714696e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -460,7 +460,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev return; pe = &phb->ioda.pe_array[pdn->pe_number]; - set_iommu_table_base(&pdev->dev, &pe->tce32_table); + set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); } static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) @@ -468,7 +468,7 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) struct pci_dev *dev; list_for_each_entry(dev, &bus->devices, bus_list) { - set_iommu_table_base(&dev->dev, &pe->tce32_table); + set_iommu_table_base_and_group(&dev->dev, &pe->tce32_table); if (dev->subordinate) pnv_ioda_setup_bus_dma(pe, dev->subordinate); } @@ -644,7 +644,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number); if (pe->pdev) - set_iommu_table_base(&pe->pdev->dev, tbl); + set_iommu_table_base_and_group(&pe->pdev->dev, tbl); else pnv_ioda_setup_bus_dma(pe, pe->pbus); @@ -723,7 +723,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number); if (pe->pdev) - set_iommu_table_base(&pe->pdev->dev, tbl); + set_iommu_table_base_and_group(&pe->pdev->dev, tbl); else pnv_ioda_setup_bus_dma(pe, pe->pbus); diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index f8b4bd8afb2e..e3807d69393e 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -92,7 +92,7 @@ static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb, pci_domain_nr(phb->hose->bus), phb->opal_id); } - set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table); + set_iommu_table_base_and_group(&pdev->dev, &phb->p5ioc2.iommu_table); } static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 4eb33a9ed532..b555ebc57ef5 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -124,77 +124,157 @@ static void pnv_teardown_msi_irqs(struct pci_dev *pdev) } #endif /* CONFIG_PCI_MSI */ -static void pnv_pci_dump_p7ioc_diag_data(struct pnv_phb *phb) +static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose, + struct OpalIoPhbErrorCommon *common) { - struct OpalIoP7IOCPhbErrorData *data = &phb->diag.p7ioc; + struct OpalIoP7IOCPhbErrorData *data; int i; - pr_info("PHB %d diagnostic data:\n", phb->hose->global_number); - - pr_info(" brdgCtl = 0x%08x\n", data->brdgCtl); - - pr_info(" portStatusReg = 0x%08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus = 0x%08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus = 0x%08x\n", data->busAgentStatus); - - pr_info(" deviceStatus = 0x%08x\n", data->deviceStatus); - pr_info(" slotStatus = 0x%08x\n", data->slotStatus); - pr_info(" linkStatus = 0x%08x\n", data->linkStatus); - pr_info(" devCmdStatus = 0x%08x\n", data->devCmdStatus); - pr_info(" devSecStatus = 0x%08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus = 0x%08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus = 0x%08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus = 0x%08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1 = 0x%08x\n", data->tlpHdr1); - pr_info(" tlpHdr2 = 0x%08x\n", data->tlpHdr2); - pr_info(" tlpHdr3 = 0x%08x\n", data->tlpHdr3); - pr_info(" tlpHdr4 = 0x%08x\n", data->tlpHdr4); - pr_info(" sourceId = 0x%08x\n", data->sourceId); - - pr_info(" errorClass = 0x%016llx\n", data->errorClass); - pr_info(" correlator = 0x%016llx\n", data->correlator); - - pr_info(" p7iocPlssr = 0x%016llx\n", data->p7iocPlssr); - pr_info(" p7iocCsr = 0x%016llx\n", data->p7iocCsr); - pr_info(" lemFir = 0x%016llx\n", data->lemFir); - pr_info(" lemErrorMask = 0x%016llx\n", data->lemErrorMask); - pr_info(" lemWOF = 0x%016llx\n", data->lemWOF); - pr_info(" phbErrorStatus = 0x%016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus = 0x%016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0 = 0x%016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1 = 0x%016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus = 0x%016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus = 0x%016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0 = 0x%016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1 = 0x%016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus = 0x%016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus = 0x%016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0 = 0x%016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1 = 0x%016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus = 0x%016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus = 0x%016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0 = 0x%016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1 = 0x%016llx\n", data->dma1ErrorLog1); + data = (struct OpalIoP7IOCPhbErrorData *)common; + pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n", + hose->global_number, common->version); + + pr_info(" brdgCtl: %08x\n", data->brdgCtl); + + pr_info(" portStatusReg: %08x\n", data->portStatusReg); + pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); + pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); + + pr_info(" deviceStatus: %08x\n", data->deviceStatus); + pr_info(" slotStatus: %08x\n", data->slotStatus); + pr_info(" linkStatus: %08x\n", data->linkStatus); + pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); + pr_info(" devSecStatus: %08x\n", data->devSecStatus); + + pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); + pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); + pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); + pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); + pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); + pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); + pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); + pr_info(" sourceId: %08x\n", data->sourceId); + pr_info(" errorClass: %016llx\n", data->errorClass); + pr_info(" correlator: %016llx\n", data->correlator); + pr_info(" p7iocPlssr: %016llx\n", data->p7iocPlssr); + pr_info(" p7iocCsr: %016llx\n", data->p7iocCsr); + pr_info(" lemFir: %016llx\n", data->lemFir); + pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); + pr_info(" lemWOF: %016llx\n", data->lemWOF); + pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); + pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); + pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); + pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); + pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); + pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); + pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); + pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); + pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); + pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); + pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); + pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); + pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); + pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); + pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); + pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) { if ((data->pestA[i] >> 63) == 0 && (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] PESTA = 0x%016llx\n", i, data->pestA[i]); - pr_info(" PESTB = 0x%016llx\n", data->pestB[i]); + + pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); + pr_info(" PESTB: %016llx\n", data->pestB[i]); + } +} + +static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose, + struct OpalIoPhbErrorCommon *common) +{ + struct OpalIoPhb3ErrorData *data; + int i; + + data = (struct OpalIoPhb3ErrorData*)common; + pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n", + hose->global_number, common->version); + + pr_info(" brdgCtl: %08x\n", data->brdgCtl); + + pr_info(" portStatusReg: %08x\n", data->portStatusReg); + pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); + pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); + + pr_info(" deviceStatus: %08x\n", data->deviceStatus); + pr_info(" slotStatus: %08x\n", data->slotStatus); + pr_info(" linkStatus: %08x\n", data->linkStatus); + pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); + pr_info(" devSecStatus: %08x\n", data->devSecStatus); + + pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); + pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); + pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); + pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); + pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); + pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); + pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); + pr_info(" sourceId: %08x\n", data->sourceId); + pr_info(" errorClass: %016llx\n", data->errorClass); + pr_info(" correlator: %016llx\n", data->correlator); + + pr_info(" nFir: %016llx\n", data->nFir); + pr_info(" nFirMask: %016llx\n", data->nFirMask); + pr_info(" nFirWOF: %016llx\n", data->nFirWOF); + pr_info(" PhbPlssr: %016llx\n", data->phbPlssr); + pr_info(" PhbCsr: %016llx\n", data->phbCsr); + pr_info(" lemFir: %016llx\n", data->lemFir); + pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); + pr_info(" lemWOF: %016llx\n", data->lemWOF); + pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); + pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); + pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); + pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); + pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); + pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); + pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); + pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); + pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); + pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); + pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); + pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); + pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); + pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); + pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); + pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); + + for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) { + if ((data->pestA[i] >> 63) == 0 && + (data->pestB[i] >> 63) == 0) + continue; + + pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); + pr_info(" PESTB: %016llx\n", data->pestB[i]); } } -static void pnv_pci_dump_phb_diag_data(struct pnv_phb *phb) +void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, + unsigned char *log_buff) { - switch(phb->model) { - case PNV_PHB_MODEL_P7IOC: - pnv_pci_dump_p7ioc_diag_data(phb); + struct OpalIoPhbErrorCommon *common; + + if (!hose || !log_buff) + return; + + common = (struct OpalIoPhbErrorCommon *)log_buff; + switch (common->ioType) { + case OPAL_PHB_ERROR_DATA_TYPE_P7IOC: + pnv_pci_dump_p7ioc_diag_data(hose, common); + break; + case OPAL_PHB_ERROR_DATA_TYPE_PHB3: + pnv_pci_dump_phb3_diag_data(hose, common); break; default: - pr_warning("PCI %d: Can't decode this PHB diag data\n", - phb->hose->global_number); + pr_warn("%s: Unrecognized ioType %d\n", + __func__, common->ioType); } } @@ -222,7 +302,7 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no) * with the normal errors generated when probing empty slots */ if (has_diag) - pnv_pci_dump_phb_diag_data(phb); + pnv_pci_dump_phb_diag_data(phb->hose, phb->diag.blob); else pr_warning("PCI %d: No diag data available\n", phb->hose->global_number); @@ -484,7 +564,8 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl, { tbl->it_blocksize = 16; tbl->it_base = (unsigned long)tce_mem; - tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; + tbl->it_offset = dma_offset >> tbl->it_page_shift; tbl->it_index = 0; tbl->it_size = tce_size >> 3; tbl->it_busno = 0; @@ -536,7 +617,7 @@ static void pnv_pci_dma_fallback_setup(struct pci_controller *hose, pdn->iommu_table = pnv_pci_setup_bml_iommu(hose); if (!pdn->iommu_table) return; - set_iommu_table_base(&pdev->dev, pdn->iommu_table); + set_iommu_table_base_and_group(&pdev->dev, pdn->iommu_table); } static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) @@ -657,3 +738,32 @@ void __init pnv_pci_init(void) ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs; #endif } + +static int tce_iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + return iommu_add_device(dev); + case BUS_NOTIFY_DEL_DEVICE: + if (dev->iommu_group) + iommu_del_device(dev); + return 0; + default: + return 0; + } +} + +static struct notifier_block tce_iommu_bus_nb = { + .notifier_call = tce_iommu_bus_notifier, +}; + +static int __init tce_iommu_bus_notifier_init(void) +{ + bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); + return 0; +} + +subsys_initcall_sync(tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 1ed8d5f40f5a..13f1942a9a5f 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -176,6 +176,7 @@ struct pnv_phb { union { unsigned char blob[PNV_PCI_DIAG_BUF_SIZE]; struct OpalIoP7IOCPhbErrorData p7ioc; + struct OpalIoPhb3ErrorData phb3; struct OpalIoP7IOCErrorData hub_diag; } diag; @@ -186,6 +187,8 @@ extern struct pci_ops pnv_pci_ops; extern struct pnv_eeh_ops ioda_eeh_ops; #endif +void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, + unsigned char *log_buff); int pnv_pci_cfg_read(struct device_node *dn, int where, int size, u32 *val); int pnv_pci_cfg_write(struct device_node *dn, diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index e17fa1432d80..a0bca05e26b0 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -143,7 +143,7 @@ static void _dump_areas(unsigned int spe_id, unsigned long priv2, pr_debug("%s:%d: shadow: %lxh\n", func, line, shadow); } -inline u64 ps3_get_spe_id(void *arg) +u64 ps3_get_spe_id(void *arg) { return spu_pdata(arg)->spe_id; } diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 62b4f8025de0..e66643250fee 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -34,7 +34,7 @@ config PPC_SPLPAR config PSERIES_MSI bool - depends on PCI_MSI && EEH + depends on PCI_MSI && PPC_PSERIES && EEH default y config PSERIES_ENERGY diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index f253361552ae..e0299183ae54 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -486,9 +486,10 @@ static void iommu_table_setparms(struct pci_controller *phb, memset((void *)tbl->it_base, 0, *sizep); tbl->it_busno = phb->bus->number; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; /* Units of tce entries */ - tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT; + tbl->it_offset = phb->dma_window_base_cur >> tbl->it_page_shift; /* Test if we are going over 2GB of DMA space */ if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) { @@ -499,7 +500,7 @@ static void iommu_table_setparms(struct pci_controller *phb, phb->dma_window_base_cur += phb->dma_window_size; /* Set the tce table size - measured in entries */ - tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT; + tbl->it_size = phb->dma_window_size >> tbl->it_page_shift; tbl->it_index = 0; tbl->it_blocksize = 16; @@ -537,11 +538,12 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb, of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size); tbl->it_busno = phb->bus->number; + tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; tbl->it_base = 0; tbl->it_blocksize = 16; tbl->it_type = TCE_PCI; - tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; - tbl->it_size = size >> IOMMU_PAGE_SHIFT; + tbl->it_offset = offset >> tbl->it_page_shift; + tbl->it_size = size >> tbl->it_page_shift; } static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) @@ -687,7 +689,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) iommu_table_setparms(phb, dn, tbl); PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node); iommu_register_group(tbl, pci_domain_nr(phb->bus), 0); - set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table); + set_iommu_table_base_and_group(&dev->dev, + PCI_DN(dn)->iommu_table); return; } @@ -699,7 +702,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) dn = dn->parent; if (dn && PCI_DN(dn)) - set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table); + set_iommu_table_base_and_group(&dev->dev, + PCI_DN(dn)->iommu_table); else printk(KERN_WARNING "iommu: Device %s has no iommu table\n", pci_name(dev)); @@ -1193,7 +1197,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) pr_debug(" found DMA window, table: %p\n", pci->iommu_table); } - set_iommu_table_base(&dev->dev, pci->iommu_table); + set_iommu_table_base_and_group(&dev->dev, pci->iommu_table); } static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 4fca3def9db9..b02af9ef3ff6 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -92,7 +92,7 @@ void vpa_init(int cpu) * PAPR says this feature is SLB-Buffer but firmware never * reports that. All SPLPAR support SLB shadow buffer. */ - addr = __pa(&slb_shadow[cpu]); + addr = __pa(paca[cpu].slb_shadow_ptr); if (firmware_has_feature(FW_FEATURE_SPLPAR)) { ret = register_slb_shadow(hwcpu, addr); if (ret) @@ -153,7 +153,8 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group, /* Make pHyp happy */ if ((rflags & _PAGE_NO_CACHE) && !(rflags & _PAGE_WRITETHRU)) - hpte_r &= ~_PAGE_COHERENT; + hpte_r &= ~HPTE_R_M; + if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N)) flags |= H_COALESCE_CAND; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index c1f190858701..49cd16e6b450 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -72,7 +72,7 @@ int CMO_PrPSP = -1; int CMO_SecPSP = -1; -unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT); +unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K); EXPORT_SYMBOL(CMO_PageSize); int fwnmi_active; /* TRUE if an FWNMI handler is present */ @@ -569,7 +569,7 @@ void pSeries_cmo_feature_init(void) { char *ptr, *key, *value, *end; int call_status; - int page_order = IOMMU_PAGE_SHIFT; + int page_order = IOMMU_PAGE_SHIFT_4K; pr_debug(" -> fw_cmo_feature_init()\n"); spin_lock(&rtas_data_buf_lock); diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c index 62cb527493e7..9a15e5b39bb8 100644 --- a/arch/powerpc/platforms/wsp/wsp_pci.c +++ b/arch/powerpc/platforms/wsp/wsp_pci.c @@ -260,7 +260,7 @@ static int tce_build_wsp(struct iommu_table *tbl, long index, long npages, *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; dma_debug("[DMA] TCE %p set to 0x%016llx (dma addr: 0x%lx)\n", - tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT); + tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT_4K); uaddr += TCE_PAGE_SIZE; index++; @@ -381,8 +381,9 @@ static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb, /* Init bits and pieces */ tbl->table.it_blocksize = 16; - tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT; - tbl->table.it_size = size >> IOMMU_PAGE_SHIFT; + tbl->table.it_page_shift = IOMMU_PAGE_SHIFT_4K; + tbl->table.it_offset = addr >> tbl->table.it_page_shift; + tbl->table.it_size = size >> tbl->table.it_page_shift; /* * It's already blank but we clear it anyway. @@ -449,8 +450,8 @@ static void wsp_pci_dma_dev_setup(struct pci_dev *pdev) if (table) { pr_info("%s: Setup iommu: 32-bit DMA region 0x%08lx..0x%08lx\n", pci_name(pdev), - table->table.it_offset << IOMMU_PAGE_SHIFT, - (table->table.it_offset << IOMMU_PAGE_SHIFT) + table->table.it_offset << IOMMU_PAGE_SHIFT_4K, + (table->table.it_offset << IOMMU_PAGE_SHIFT_4K) + phb->dma32_region_size - 1); archdata->dma_data.iommu_table_base = &table->table; return; diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig index 13ec968be4c7..7baa70d6dc01 100644 --- a/arch/powerpc/sysdev/Kconfig +++ b/arch/powerpc/sysdev/Kconfig @@ -19,7 +19,7 @@ config PPC_MSI_BITMAP default y if MPIC default y if FSL_PCI default y if PPC4xx_MSI - default y if POWERNV_MSI + default y if PPC_POWERNV source "arch/powerpc/sysdev/xics/Kconfig" diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 4dfd61df8aba..7066e5262468 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -122,7 +122,7 @@ static int fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask) * address width of the SoC such that we can address any internal * SoC address from across PCI if needed */ - if ((dev->bus == &pci_bus_type) && + if ((dev_is_pci(dev)) && dma_mask >= DMA_BIT_MASK(MAX_PHYS_ADDR_BITS)) { set_dma_ops(dev, &dma_direct_ops); set_dma_offset(dev, pci64_dma_offset); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index af9d3469fb99..a90731b3d44a 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2051,6 +2051,10 @@ static void dump_one_paca(int cpu) DUMP(p, stab_addr, "lx"); #endif DUMP(p, emergency_sp, "p"); +#ifdef CONFIG_PPC_BOOK3S_64 + DUMP(p, mc_emergency_sp, "p"); + DUMP(p, in_mce, "x"); +#endif DUMP(p, data_offset, "lx"); DUMP(p, hw_cpu_id, "x"); DUMP(p, cpu_start, "x"); diff --git a/drivers/macintosh/windfarm_lm75_sensor.c b/drivers/macintosh/windfarm_lm75_sensor.c index 9ef32b3df91f..590214ba736c 100644 --- a/drivers/macintosh/windfarm_lm75_sensor.c +++ b/drivers/macintosh/windfarm_lm75_sensor.c @@ -133,7 +133,7 @@ static int wf_lm75_probe(struct i2c_client *client, lm->inited = 0; lm->ds1775 = ds1775; lm->i2c = client; - lm->sens.name = (char *)name; /* XXX fix constness in structure */ + lm->sens.name = name; lm->sens.ops = &wf_lm75_ops; i2c_set_clientdata(client, lm); diff --git a/drivers/macintosh/windfarm_max6690_sensor.c b/drivers/macintosh/windfarm_max6690_sensor.c index 945a25b2f31e..87e439b10318 100644 --- a/drivers/macintosh/windfarm_max6690_sensor.c +++ b/drivers/macintosh/windfarm_max6690_sensor.c @@ -95,7 +95,7 @@ static int wf_max6690_probe(struct i2c_client *client, } max->i2c = client; - max->sens.name = (char *)name; /* XXX fix constness in structure */ + max->sens.name = name; max->sens.ops = &wf_max6690_ops; i2c_set_clientdata(client, max); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 952d795230a4..d04dbaba83dd 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1276,18 +1276,21 @@ static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev) { struct net_device *netdev = dev_get_drvdata(&vdev->dev); struct ibmveth_adapter *adapter; + struct iommu_table *tbl; unsigned long ret; int i; int rxqentries = 1; + tbl = get_iommu_table_base(&vdev->dev); + /* netdev inits at probe time along with the structures we need below*/ if (netdev == NULL) - return IOMMU_PAGE_ALIGN(IBMVETH_IO_ENTITLEMENT_DEFAULT); + return IOMMU_PAGE_ALIGN(IBMVETH_IO_ENTITLEMENT_DEFAULT, tbl); adapter = netdev_priv(netdev); ret = IBMVETH_BUFF_LIST_SIZE + IBMVETH_FILT_LIST_SIZE; - ret += IOMMU_PAGE_ALIGN(netdev->mtu); + ret += IOMMU_PAGE_ALIGN(netdev->mtu, tbl); for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { /* add the size of the active receive buffers */ @@ -1295,11 +1298,12 @@ static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev) ret += adapter->rx_buff_pool[i].size * IOMMU_PAGE_ALIGN(adapter->rx_buff_pool[i]. - buff_size); + buff_size, tbl); rxqentries += adapter->rx_buff_pool[i].size; } /* add the size of the receive queue entries */ - ret += IOMMU_PAGE_ALIGN(rxqentries * sizeof(struct ibmveth_rx_q_entry)); + ret += IOMMU_PAGE_ALIGN( + rxqentries * sizeof(struct ibmveth_rx_q_entry), tbl); return ret; } diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index bdae7a04af75..a84788ba662c 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -81,7 +81,7 @@ static int tce_iommu_enable(struct tce_container *container) * enforcing the limit based on the max that the guest can map. */ down_write(¤t->mm->mmap_sem); - npages = (tbl->it_size << IOMMU_PAGE_SHIFT) >> PAGE_SHIFT; + npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT; locked = current->mm->locked_vm + npages; lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { @@ -110,7 +110,7 @@ static void tce_iommu_disable(struct tce_container *container) down_write(¤t->mm->mmap_sem); current->mm->locked_vm -= (container->tbl->it_size << - IOMMU_PAGE_SHIFT) >> PAGE_SHIFT; + IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT; up_write(¤t->mm->mmap_sem); } @@ -174,8 +174,8 @@ static long tce_iommu_ioctl(void *iommu_data, if (info.argsz < minsz) return -EINVAL; - info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT; - info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT; + info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT_4K; + info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT_4K; info.flags = 0; if (copy_to_user((void __user *)arg, &info, minsz)) @@ -205,8 +205,8 @@ static long tce_iommu_ioctl(void *iommu_data, VFIO_DMA_MAP_FLAG_WRITE)) return -EINVAL; - if ((param.size & ~IOMMU_PAGE_MASK) || - (param.vaddr & ~IOMMU_PAGE_MASK)) + if ((param.size & ~IOMMU_PAGE_MASK_4K) || + (param.vaddr & ~IOMMU_PAGE_MASK_4K)) return -EINVAL; /* iova is checked by the IOMMU API */ @@ -220,17 +220,17 @@ static long tce_iommu_ioctl(void *iommu_data, if (ret) return ret; - for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT); ++i) { + for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT_4K); ++i) { ret = iommu_put_tce_user_mode(tbl, - (param.iova >> IOMMU_PAGE_SHIFT) + i, + (param.iova >> IOMMU_PAGE_SHIFT_4K) + i, tce); if (ret) break; - tce += IOMMU_PAGE_SIZE; + tce += IOMMU_PAGE_SIZE_4K; } if (ret) iommu_clear_tces_and_put_pages(tbl, - param.iova >> IOMMU_PAGE_SHIFT, i); + param.iova >> IOMMU_PAGE_SHIFT_4K, i); iommu_flush_tce(tbl); @@ -256,17 +256,17 @@ static long tce_iommu_ioctl(void *iommu_data, if (param.flags) return -EINVAL; - if (param.size & ~IOMMU_PAGE_MASK) + if (param.size & ~IOMMU_PAGE_MASK_4K) return -EINVAL; ret = iommu_tce_clear_param_check(tbl, param.iova, 0, - param.size >> IOMMU_PAGE_SHIFT); + param.size >> IOMMU_PAGE_SHIFT_4K); if (ret) return ret; ret = iommu_clear_tces_and_put_pages(tbl, - param.iova >> IOMMU_PAGE_SHIFT, - param.size >> IOMMU_PAGE_SHIFT); + param.iova >> IOMMU_PAGE_SHIFT_4K, + param.size >> IOMMU_PAGE_SHIFT_4K); iommu_flush_tce(tbl); return ret; diff --git a/include/linux/mm.h b/include/linux/mm.h index 1cedd000cf29..a7b4e310bf42 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1842,7 +1842,7 @@ static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) } #endif -#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE +#ifdef CONFIG_NUMA_BALANCING unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long start, unsigned long end); #endif diff --git a/mm/mempolicy.c b/mm/mempolicy.c index eca4a3129129..9f73b29d304d 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -613,7 +613,7 @@ static inline int queue_pages_pgd_range(struct vm_area_struct *vma, return 0; } -#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE +#ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these @@ -627,7 +627,6 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { int nr_updated; - BUILD_BUG_ON(_PAGE_NUMA != _PAGE_PROTNONE); nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1); if (nr_updated) @@ -641,7 +640,7 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, { return 0; } -#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ +#endif /* CONFIG_NUMA_BALANCING */ /* * Walk through page tables and collect pages to be migrated. |