diff options
Diffstat (limited to 'arch/powerpc')
66 files changed, 1285 insertions, 382 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 38f3b7e47ec5..875d815a8e7f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -97,7 +97,7 @@ config PPC select VIRT_TO_BUS if !PPC64 select HAVE_IDE select HAVE_IOREMAP_PROT - select HAVE_EFFICIENT_UNALIGNED_ACCESS + select HAVE_EFFICIENT_UNALIGNED_ACCESS if !CPU_LITTLE_ENDIAN select HAVE_KPROBES select HAVE_ARCH_KGDB select HAVE_KRETPROBES @@ -139,6 +139,9 @@ config PPC select OLD_SIGACTION if PPC32 select HAVE_DEBUG_STACKOVERFLOW +config GENERIC_CSUM + def_bool CPU_LITTLE_ENDIAN + config EARLY_PRINTK bool default y @@ -1009,6 +1012,9 @@ config PHYSICAL_START default "0x00000000" endif +config ARCH_RANDOM + def_bool n + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 51cfb78d4061..607acf54a425 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -36,17 +36,26 @@ KBUILD_DEFCONFIG := ppc64_defconfig endif ifeq ($(CONFIG_PPC64),y) -OLDARCH := ppc64 - new_nm := $(shell if $(NM) --help 2>&1 | grep -- '--synthetic' > /dev/null; then echo y; else echo n; fi) ifeq ($(new_nm),y) NM := $(NM) --synthetic endif +endif +ifeq ($(CONFIG_PPC64),y) +ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) +OLDARCH := ppc64le +else +OLDARCH := ppc64 +endif +else +ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) +OLDARCH := ppcle else OLDARCH := ppc endif +endif # It seems there are times we use this Makefile without # including the config file, but this replicates the old behaviour @@ -56,11 +65,29 @@ endif UTS_MACHINE := $(OLDARCH) +ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) +override CC += -mlittle-endian -mno-strict-align +override AS += -mlittle-endian +override LD += -EL +override CROSS32CC += -mlittle-endian +override CROSS32AS += -mlittle-endian +LDEMULATION := lppc +GNUTARGET := powerpcle +MULTIPLEWORD := -mno-multiple +else +override CC += -mbig-endian +override AS += -mbig-endian +override LD += -EB +LDEMULATION := ppc +GNUTARGET := powerpc +MULTIPLEWORD := -mmultiple +endif + ifeq ($(HAS_BIARCH),y) override AS += -a$(CONFIG_WORD_SIZE) -override LD += -m elf$(CONFIG_WORD_SIZE)ppc +override LD += -m elf$(CONFIG_WORD_SIZE)$(LDEMULATION) override CC += -m$(CONFIG_WORD_SIZE) -override AR := GNUTARGET=elf$(CONFIG_WORD_SIZE)-powerpc $(AR) +override AR := GNUTARGET=elf$(CONFIG_WORD_SIZE)-$(GNUTARGET) $(AR) endif LDFLAGS_vmlinux-y := -Bstatic @@ -86,7 +113,7 @@ endif CFLAGS-$(CONFIG_PPC64) := -mtraceback=no -mcall-aixdesc CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,-mminimal-toc) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) -CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 -mmultiple +CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 $(MULTIPLEWORD) ifeq ($(CONFIG_PPC_BOOK3S_64),y) CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power7,-mtune=power4) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 15ca2255f438..ca7f08cc4afd 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -22,7 +22,8 @@ all: $(obj)/zImage BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -Os -msoft-float -pipe \ -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ - -isystem $(shell $(CROSS32CC) -print-file-name=include) + -isystem $(shell $(CROSS32CC) -print-file-name=include) \ + -mbig-endian BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc ifdef CONFIG_DEBUG_INFO diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h new file mode 100644 index 000000000000..d853d163ba47 --- /dev/null +++ b/arch/powerpc/include/asm/archrandom.h @@ -0,0 +1,32 @@ +#ifndef _ASM_POWERPC_ARCHRANDOM_H +#define _ASM_POWERPC_ARCHRANDOM_H + +#ifdef CONFIG_ARCH_RANDOM + +#include <asm/machdep.h> + +static inline int arch_get_random_long(unsigned long *v) +{ + if (ppc_md.get_random_long) + return ppc_md.get_random_long(v); + + return 0; +} + +static inline int arch_get_random_int(unsigned int *v) +{ + unsigned long val; + int rc; + + rc = arch_get_random_long(&val); + if (rc) + *v = val; + + return rc; +} + +int powernv_get_random_long(unsigned long *v); + +#endif /* CONFIG_ARCH_RANDOM */ + +#endif /* _ASM_POWERPC_ARCHRANDOM_H */ diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index ce0c28495f9a..8251a3ba870f 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -14,6 +14,9 @@ * which always checksum on 4 octet boundaries. ihl is the number * of 32-bit words and is always >= 5. */ +#ifdef CONFIG_GENERIC_CSUM +#include <asm-generic/checksum.h> +#else extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl); /* @@ -123,5 +126,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, return sum; #endif } + +#endif #endif /* __KERNEL__ */ #endif diff --git a/arch/powerpc/include/asm/hvsi.h b/arch/powerpc/include/asm/hvsi.h index d3f64f361814..d4a5315718ca 100644 --- a/arch/powerpc/include/asm/hvsi.h +++ b/arch/powerpc/include/asm/hvsi.h @@ -25,7 +25,7 @@ struct hvsi_header { uint8_t type; uint8_t len; - uint16_t seqno; + __be16 seqno; } __attribute__((packed)); struct hvsi_data { @@ -35,24 +35,24 @@ struct hvsi_data { struct hvsi_control { struct hvsi_header hdr; - uint16_t verb; + __be16 verb; /* optional depending on verb: */ - uint32_t word; - uint32_t mask; + __be32 word; + __be32 mask; } __attribute__((packed)); struct hvsi_query { struct hvsi_header hdr; - uint16_t verb; + __be16 verb; } __attribute__((packed)); struct hvsi_query_response { struct hvsi_header hdr; - uint16_t verb; - uint16_t query_seqno; + __be16 verb; + __be16 query_seqno; union { uint8_t version; - uint32_t mctrl_word; + __be32 mctrl_word; } u; } __attribute__((packed)); diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 5a64757dc0d1..575fbf81fad0 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -21,7 +21,7 @@ extern struct pci_dev *isa_bridge_pcidev; /* * has legacy ISA devices ? */ -#define arch_has_dev_port() (isa_bridge_pcidev != NULL) +#define arch_has_dev_port() (isa_bridge_pcidev != NULL || isa_io_special) #endif #include <linux/device.h> @@ -113,7 +113,7 @@ extern bool isa_io_special; /* gcc 4.0 and older doesn't have 'Z' constraint */ #if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ == 0) -#define DEF_MMIO_IN_LE(name, size, insn) \ +#define DEF_MMIO_IN_X(name, size, insn) \ static inline u##size name(const volatile u##size __iomem *addr) \ { \ u##size ret; \ @@ -122,7 +122,7 @@ static inline u##size name(const volatile u##size __iomem *addr) \ return ret; \ } -#define DEF_MMIO_OUT_LE(name, size, insn) \ +#define DEF_MMIO_OUT_X(name, size, insn) \ static inline void name(volatile u##size __iomem *addr, u##size val) \ { \ __asm__ __volatile__("sync;"#insn" %1,0,%2" \ @@ -130,7 +130,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val) \ IO_SET_SYNC_FLAG(); \ } #else /* newer gcc */ -#define DEF_MMIO_IN_LE(name, size, insn) \ +#define DEF_MMIO_IN_X(name, size, insn) \ static inline u##size name(const volatile u##size __iomem *addr) \ { \ u##size ret; \ @@ -139,7 +139,7 @@ static inline u##size name(const volatile u##size __iomem *addr) \ return ret; \ } -#define DEF_MMIO_OUT_LE(name, size, insn) \ +#define DEF_MMIO_OUT_X(name, size, insn) \ static inline void name(volatile u##size __iomem *addr, u##size val) \ { \ __asm__ __volatile__("sync;"#insn" %1,%y0" \ @@ -148,7 +148,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val) \ } #endif -#define DEF_MMIO_IN_BE(name, size, insn) \ +#define DEF_MMIO_IN_D(name, size, insn) \ static inline u##size name(const volatile u##size __iomem *addr) \ { \ u##size ret; \ @@ -157,7 +157,7 @@ static inline u##size name(const volatile u##size __iomem *addr) \ return ret; \ } -#define DEF_MMIO_OUT_BE(name, size, insn) \ +#define DEF_MMIO_OUT_D(name, size, insn) \ static inline void name(volatile u##size __iomem *addr, u##size val) \ { \ __asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0" \ @@ -165,22 +165,37 @@ static inline void name(volatile u##size __iomem *addr, u##size val) \ IO_SET_SYNC_FLAG(); \ } +DEF_MMIO_IN_D(in_8, 8, lbz); +DEF_MMIO_OUT_D(out_8, 8, stb); -DEF_MMIO_IN_BE(in_8, 8, lbz); -DEF_MMIO_IN_BE(in_be16, 16, lhz); -DEF_MMIO_IN_BE(in_be32, 32, lwz); -DEF_MMIO_IN_LE(in_le16, 16, lhbrx); -DEF_MMIO_IN_LE(in_le32, 32, lwbrx); +#ifdef __BIG_ENDIAN__ +DEF_MMIO_IN_D(in_be16, 16, lhz); +DEF_MMIO_IN_D(in_be32, 32, lwz); +DEF_MMIO_IN_X(in_le16, 16, lhbrx); +DEF_MMIO_IN_X(in_le32, 32, lwbrx); -DEF_MMIO_OUT_BE(out_8, 8, stb); -DEF_MMIO_OUT_BE(out_be16, 16, sth); -DEF_MMIO_OUT_BE(out_be32, 32, stw); -DEF_MMIO_OUT_LE(out_le16, 16, sthbrx); -DEF_MMIO_OUT_LE(out_le32, 32, stwbrx); +DEF_MMIO_OUT_D(out_be16, 16, sth); +DEF_MMIO_OUT_D(out_be32, 32, stw); +DEF_MMIO_OUT_X(out_le16, 16, sthbrx); +DEF_MMIO_OUT_X(out_le32, 32, stwbrx); +#else +DEF_MMIO_IN_X(in_be16, 16, lhbrx); +DEF_MMIO_IN_X(in_be32, 32, lwbrx); +DEF_MMIO_IN_D(in_le16, 16, lhz); +DEF_MMIO_IN_D(in_le32, 32, lwz); + +DEF_MMIO_OUT_X(out_be16, 16, sthbrx); +DEF_MMIO_OUT_X(out_be32, 32, stwbrx); +DEF_MMIO_OUT_D(out_le16, 16, sth); +DEF_MMIO_OUT_D(out_le32, 32, stw); + +#endif /* __BIG_ENDIAN */ #ifdef __powerpc64__ -DEF_MMIO_OUT_BE(out_be64, 64, std); -DEF_MMIO_IN_BE(in_be64, 64, ld); + +#ifdef __BIG_ENDIAN__ +DEF_MMIO_OUT_D(out_be64, 64, std); +DEF_MMIO_IN_D(in_be64, 64, ld); /* There is no asm instructions for 64 bits reverse loads and stores */ static inline u64 in_le64(const volatile u64 __iomem *addr) @@ -192,6 +207,22 @@ static inline void out_le64(volatile u64 __iomem *addr, u64 val) { out_be64(addr, swab64(val)); } +#else +DEF_MMIO_OUT_D(out_le64, 64, std); +DEF_MMIO_IN_D(in_le64, 64, ld); + +/* There is no asm instructions for 64 bits reverse loads and stores */ +static inline u64 in_be64(const volatile u64 __iomem *addr) +{ + return swab64(in_le64(addr)); +} + +static inline void out_be64(volatile u64 __iomem *addr, u64 val) +{ + out_le64(addr, swab64(val)); +} + +#endif #endif /* __powerpc64__ */ /* diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 07dd3b1312e5..ad3025d0880b 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -275,6 +275,10 @@ struct machdep_calls { ssize_t (*cpu_probe)(const char *, size_t); ssize_t (*cpu_release)(const char *, size_t); #endif + +#ifdef CONFIG_ARCH_RANDOM + int (*get_random_long)(unsigned long *v); +#endif }; extern void e500_idle(void); diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index c4cf01197273..807014dde821 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -135,8 +135,8 @@ extern char initial_stab[]; #ifndef __ASSEMBLY__ struct hash_pte { - unsigned long v; - unsigned long r; + __be64 v; + __be64 r; }; extern struct hash_pte *htab_address; diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index c5cd72833d6e..4cc33ba1edd3 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -460,10 +460,12 @@ enum { enum { OPAL_PHB_ERROR_DATA_TYPE_P7IOC = 1, + OPAL_PHB_ERROR_DATA_TYPE_PHB3 = 2 }; enum { OPAL_P7IOC_NUM_PEST_REGS = 128, + OPAL_PHB3_NUM_PEST_REGS = 256 }; struct OpalIoPhbErrorCommon { @@ -531,28 +533,91 @@ struct OpalIoP7IOCPhbErrorData { uint64_t pestB[OPAL_P7IOC_NUM_PEST_REGS]; }; +struct OpalIoPhb3ErrorData { + struct OpalIoPhbErrorCommon common; + + uint32_t brdgCtl; + + /* PHB3 UTL regs */ + uint32_t portStatusReg; + uint32_t rootCmplxStatus; + uint32_t busAgentStatus; + + /* PHB3 cfg regs */ + uint32_t deviceStatus; + uint32_t slotStatus; + uint32_t linkStatus; + uint32_t devCmdStatus; + uint32_t devSecStatus; + + /* cfg AER regs */ + uint32_t rootErrorStatus; + uint32_t uncorrErrorStatus; + uint32_t corrErrorStatus; + uint32_t tlpHdr1; + uint32_t tlpHdr2; + uint32_t tlpHdr3; + uint32_t tlpHdr4; + uint32_t sourceId; + + uint32_t rsv3; + + /* Record data about the call to allocate a buffer */ + uint64_t errorClass; + uint64_t correlator; + + uint64_t nFir; /* 000 */ + uint64_t nFirMask; /* 003 */ + uint64_t nFirWOF; /* 008 */ + + /* PHB3 MMIO Error Regs */ + uint64_t phbPlssr; /* 120 */ + uint64_t phbCsr; /* 110 */ + uint64_t lemFir; /* C00 */ + uint64_t lemErrorMask; /* C18 */ + uint64_t lemWOF; /* C40 */ + uint64_t phbErrorStatus; /* C80 */ + uint64_t phbFirstErrorStatus; /* C88 */ + uint64_t phbErrorLog0; /* CC0 */ + uint64_t phbErrorLog1; /* CC8 */ + uint64_t mmioErrorStatus; /* D00 */ + uint64_t mmioFirstErrorStatus; /* D08 */ + uint64_t mmioErrorLog0; /* D40 */ + uint64_t mmioErrorLog1; /* D48 */ + uint64_t dma0ErrorStatus; /* D80 */ + uint64_t dma0FirstErrorStatus; /* D88 */ + uint64_t dma0ErrorLog0; /* DC0 */ + uint64_t dma0ErrorLog1; /* DC8 */ + uint64_t dma1ErrorStatus; /* E00 */ + uint64_t dma1FirstErrorStatus; /* E08 */ + uint64_t dma1ErrorLog0; /* E40 */ + uint64_t dma1ErrorLog1; /* E48 */ + uint64_t pestA[OPAL_PHB3_NUM_PEST_REGS]; + uint64_t pestB[OPAL_PHB3_NUM_PEST_REGS]; +}; + typedef struct oppanel_line { const char * line; uint64_t line_len; } oppanel_line_t; /* API functions */ -int64_t opal_console_write(int64_t term_number, int64_t *length, +int64_t opal_console_write(int64_t term_number, __be64 *length, const uint8_t *buffer); -int64_t opal_console_read(int64_t term_number, int64_t *length, +int64_t opal_console_read(int64_t term_number, __be64 *length, uint8_t *buffer); int64_t opal_console_write_buffer_space(int64_t term_number, - int64_t *length); -int64_t opal_rtc_read(uint32_t *year_month_day, - uint64_t *hour_minute_second_millisecond); + __be64 *length); +int64_t opal_rtc_read(__be32 *year_month_day, + __be64 *hour_minute_second_millisecond); int64_t opal_rtc_write(uint32_t year_month_day, uint64_t hour_minute_second_millisecond); int64_t opal_cec_power_down(uint64_t request); int64_t opal_cec_reboot(void); int64_t opal_read_nvram(uint64_t buffer, uint64_t size, uint64_t offset); int64_t opal_write_nvram(uint64_t buffer, uint64_t size, uint64_t offset); -int64_t opal_handle_interrupt(uint64_t isn, uint64_t *outstanding_event_mask); -int64_t opal_poll_events(uint64_t *outstanding_event_mask); +int64_t opal_handle_interrupt(uint64_t isn, __be64 *outstanding_event_mask); +int64_t opal_poll_events(__be64 *outstanding_event_mask); int64_t opal_pci_set_hub_tce_memory(uint64_t hub_id, uint64_t tce_mem_addr, uint64_t tce_mem_size); int64_t opal_pci_set_phb_tce_memory(uint64_t phb_id, uint64_t tce_mem_addr, @@ -560,9 +625,9 @@ int64_t opal_pci_set_phb_tce_memory(uint64_t phb_id, uint64_t tce_mem_addr, int64_t opal_pci_config_read_byte(uint64_t phb_id, uint64_t bus_dev_func, uint64_t offset, uint8_t *data); int64_t opal_pci_config_read_half_word(uint64_t phb_id, uint64_t bus_dev_func, - uint64_t offset, uint16_t *data); + uint64_t offset, __be16 *data); int64_t opal_pci_config_read_word(uint64_t phb_id, uint64_t bus_dev_func, - uint64_t offset, uint32_t *data); + uint64_t offset, __be32 *data); int64_t opal_pci_config_write_byte(uint64_t phb_id, uint64_t bus_dev_func, uint64_t offset, uint8_t data); int64_t opal_pci_config_write_half_word(uint64_t phb_id, uint64_t bus_dev_func, @@ -570,14 +635,14 @@ int64_t opal_pci_config_write_half_word(uint64_t phb_id, uint64_t bus_dev_func, int64_t opal_pci_config_write_word(uint64_t phb_id, uint64_t bus_dev_func, uint64_t offset, uint32_t data); int64_t opal_set_xive(uint32_t isn, uint16_t server, uint8_t priority); -int64_t opal_get_xive(uint32_t isn, uint16_t *server, uint8_t *priority); +int64_t opal_get_xive(uint32_t isn, __be16 *server, uint8_t *priority); int64_t opal_register_exception_handler(uint64_t opal_exception, uint64_t handler_address, uint64_t glue_cache_line); int64_t opal_pci_eeh_freeze_status(uint64_t phb_id, uint64_t pe_number, uint8_t *freeze_state, - uint16_t *pci_error_type, - uint64_t *phb_status); + __be16 *pci_error_type, + __be64 *phb_status); int64_t opal_pci_eeh_freeze_clear(uint64_t phb_id, uint64_t pe_number, uint64_t eeh_action_token); int64_t opal_pci_shpc(uint64_t phb_id, uint64_t shpc_action, uint8_t *state); @@ -614,13 +679,13 @@ int64_t opal_pci_msi_eoi(uint64_t phb_id, uint32_t hw_irq); int64_t opal_pci_set_xive_pe(uint64_t phb_id, uint32_t pe_number, uint32_t xive_num); int64_t opal_get_xive_source(uint64_t phb_id, uint32_t xive_num, - int32_t *interrupt_source_number); + __be32 *interrupt_source_number); int64_t opal_get_msi_32(uint64_t phb_id, uint32_t mve_number, uint32_t xive_num, - uint8_t msi_range, uint32_t *msi_address, - uint32_t *message_data); + uint8_t msi_range, __be32 *msi_address, + __be32 *message_data); int64_t opal_get_msi_64(uint64_t phb_id, uint32_t mve_number, uint32_t xive_num, uint8_t msi_range, - uint64_t *msi_address, uint32_t *message_data); + __be64 *msi_address, __be32 *message_data); int64_t opal_start_cpu(uint64_t thread_number, uint64_t start_address); int64_t opal_query_cpu_status(uint64_t thread_number, uint8_t *thread_status); int64_t opal_write_oppanel(oppanel_line_t *lines, uint64_t num_lines); @@ -642,7 +707,7 @@ int64_t opal_pci_fence_phb(uint64_t phb_id); int64_t opal_pci_reinit(uint64_t phb_id, uint8_t reinit_scope); int64_t opal_pci_mask_pe_error(uint64_t phb_id, uint16_t pe_number, uint8_t error_type, uint8_t mask_action); int64_t opal_set_slot_led_status(uint64_t phb_id, uint64_t slot_id, uint8_t led_type, uint8_t led_action); -int64_t opal_get_epow_status(uint64_t *status); +int64_t opal_get_epow_status(__be64 *status); int64_t opal_set_system_attention_led(uint8_t led_action); int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe, uint16_t *pci_error_type, uint16_t *severity); diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index d7fe9f5b46d4..ad5fcf51b252 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -181,6 +181,7 @@ #define PPC_INST_TLBIVAX 0x7c000624 #define PPC_INST_TLBSRX_DOT 0x7c0006a5 #define PPC_INST_XXLOR 0xf0000510 +#define PPC_INST_XXSWAPD 0xf0000250 #define PPC_INST_XVCPSGNDP 0xf0000780 #define PPC_INST_TRECHKPT 0x7c0007dd #define PPC_INST_TRECLAIM 0x7c00075d @@ -344,6 +345,8 @@ VSX_XX1((s), a, b)) #define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \ VSX_XX3((t), a, b)) +#define XXSWAPD(t, a) stringify_in_c(.long PPC_INST_XXSWAPD | \ + VSX_XX3((t), a, a)) #define XVCPSGNDP(t, a, b) stringify_in_c(.long (PPC_INST_XVCPSGNDP | \ VSX_XX3((t), (a), (b)))) diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 140f67090f0b..8deaaad3b32f 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -124,14 +124,25 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #define REST_16VRS(n,b,base) REST_8VRS(n,b,base); REST_8VRS(n+8,b,base) #define REST_32VRS(n,b,base) REST_16VRS(n,b,base); REST_16VRS(n+16,b,base) +#ifdef __BIG_ENDIAN__ +#define STXVD2X_ROT(n,b,base) STXVD2X(n,b,base) +#define LXVD2X_ROT(n,b,base) LXVD2X(n,b,base) +#else +#define STXVD2X_ROT(n,b,base) XXSWAPD(n,n); \ + STXVD2X(n,b,base); \ + XXSWAPD(n,n) + +#define LXVD2X_ROT(n,b,base) LXVD2X(n,b,base); \ + XXSWAPD(n,n) +#endif /* Save the lower 32 VSRs in the thread VSR region */ -#define SAVE_VSR(n,b,base) li b,16*(n); STXVD2X(n,R##base,R##b) +#define SAVE_VSR(n,b,base) li b,16*(n); STXVD2X_ROT(n,R##base,R##b) #define SAVE_2VSRS(n,b,base) SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base) #define SAVE_4VSRS(n,b,base) SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base) #define SAVE_8VSRS(n,b,base) SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base) #define SAVE_16VSRS(n,b,base) SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base) #define SAVE_32VSRS(n,b,base) SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base) -#define REST_VSR(n,b,base) li b,16*(n); LXVD2X(n,R##base,R##b) +#define REST_VSR(n,b,base) li b,16*(n); LXVD2X_ROT(n,R##base,R##b) #define REST_2VSRS(n,b,base) REST_VSR(n,b,base); REST_VSR(n+1,b,base) #define REST_4VSRS(n,b,base) REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base) #define REST_8VSRS(n,b,base) REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base) @@ -749,6 +760,35 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,946) #define N_SLINE 68 #define N_SO 100 -#endif /* __ASSEMBLY__ */ +/* + * Create an endian fixup trampoline + * + * This starts with a "tdi 0,0,0x48" instruction which is + * essentially a "trap never", and thus akin to a nop. + * + * The opcode for this instruction read with the wrong endian + * however results in a b . + 8 + * + * So essentially we use that trick to execute the following + * trampoline in "reverse endian" if we are running with the + * MSR_LE bit set the "wrong" way for whatever endianness the + * kernel is built for. + */ +#ifdef CONFIG_PPC_BOOK3E +#define FIXUP_ENDIAN +#else +#define FIXUP_ENDIAN \ + tdi 0,0,0x48; /* Reverse endian of b . + 8 */ \ + b $+36; /* Skip trampoline if endian is good */ \ + .long 0x05009f42; /* bcl 20,31,$+4 */ \ + .long 0xa602487d; /* mflr r10 */ \ + .long 0x1c004a39; /* addi r10,r10,28 */ \ + .long 0xa600607d; /* mfmsr r11 */ \ + .long 0x01006b69; /* xori r11,r11,1 */ \ + .long 0xa6035a7d; /* mtsrr0 r10 */ \ + .long 0xa6037b7d; /* mtsrr1 r11 */ \ + .long 0x2400004c /* rfid */ +#endif /* !CONFIG_PPC_BOOK3E */ +#endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PPC_ASM_H */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index ea88e7bd4a34..c1583070937d 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -14,8 +14,18 @@ #ifdef CONFIG_VSX #define TS_FPRWIDTH 2 + +#ifdef __BIG_ENDIAN__ +#define TS_FPROFFSET 0 +#define TS_VSRLOWOFFSET 1 +#else +#define TS_FPROFFSET 1 +#define TS_VSRLOWOFFSET 0 +#endif + #else #define TS_FPRWIDTH 1 +#define TS_FPROFFSET 0 #endif #ifdef CONFIG_PPC64 @@ -142,8 +152,6 @@ typedef struct { unsigned long seg; } mm_segment_t; -#define TS_FPROFFSET 0 -#define TS_VSRLOWOFFSET 1 #define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET] #define TS_TRANS_FPR(i) transact_fp.fpr[i][TS_FPROFFSET] diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 10d1ef016bf1..126f6e98f84d 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -115,7 +115,12 @@ #define MSR_64BIT MSR_SF /* Server variant */ -#define MSR_ (MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV) +#define __MSR (MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV) +#ifdef __BIG_ENDIAN__ +#define MSR_ __MSR +#else +#define MSR_ (__MSR | MSR_LE) +#endif #define MSR_KERNEL (MSR_ | MSR_64BIT) #define MSR_USER32 (MSR_ | MSR_PR | MSR_EE) #define MSR_USER64 (MSR_USER32 | MSR_64BIT) diff --git a/arch/powerpc/include/asm/scom.h b/arch/powerpc/include/asm/scom.h index 0cabfd7bc2d1..07dcdcfdaefc 100644 --- a/arch/powerpc/include/asm/scom.h +++ b/arch/powerpc/include/asm/scom.h @@ -54,8 +54,8 @@ struct scom_controller { scom_map_t (*map)(struct device_node *ctrl_dev, u64 reg, u64 count); void (*unmap)(scom_map_t map); - u64 (*read)(scom_map_t map, u32 reg); - void (*write)(scom_map_t map, u32 reg, u64 value); + int (*read)(scom_map_t map, u32 reg, u64 *value); + int (*write)(scom_map_t map, u32 reg, u64 value); }; extern const struct scom_controller *scom_controller; @@ -133,10 +133,18 @@ static inline void scom_unmap(scom_map_t map) * scom_read - Read a SCOM register * @map: Result of scom_map * @reg: Register index within that map + * @value: Updated with the value read + * + * Returns 0 (success) or a negative error code */ -static inline u64 scom_read(scom_map_t map, u32 reg) +static inline int scom_read(scom_map_t map, u32 reg, u64 *value) { - return scom_controller->read(map, reg); + int rc; + + rc = scom_controller->read(map, reg, value); + if (rc) + *value = 0xfffffffffffffffful; + return rc; } /** @@ -144,12 +152,15 @@ static inline u64 scom_read(scom_map_t map, u32 reg) * @map: Result of scom_map * @reg: Register index within that map * @value: Value to write + * + * Returns 0 (success) or a negative error code */ -static inline void scom_write(scom_map_t map, u32 reg, u64 value) +static inline int scom_write(scom_map_t map, u32 reg, u64 value) { - scom_controller->write(map, reg, value); + return scom_controller->write(map, reg, value); } + #endif /* CONFIG_PPC_SCOM */ #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index e40010abcaf1..0dffad6bcc84 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -10,7 +10,9 @@ #define __HAVE_ARCH_STRNCMP #define __HAVE_ARCH_STRCAT #define __HAVE_ARCH_MEMSET +#ifdef __BIG_ENDIAN__ #define __HAVE_ARCH_MEMCPY +#endif #define __HAVE_ARCH_MEMMOVE #define __HAVE_ARCH_MEMCMP #define __HAVE_ARCH_MEMCHR @@ -22,7 +24,9 @@ extern int strcmp(const char *,const char *); extern int strncmp(const char *, const char *, __kernel_size_t); extern char * strcat(char *, const char *); extern void * memset(void *,int,__kernel_size_t); +#ifdef __BIG_ENDIAN__ extern void * memcpy(void *,const void *,__kernel_size_t); +#endif extern void * memmove(void *,const void *,__kernel_size_t); extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index d0b6d4ac6dda..213a5f2b0717 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -8,6 +8,8 @@ #include <linux/kernel.h> #include <asm/asm-compat.h> +#ifdef __BIG_ENDIAN__ + struct word_at_a_time { const unsigned long high_bits, low_bits; }; @@ -38,4 +40,73 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct return (val + c->high_bits) & ~rhs; } +#else + +/* + * This is largely generic for little-endian machines, but the + * optimal byte mask counting is probably going to be something + * that is architecture-specific. If you have a reliably fast + * bit count instruction, that might be better than the multiply + * and shift, for example. + */ +struct word_at_a_time { + const unsigned long one_bits, high_bits; +}; + +#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } + +#ifdef CONFIG_64BIT + +/* + * Jan Achrenius on G+: microoptimized version of + * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56" + * that works for the bytemasks without having to + * mask them first. + */ +static inline long count_masked_bytes(unsigned long mask) +{ + return mask*0x0001020304050608ul >> 56; +} + +#else /* 32-bit case */ + +/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ +static inline long count_masked_bytes(long mask) +{ + /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ + long a = (0x0ff0001+mask) >> 23; + /* Fix the 1 for 00 case */ + return a & mask; +} + +#endif + +/* Return nonzero if it has a zero */ +static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) +{ + unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; + *bits = mask; + return mask; +} + +static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) +{ + return bits; +} + +static inline unsigned long create_zero_mask(unsigned long bits) +{ + bits = (bits - 1) & ~bits; + return bits >> 7; +} + +/* The mask we created is directly usable as a bytemask */ +#define zero_bytemask(mask) (mask) + +static inline unsigned long find_zero(unsigned long mask) +{ + return count_masked_bytes(mask); +} +#endif + #endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/powerpc/include/uapi/asm/byteorder.h b/arch/powerpc/include/uapi/asm/byteorder.h index aa6cc4fac965..ca931d074000 100644 --- a/arch/powerpc/include/uapi/asm/byteorder.h +++ b/arch/powerpc/include/uapi/asm/byteorder.h @@ -7,6 +7,10 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#ifdef __LITTLE_ENDIAN__ +#include <linux/byteorder/little_endian.h> +#else #include <linux/byteorder/big_endian.h> +#endif #endif /* _ASM_POWERPC_BYTEORDER_H */ diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index eaa16bc17e9d..6e3f9772aaba 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -54,8 +54,6 @@ struct aligninfo { /* DSISR bits reported for a DCBZ instruction: */ #define DCBZ 0x5f /* 8xx/82xx dcbz faults when cache not enabled */ -#define SWAP(a, b) (t = (a), (a) = (b), (b) = t) - /* * The PowerPC stores certain bits of the instruction that caused the * alignment exception in the DSISR register. This array maps those @@ -264,6 +262,7 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr) #define SWIZ_PTR(p) ((unsigned char __user *)((p) ^ swiz)) +#ifdef __BIG_ENDIAN__ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, unsigned int reg, unsigned int nb, unsigned int flags, unsigned int instr, @@ -392,6 +391,7 @@ static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg, return -EFAULT; return 1; /* exception handled and fixed up */ } +#endif #ifdef CONFIG_SPE @@ -458,7 +458,7 @@ static struct aligninfo spe_aligninfo[32] = { static int emulate_spe(struct pt_regs *regs, unsigned int reg, unsigned int instr) { - int t, ret; + int ret; union { u64 ll; u32 w[2]; @@ -581,24 +581,18 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, if (flags & SW) { switch (flags & 0xf0) { case E8: - SWAP(data.v[0], data.v[7]); - SWAP(data.v[1], data.v[6]); - SWAP(data.v[2], data.v[5]); - SWAP(data.v[3], data.v[4]); + data.ll = swab64(data.ll); break; case E4: - - SWAP(data.v[0], data.v[3]); - SWAP(data.v[1], data.v[2]); - SWAP(data.v[4], data.v[7]); - SWAP(data.v[5], data.v[6]); + data.w[0] = swab32(data.w[0]); + data.w[1] = swab32(data.w[1]); break; /* Its half word endian */ default: - SWAP(data.v[0], data.v[1]); - SWAP(data.v[2], data.v[3]); - SWAP(data.v[4], data.v[5]); - SWAP(data.v[6], data.v[7]); + data.h[0] = swab16(data.h[0]); + data.h[1] = swab16(data.h[1]); + data.h[2] = swab16(data.h[2]); + data.h[3] = swab16(data.h[3]); break; } } @@ -658,14 +652,31 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg, flush_vsx_to_thread(current); if (reg < 32) - ptr = (char *) ¤t->thread.TS_FPR(reg); + ptr = (char *) ¤t->thread.fp_state.fpr[reg][0]; else ptr = (char *) ¤t->thread.vr_state.vr[reg - 32]; lptr = (unsigned long *) ptr; +#ifdef __LITTLE_ENDIAN__ + if (flags & SW) { + elsize = length; + sw = length-1; + } else { + /* + * The elements are BE ordered, even in LE mode, so process + * them in reverse order. + */ + addr += length - elsize; + + /* 8 byte memory accesses go in the top 8 bytes of the VR */ + if (length == 8) + ptr += 8; + } +#else if (flags & SW) sw = elsize-1; +#endif for (j = 0; j < length; j += elsize) { for (i = 0; i < elsize; ++i) { @@ -675,19 +686,31 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg, ret |= __get_user(ptr[i^sw], addr + i); } ptr += elsize; +#ifdef __LITTLE_ENDIAN__ + addr -= elsize; +#else addr += elsize; +#endif } +#ifdef __BIG_ENDIAN__ +#define VSX_HI 0 +#define VSX_LO 1 +#else +#define VSX_HI 1 +#define VSX_LO 0 +#endif + if (!ret) { if (flags & U) regs->gpr[areg] = regs->dar; /* Splat load copies the same data to top and bottom 8 bytes */ if (flags & SPLT) - lptr[1] = lptr[0]; - /* For 8 byte loads, zero the top 8 bytes */ + lptr[VSX_LO] = lptr[VSX_HI]; + /* For 8 byte loads, zero the low 8 bytes */ else if (!(flags & ST) && (8 == length)) - lptr[1] = 0; + lptr[VSX_LO] = 0; } else return -EFAULT; @@ -710,18 +733,28 @@ int fix_alignment(struct pt_regs *regs) unsigned int dsisr; unsigned char __user *addr; unsigned long p, swiz; - int ret, t; - union { + int ret, i; + union data { u64 ll; double dd; unsigned char v[8]; struct { +#ifdef __LITTLE_ENDIAN__ + int low32; + unsigned hi32; +#else unsigned hi32; int low32; +#endif } x32; struct { +#ifdef __LITTLE_ENDIAN__ + short low16; + unsigned char hi48[6]; +#else unsigned char hi48[6]; short low16; +#endif } x16; } data; @@ -780,8 +813,9 @@ int fix_alignment(struct pt_regs *regs) /* Byteswap little endian loads and stores */ swiz = 0; - if (regs->msr & MSR_LE) { + if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) { flags ^= SW; +#ifdef __BIG_ENDIAN__ /* * So-called "PowerPC little endian" mode works by * swizzling addresses rather than by actually doing @@ -794,6 +828,7 @@ int fix_alignment(struct pt_regs *regs) */ if (cpu_has_feature(CPU_FTR_PPC_LE)) swiz = 7; +#endif } /* DAR has the operand effective address */ @@ -818,7 +853,7 @@ int fix_alignment(struct pt_regs *regs) elsize = 8; flags = 0; - if (regs->msr & MSR_LE) + if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) flags |= SW; if (instruction & 0x100) flags |= ST; @@ -847,9 +882,13 @@ int fix_alignment(struct pt_regs *regs) * function */ if (flags & M) { +#ifdef __BIG_ENDIAN__ PPC_WARN_ALIGNMENT(multiple, regs); return emulate_multiple(regs, addr, reg, nb, flags, instr, swiz); +#else + return -EFAULT; +#endif } /* Verify the address of the operand */ @@ -868,8 +907,12 @@ int fix_alignment(struct pt_regs *regs) /* Special case for 16-byte FP loads and stores */ if (nb == 16) { +#ifdef __BIG_ENDIAN__ PPC_WARN_ALIGNMENT(fp_pair, regs); return emulate_fp_pair(addr, reg, flags); +#else + return -EFAULT; +#endif } PPC_WARN_ALIGNMENT(unaligned, regs); @@ -878,24 +921,28 @@ int fix_alignment(struct pt_regs *regs) * get it from register values */ if (!(flags & ST)) { - data.ll = 0; - ret = 0; - p = (unsigned long) addr; + unsigned int start = 0; + switch (nb) { - case 8: - ret |= __get_user_inatomic(data.v[0], SWIZ_PTR(p++)); - ret |= __get_user_inatomic(data.v[1], SWIZ_PTR(p++)); - ret |= __get_user_inatomic(data.v[2], SWIZ_PTR(p++)); - ret |= __get_user_inatomic(data.v[3], SWIZ_PTR(p++)); case 4: - ret |= __get_user_inatomic(data.v[4], SWIZ_PTR(p++)); - ret |= __get_user_inatomic(data.v[5], SWIZ_PTR(p++)); + start = offsetof(union data, x32.low32); + break; case 2: - ret |= __get_user_inatomic(data.v[6], SWIZ_PTR(p++)); - ret |= __get_user_inatomic(data.v[7], SWIZ_PTR(p++)); - if (unlikely(ret)) - return -EFAULT; + start = offsetof(union data, x16.low16); + break; } + + data.ll = 0; + ret = 0; + p = (unsigned long)addr; + + for (i = 0; i < nb; i++) + ret |= __get_user_inatomic(data.v[start + i], + SWIZ_PTR(p++)); + + if (unlikely(ret)) + return -EFAULT; + } else if (flags & F) { data.ll = current->thread.TS_FPR(reg); if (flags & S) { @@ -903,7 +950,7 @@ int fix_alignment(struct pt_regs *regs) #ifdef CONFIG_PPC_FPU preempt_disable(); enable_kernel_fp(); - cvt_df(&data.dd, (float *)&data.v[4]); + cvt_df(&data.dd, (float *)&data.x32.low32); preempt_enable(); #else return 0; @@ -915,17 +962,13 @@ int fix_alignment(struct pt_regs *regs) if (flags & SW) { switch (nb) { case 8: - SWAP(data.v[0], data.v[7]); - SWAP(data.v[1], data.v[6]); - SWAP(data.v[2], data.v[5]); - SWAP(data.v[3], data.v[4]); + data.ll = swab64(data.ll); break; case 4: - SWAP(data.v[4], data.v[7]); - SWAP(data.v[5], data.v[6]); + data.x32.low32 = swab32(data.x32.low32); break; case 2: - SWAP(data.v[6], data.v[7]); + data.x16.low16 = swab16(data.x16.low16); break; } } @@ -947,7 +990,7 @@ int fix_alignment(struct pt_regs *regs) #ifdef CONFIG_PPC_FPU preempt_disable(); enable_kernel_fp(); - cvt_fd((float *)&data.v[4], &data.dd); + cvt_fd((float *)&data.x32.low32, &data.dd); preempt_enable(); #else return 0; @@ -957,21 +1000,24 @@ int fix_alignment(struct pt_regs *regs) /* Store result to memory or update registers */ if (flags & ST) { - ret = 0; - p = (unsigned long) addr; + unsigned int start = 0; + switch (nb) { - case 8: - ret |= __put_user_inatomic(data.v[0], SWIZ_PTR(p++)); - ret |= __put_user_inatomic(data.v[1], SWIZ_PTR(p++)); - ret |= __put_user_inatomic(data.v[2], SWIZ_PTR(p++)); - ret |= __put_user_inatomic(data.v[3], SWIZ_PTR(p++)); case 4: - ret |= __put_user_inatomic(data.v[4], SWIZ_PTR(p++)); - ret |= __put_user_inatomic(data.v[5], SWIZ_PTR(p++)); + start = offsetof(union data, x32.low32); + break; case 2: - ret |= __put_user_inatomic(data.v[6], SWIZ_PTR(p++)); - ret |= __put_user_inatomic(data.v[7], SWIZ_PTR(p++)); + start = offsetof(union data, x16.low16); + break; } + + ret = 0; + p = (unsigned long)addr; + + for (i = 0; i < nb; i++) + ret |= __put_user_inatomic(data.v[start + i], + SWIZ_PTR(p++)); + if (unlikely(ret)) return -EFAULT; } else if (flags & F) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 55593ee2d5aa..1fb331db34c8 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -327,11 +327,11 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) /* Isolate the PHB and send event */ eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED); eeh_serialize_unlock(flags); - eeh_send_failure_event(phb_pe); pr_err("EEH: PHB#%x failure detected\n", phb_pe->phb->global_number); dump_stack(); + eeh_send_failure_event(phb_pe); return 1; out: @@ -454,8 +454,6 @@ int eeh_dev_check_failure(struct eeh_dev *edev) eeh_pe_state_mark(pe, EEH_PE_ISOLATED); eeh_serialize_unlock(flags); - eeh_send_failure_event(pe); - /* Most EEH events are due to device driver bugs. Having * a stack trace will help the device-driver authors figure * out what happened. So print that out. @@ -464,6 +462,8 @@ int eeh_dev_check_failure(struct eeh_dev *edev) pe->addr, pe->phb->global_number); dump_stack(); + eeh_send_failure_event(pe); + return 1; dn_unlock: diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index c04cdf70d487..12679cd43e0c 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -673,9 +673,7 @@ _GLOBAL(ret_from_except_lite) resume_kernel: /* check current_thread_info, _TIF_EMULATE_STACK_STORE */ - CURRENT_THREAD_INFO(r9, r1) - ld r8,TI_FLAGS(r9) - andis. r8,r8,_TIF_EMULATE_STACK_STORE@h + andis. r8,r4,_TIF_EMULATE_STACK_STORE@h beq+ 1f addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ @@ -1017,7 +1015,7 @@ _GLOBAL(enter_rtas) li r9,1 rldicr r9,r9,MSR_SF_LG,(63-MSR_SF_LG) - ori r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI + ori r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI|MSR_LE andc r6,r0,r9 sync /* disable interrupts so SRR0/1 */ mtmsrd r0 /* don't get trashed */ @@ -1032,6 +1030,8 @@ _GLOBAL(enter_rtas) b . /* prevent speculative execution */ _STATIC(rtas_return_loc) + FIXUP_ENDIAN + /* relocation is off at this point */ GET_PACA(r4) clrldi r4,r4,2 /* convert to realmode address */ @@ -1103,28 +1103,30 @@ _GLOBAL(enter_prom) std r10,_CCR(r1) std r11,_MSR(r1) - /* Get the PROM entrypoint */ - mtlr r4 + /* Put PROM address in SRR0 */ + mtsrr0 r4 - /* Switch MSR to 32 bits mode + /* Setup our trampoline return addr in LR */ + bcl 20,31,$+4 +0: mflr r4 + addi r4,r4,(1f - 0b) + mtlr r4 + + /* Prepare a 32-bit mode big endian MSR */ #ifdef CONFIG_PPC_BOOK3E rlwinm r11,r11,0,1,31 - mtmsr r11 + mtsrr1 r11 + rfi #else /* CONFIG_PPC_BOOK3E */ - mfmsr r11 - li r12,1 - rldicr r12,r12,MSR_SF_LG,(63-MSR_SF_LG) - andc r11,r11,r12 - li r12,1 - rldicr r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG) - andc r11,r11,r12 - mtmsrd r11 + LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE) + andc r11,r11,r12 + mtsrr1 r11 + rfid #endif /* CONFIG_PPC_BOOK3E */ - isync - /* Enter PROM here... */ - blrl +1: /* Return from OF */ + FIXUP_ENDIAN /* Just make sure that r1 top 32 bits didn't get * corrupt by OF diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 2d067049db27..68d74b45232d 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -607,6 +607,7 @@ kernel_dbg_exc: NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR, PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x260, PACA_EXGEN, INTS_DISABLE) + CHECK_NAPPING() addi r3,r1,STACK_FRAME_OVERHEAD bl .performance_monitor_exception b .ret_from_except_lite diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 1fb78561096a..9b27b293a922 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -174,7 +174,11 @@ __ftrace_make_nop(struct module *mod, pr_devel(" %08x %08x\n", jmp[0], jmp[1]); +#ifdef __LITTLE_ENDIAN__ + ptr = ((unsigned long)jmp[1] << 32) + jmp[0]; +#else ptr = ((unsigned long)jmp[0] << 32) + jmp[1]; +#endif /* This should match what was called */ if (ptr != ppc_function_entry((void *)addr)) { diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 3d11d8038dee..2ae41aba4053 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -68,6 +68,7 @@ _stext: _GLOBAL(__start) /* NOP this out unconditionally */ BEGIN_FTR_SECTION + FIXUP_ENDIAN b .__start_initialization_multiplatform END_FTR_SECTION(0, 1) @@ -115,6 +116,7 @@ __run_at_load: */ .globl __secondary_hold __secondary_hold: + FIXUP_ENDIAN #ifndef CONFIG_PPC_BOOK3E mfmsr r24 ori r24,r24,MSR_RI @@ -205,6 +207,7 @@ _GLOBAL(generic_secondary_thread_init) * as SCOM before entry). */ _GLOBAL(generic_secondary_smp_init) + FIXUP_ENDIAN mr r24,r3 mr r25,r4 diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 22e88dd2f34a..40bd7bd4e19a 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -35,7 +35,7 @@ static struct legacy_serial_info { phys_addr_t taddr; } legacy_serial_infos[MAX_LEGACY_SERIAL_PORTS]; -static struct __initdata of_device_id legacy_serial_parents[] = { +static struct of_device_id legacy_serial_parents[] __initdata = { {.type = "soc",}, {.type = "tsi-bridge",}, {.type = "opb", }, diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 2b0ad9845363..e47d268727a4 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -659,6 +659,20 @@ _GLOBAL(__lshrdi3) blr /* + * 64-bit comparison: __cmpdi2(s64 a, s64 b) + * Returns 0 if a < b, 1 if a == b, 2 if a > b. + */ +_GLOBAL(__cmpdi2) + cmpw r3,r5 + li r3,1 + bne 1f + cmplw r4,r6 + beqlr +1: li r3,0 + bltlr + li r3,2 + blr +/* * 64-bit comparison: __ucmpdi2(u64 a, u64 b) * Returns 0 if a < b, 1 if a == b, 2 if a > b. */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 6ee59a0eb268..a102f4412392 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -62,6 +62,16 @@ struct ppc64_stub_entry r2) into the stub. */ static struct ppc64_stub_entry ppc64_stub = { .jump = { +#ifdef __LITTLE_ENDIAN__ + 0x00, 0x00, 0x82, 0x3d, /* addis r12,r2, <high> */ + 0x00, 0x00, 0x8c, 0x39, /* addi r12,r12, <low> */ + /* Save current r2 value in magic place on the stack. */ + 0x28, 0x00, 0x41, 0xf8, /* std r2,40(r1) */ + 0x20, 0x00, 0x6c, 0xe9, /* ld r11,32(r12) */ + 0x28, 0x00, 0x4c, 0xe8, /* ld r2,40(r12) */ + 0xa6, 0x03, 0x69, 0x7d, /* mtctr r11 */ + 0x20, 0x04, 0x80, 0x4e /* bctr */ +#else 0x3d, 0x82, 0x00, 0x00, /* addis r12,r2, <high> */ 0x39, 0x8c, 0x00, 0x00, /* addi r12,r12, <low> */ /* Save current r2 value in magic place on the stack. */ @@ -70,6 +80,7 @@ static struct ppc64_stub_entry ppc64_stub = 0xe8, 0x4c, 0x00, 0x28, /* ld r2,40(r12) */ 0x7d, 0x69, 0x03, 0xa6, /* mtctr r11 */ 0x4e, 0x80, 0x04, 0x20 /* bctr */ +#endif } }; /* Count how many different 24-bit relocations (different symbol, @@ -269,8 +280,13 @@ static inline int create_stub(Elf64_Shdr *sechdrs, *entry = ppc64_stub; +#ifdef __LITTLE_ENDIAN__ + loc1 = (Elf64_Half *)&entry->jump[0]; + loc2 = (Elf64_Half *)&entry->jump[4]; +#else loc1 = (Elf64_Half *)&entry->jump[2]; loc2 = (Elf64_Half *)&entry->jump[6]; +#endif /* Stub uses address relative to r2. */ reladdr = (unsigned long)entry - my_r2(sechdrs, me); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 3fc16e3beb9f..0620eaaaad45 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -46,7 +46,7 @@ struct lppaca lppaca[] = { static struct lppaca *extra_lppacas; static long __initdata lppaca_size; -static void allocate_lppacas(int nr_cpus, unsigned long limit) +static void __init allocate_lppacas(int nr_cpus, unsigned long limit) { if (nr_cpus <= NR_LPPACAS) return; @@ -57,7 +57,7 @@ static void allocate_lppacas(int nr_cpus, unsigned long limit) PAGE_SIZE, limit)); } -static struct lppaca *new_lppaca(int cpu) +static struct lppaca * __init new_lppaca(int cpu) { struct lppaca *lp; @@ -70,7 +70,7 @@ static struct lppaca *new_lppaca(int cpu) return lp; } -static void free_lppacas(void) +static void __init free_lppacas(void) { long new_size = 0, nr; diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 56a4bec1b11a..3bd77edd7610 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -79,10 +79,12 @@ EXPORT_SYMBOL(strlen); EXPORT_SYMBOL(strcmp); EXPORT_SYMBOL(strncmp); +#ifndef CONFIG_GENERIC_CSUM EXPORT_SYMBOL(csum_partial); EXPORT_SYMBOL(csum_partial_copy_generic); EXPORT_SYMBOL(ip_fast_csum); EXPORT_SYMBOL(csum_tcpudp_magic); +#endif EXPORT_SYMBOL(__copy_tofrom_user); EXPORT_SYMBOL(__clear_user); @@ -147,10 +149,14 @@ EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__lshrdi3); int __ucmpdi2(unsigned long long, unsigned long long); EXPORT_SYMBOL(__ucmpdi2); +int __cmpdi2(long long, long long); +EXPORT_SYMBOL(__cmpdi2); #endif long long __bswapdi2(long long); EXPORT_SYMBOL(__bswapdi2); +#ifdef __BIG_ENDIAN__ EXPORT_SYMBOL(memcpy); +#endif EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memcmp); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 5fe2842e8bab..cb64a6e1dc51 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -858,7 +858,8 @@ static void __init prom_send_capabilities(void) { ihandle root; prom_arg_t ret; - __be32 *cores; + u32 cores; + unsigned char *ptcores; root = call_prom("open", 1, 1, ADDR("/")); if (root != 0) { @@ -868,15 +869,30 @@ static void __init prom_send_capabilities(void) * (we assume this is the same for all cores) and use it to * divide NR_CPUS. */ - cores = (__be32 *)&ibm_architecture_vec[IBM_ARCH_VEC_NRCORES_OFFSET]; - if (be32_to_cpup(cores) != NR_CPUS) { + + /* The core value may start at an odd address. If such a word + * access is made at a cache line boundary, this leads to an + * exception which may not be handled at this time. + * Forcing a per byte access to avoid exception. + */ + ptcores = &ibm_architecture_vec[IBM_ARCH_VEC_NRCORES_OFFSET]; + cores = 0; + cores |= ptcores[0] << 24; + cores |= ptcores[1] << 16; + cores |= ptcores[2] << 8; + cores |= ptcores[3]; + if (cores != NR_CPUS) { prom_printf("WARNING ! " "ibm_architecture_vec structure inconsistent: %lu!\n", - be32_to_cpup(cores)); + cores); } else { - *cores = cpu_to_be32(DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads())); + cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads()); prom_printf("Max number of cores passed to firmware: %lu (NR_CPUS = %lu)\n", - be32_to_cpup(cores), NR_CPUS); + cores, NR_CPUS); + ptcores[0] = (cores >> 24) & 0xff; + ptcores[1] = (cores >> 16) & 0xff; + ptcores[2] = (cores >> 8) & 0xff; + ptcores[3] = cores & 0xff; } /* try calling the ibm,client-architecture-support method */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 238580043d85..1ca589c9ec6d 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -1555,8 +1555,8 @@ long arch_ptrace(struct task_struct *child, long request, flush_fp_to_thread(child); if (fpidx < (PT_FPSCR - PT_FPR0)) - tmp = ((unsigned long *)child->thread.fp_state.fpr) - [fpidx * TS_FPRWIDTH]; + memcpy(&tmp, &child->thread.fp_state.fpr, + sizeof(long)); else tmp = child->thread.fp_state.fpscr; } @@ -1588,8 +1588,8 @@ long arch_ptrace(struct task_struct *child, long request, flush_fp_to_thread(child); if (fpidx < (PT_FPSCR - PT_FPR0)) - ((unsigned long *)child->thread.fp_state.fpr) - [fpidx * TS_FPRWIDTH] = data; + memcpy(&child->thread.fp_state.fpr, &data, + sizeof(long)); else child->thread.fp_state.fpscr = data; ret = 0; diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 6e7b7cdeec65..7d4c7172f38e 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -223,7 +223,7 @@ unsigned long get_phb_buid(struct device_node *phb) static int phb_set_bus_ranges(struct device_node *dev, struct pci_controller *phb) { - const int *bus_range; + const __be32 *bus_range; unsigned int len; bus_range = of_get_property(dev, "bus-range", &len); @@ -231,8 +231,8 @@ static int phb_set_bus_ranges(struct device_node *dev, return 1; } - phb->first_busno = bus_range[0]; - phb->last_busno = bus_range[1]; + phb->first_busno = be32_to_cpu(bus_range[0]); + phb->last_busno = be32_to_cpu(bus_range[1]); return 0; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index ea25e45ea959..c094e28b3f10 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1047,8 +1047,9 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, regs->gpr[5] = (unsigned long) &rt_sf->uc; regs->gpr[6] = (unsigned long) rt_sf; regs->nip = (unsigned long) ka->sa.sa_handler; - /* enter the signal handler in big-endian mode */ + /* enter the signal handler in native-endian mode */ regs->msr &= ~MSR_LE; + regs->msr |= (MSR_KERNEL & MSR_LE); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM /* Remove TM bits from thread's MSR. The MSR in the sigcontext * just indicates to userland that we were doing a transaction, but we diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index a3c1ed4b979c..b3c615764c9b 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -774,8 +774,9 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, /* Set up "regs" so we "return" to the signal handler. */ err |= get_user(regs->nip, &funct_desc_ptr->entry); - /* enter the signal handler in big-endian mode */ + /* enter the signal handler in native-endian mode */ regs->msr &= ~MSR_LE; + regs->msr |= (MSR_KERNEL & MSR_LE); regs->gpr[1] = newsp; err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); regs->gpr[3] = signr; diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index f223409629b9..e58ee10fa5c0 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -4,7 +4,11 @@ */ #include <asm/vdso.h> +#ifdef __LITTLE_ENDIAN__ +OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle") +#else OUTPUT_FORMAT("elf32-powerpc", "elf32-powerpc", "elf32-powerpc") +#endif OUTPUT_ARCH(powerpc:common) ENTRY(_start) diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index e4863819663b..64fb183a47c2 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -4,7 +4,11 @@ */ #include <asm/vdso.h> +#ifdef __LITTLE_ENDIAN__ +OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle") +#else OUTPUT_FORMAT("elf64-powerpc", "elf64-powerpc", "elf64-powerpc") +#endif OUTPUT_ARCH(powerpc:common64) ENTRY(_start) diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index ffaef2cb101a..e593ff257bd3 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -6,6 +6,7 @@ source "virt/kvm/Kconfig" menuconfig VIRTUALIZATION bool "Virtualization" + depends on !CPU_LITTLE_ENDIAN ---help--- Say Y here to get to see options for using your Linux host to run other operating systems inside virtual machines (guests). diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 450433276699..5310132856c1 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -10,15 +10,23 @@ CFLAGS_REMOVE_code-patching.o = -pg CFLAGS_REMOVE_feature-fixups.o = -pg obj-y := string.o alloc.o \ - checksum_$(CONFIG_WORD_SIZE).o crtsavres.o + crtsavres.o obj-$(CONFIG_PPC32) += div64.o copy_32.o obj-$(CONFIG_HAS_IOMEM) += devres.o obj-$(CONFIG_PPC64) += copypage_64.o copyuser_64.o \ - memcpy_64.o usercopy_64.o mem_64.o string.o \ - checksum_wrappers_64.o hweight_64.o \ - copyuser_power7.o string_64.o copypage_power7.o \ - memcpy_power7.o + usercopy_64.o mem_64.o string.o \ + hweight_64.o \ + copyuser_power7.o string_64.o copypage_power7.o +ifeq ($(CONFIG_GENERIC_CSUM),) +obj-y += checksum_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_PPC64) += checksum_wrappers_64.o +endif + +ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),) +obj-$(CONFIG_PPC64) += memcpy_power7.o memcpy_64.o +endif + obj-$(CONFIG_PPC_EMULATE_SSTEP) += sstep.o ldstfp.o ifeq ($(CONFIG_PPC64),y) diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index d1f11795a7ad..e8e9c36dc784 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -19,6 +19,14 @@ */ #include <asm/ppc_asm.h> +#ifdef __BIG_ENDIAN__ +#define LVS(VRT,RA,RB) lvsl VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC +#else +#define LVS(VRT,RA,RB) lvsr VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRB,VRA,VRC +#endif + .macro err1 100: .section __ex_table,"a" @@ -552,13 +560,13 @@ err3; stw r7,4(r3) li r10,32 li r11,48 - lvsl vr16,0,r4 /* Setup permute control vector */ + LVS(vr16,0,r4) /* Setup permute control vector */ err3; lvx vr0,0,r4 addi r4,r4,16 bf cr7*4+3,5f err3; lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) addi r4,r4,16 err3; stvx vr8,r0,r3 addi r3,r3,16 @@ -566,9 +574,9 @@ err3; stvx vr8,r0,r3 5: bf cr7*4+2,6f err3; lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) err3; lvx vr0,r4,r9 - vperm vr9,vr1,vr0,vr16 + VPERM(vr9,vr1,vr0,vr16) addi r4,r4,32 err3; stvx vr8,r0,r3 err3; stvx vr9,r3,r9 @@ -576,13 +584,13 @@ err3; stvx vr9,r3,r9 6: bf cr7*4+1,7f err3; lvx vr3,r0,r4 - vperm vr8,vr0,vr3,vr16 + VPERM(vr8,vr0,vr3,vr16) err3; lvx vr2,r4,r9 - vperm vr9,vr3,vr2,vr16 + VPERM(vr9,vr3,vr2,vr16) err3; lvx vr1,r4,r10 - vperm vr10,vr2,vr1,vr16 + VPERM(vr10,vr2,vr1,vr16) err3; lvx vr0,r4,r11 - vperm vr11,vr1,vr0,vr16 + VPERM(vr11,vr1,vr0,vr16) addi r4,r4,64 err3; stvx vr8,r0,r3 err3; stvx vr9,r3,r9 @@ -611,21 +619,21 @@ err3; stvx vr11,r3,r11 .align 5 8: err4; lvx vr7,r0,r4 - vperm vr8,vr0,vr7,vr16 + VPERM(vr8,vr0,vr7,vr16) err4; lvx vr6,r4,r9 - vperm vr9,vr7,vr6,vr16 + VPERM(vr9,vr7,vr6,vr16) err4; lvx vr5,r4,r10 - vperm vr10,vr6,vr5,vr16 + VPERM(vr10,vr6,vr5,vr16) err4; lvx vr4,r4,r11 - vperm vr11,vr5,vr4,vr16 + VPERM(vr11,vr5,vr4,vr16) err4; lvx vr3,r4,r12 - vperm vr12,vr4,vr3,vr16 + VPERM(vr12,vr4,vr3,vr16) err4; lvx vr2,r4,r14 - vperm vr13,vr3,vr2,vr16 + VPERM(vr13,vr3,vr2,vr16) err4; lvx vr1,r4,r15 - vperm vr14,vr2,vr1,vr16 + VPERM(vr14,vr2,vr1,vr16) err4; lvx vr0,r4,r16 - vperm vr15,vr1,vr0,vr16 + VPERM(vr15,vr1,vr0,vr16) addi r4,r4,128 err4; stvx vr8,r0,r3 err4; stvx vr9,r3,r9 @@ -649,13 +657,13 @@ err4; stvx vr15,r3,r16 bf cr7*4+1,9f err3; lvx vr3,r0,r4 - vperm vr8,vr0,vr3,vr16 + VPERM(vr8,vr0,vr3,vr16) err3; lvx vr2,r4,r9 - vperm vr9,vr3,vr2,vr16 + VPERM(vr9,vr3,vr2,vr16) err3; lvx vr1,r4,r10 - vperm vr10,vr2,vr1,vr16 + VPERM(vr10,vr2,vr1,vr16) err3; lvx vr0,r4,r11 - vperm vr11,vr1,vr0,vr16 + VPERM(vr11,vr1,vr0,vr16) addi r4,r4,64 err3; stvx vr8,r0,r3 err3; stvx vr9,r3,r9 @@ -665,9 +673,9 @@ err3; stvx vr11,r3,r11 9: bf cr7*4+2,10f err3; lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) err3; lvx vr0,r4,r9 - vperm vr9,vr1,vr0,vr16 + VPERM(vr9,vr1,vr0,vr16) addi r4,r4,32 err3; stvx vr8,r0,r3 err3; stvx vr9,r3,r9 @@ -675,7 +683,7 @@ err3; stvx vr9,r3,r9 10: bf cr7*4+3,11f err3; lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) addi r4,r4,16 err3; stvx vr8,r0,r3 addi r3,r3,16 diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S index 0663630baf3b..e4177dbea6bd 100644 --- a/arch/powerpc/lib/memcpy_power7.S +++ b/arch/powerpc/lib/memcpy_power7.S @@ -20,6 +20,15 @@ #include <asm/ppc_asm.h> _GLOBAL(memcpy_power7) + +#ifdef __BIG_ENDIAN__ +#define LVS(VRT,RA,RB) lvsl VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC +#else +#define LVS(VRT,RA,RB) lvsr VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRB,VRA,VRC +#endif + #ifdef CONFIG_ALTIVEC cmpldi r5,16 cmpldi cr1,r5,4096 @@ -485,13 +494,13 @@ _GLOBAL(memcpy_power7) li r10,32 li r11,48 - lvsl vr16,0,r4 /* Setup permute control vector */ + LVS(vr16,0,r4) /* Setup permute control vector */ lvx vr0,0,r4 addi r4,r4,16 bf cr7*4+3,5f lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) addi r4,r4,16 stvx vr8,r0,r3 addi r3,r3,16 @@ -499,9 +508,9 @@ _GLOBAL(memcpy_power7) 5: bf cr7*4+2,6f lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) lvx vr0,r4,r9 - vperm vr9,vr1,vr0,vr16 + VPERM(vr9,vr1,vr0,vr16) addi r4,r4,32 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -509,13 +518,13 @@ _GLOBAL(memcpy_power7) 6: bf cr7*4+1,7f lvx vr3,r0,r4 - vperm vr8,vr0,vr3,vr16 + VPERM(vr8,vr0,vr3,vr16) lvx vr2,r4,r9 - vperm vr9,vr3,vr2,vr16 + VPERM(vr9,vr3,vr2,vr16) lvx vr1,r4,r10 - vperm vr10,vr2,vr1,vr16 + VPERM(vr10,vr2,vr1,vr16) lvx vr0,r4,r11 - vperm vr11,vr1,vr0,vr16 + VPERM(vr11,vr1,vr0,vr16) addi r4,r4,64 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -544,21 +553,21 @@ _GLOBAL(memcpy_power7) .align 5 8: lvx vr7,r0,r4 - vperm vr8,vr0,vr7,vr16 + VPERM(vr8,vr0,vr7,vr16) lvx vr6,r4,r9 - vperm vr9,vr7,vr6,vr16 + VPERM(vr9,vr7,vr6,vr16) lvx vr5,r4,r10 - vperm vr10,vr6,vr5,vr16 + VPERM(vr10,vr6,vr5,vr16) lvx vr4,r4,r11 - vperm vr11,vr5,vr4,vr16 + VPERM(vr11,vr5,vr4,vr16) lvx vr3,r4,r12 - vperm vr12,vr4,vr3,vr16 + VPERM(vr12,vr4,vr3,vr16) lvx vr2,r4,r14 - vperm vr13,vr3,vr2,vr16 + VPERM(vr13,vr3,vr2,vr16) lvx vr1,r4,r15 - vperm vr14,vr2,vr1,vr16 + VPERM(vr14,vr2,vr1,vr16) lvx vr0,r4,r16 - vperm vr15,vr1,vr0,vr16 + VPERM(vr15,vr1,vr0,vr16) addi r4,r4,128 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -582,13 +591,13 @@ _GLOBAL(memcpy_power7) bf cr7*4+1,9f lvx vr3,r0,r4 - vperm vr8,vr0,vr3,vr16 + VPERM(vr8,vr0,vr3,vr16) lvx vr2,r4,r9 - vperm vr9,vr3,vr2,vr16 + VPERM(vr9,vr3,vr2,vr16) lvx vr1,r4,r10 - vperm vr10,vr2,vr1,vr16 + VPERM(vr10,vr2,vr1,vr16) lvx vr0,r4,r11 - vperm vr11,vr1,vr0,vr16 + VPERM(vr11,vr1,vr0,vr16) addi r4,r4,64 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -598,9 +607,9 @@ _GLOBAL(memcpy_power7) 9: bf cr7*4+2,10f lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) lvx vr0,r4,r9 - vperm vr9,vr1,vr0,vr16 + VPERM(vr9,vr1,vr0,vr16) addi r4,r4,32 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -608,7 +617,7 @@ _GLOBAL(memcpy_power7) 10: bf cr7*4+3,11f lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) addi r4,r4,16 stvx vr8,r0,r3 addi r3,r3,16 diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index c33d939120c9..3ea26c25590b 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -35,7 +35,11 @@ #define DBG_LOW(fmt...) #endif +#ifdef __BIG_ENDIAN__ #define HPTE_LOCK_BIT 3 +#else +#define HPTE_LOCK_BIT (56+3) +#endif DEFINE_RAW_SPINLOCK(native_tlbie_lock); @@ -172,7 +176,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize, static inline void native_lock_hpte(struct hash_pte *hptep) { - unsigned long *word = &hptep->v; + unsigned long *word = (unsigned long *)&hptep->v; while (1) { if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word)) @@ -184,7 +188,7 @@ static inline void native_lock_hpte(struct hash_pte *hptep) static inline void native_unlock_hpte(struct hash_pte *hptep) { - unsigned long *word = &hptep->v; + unsigned long *word = (unsigned long *)&hptep->v; clear_bit_unlock(HPTE_LOCK_BIT, word); } @@ -204,10 +208,10 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, } for (i = 0; i < HPTES_PER_GROUP; i++) { - if (! (hptep->v & HPTE_V_VALID)) { + if (! (be64_to_cpu(hptep->v) & HPTE_V_VALID)) { /* retry with lock held */ native_lock_hpte(hptep); - if (! (hptep->v & HPTE_V_VALID)) + if (! (be64_to_cpu(hptep->v) & HPTE_V_VALID)) break; native_unlock_hpte(hptep); } @@ -226,14 +230,14 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, i, hpte_v, hpte_r); } - hptep->r = hpte_r; + hptep->r = cpu_to_be64(hpte_r); /* Guarantee the second dword is visible before the valid bit */ eieio(); /* * Now set the first dword including the valid bit * NOTE: this also unlocks the hpte */ - hptep->v = hpte_v; + hptep->v = cpu_to_be64(hpte_v); __asm__ __volatile__ ("ptesync" : : : "memory"); @@ -254,12 +258,12 @@ static long native_hpte_remove(unsigned long hpte_group) for (i = 0; i < HPTES_PER_GROUP; i++) { hptep = htab_address + hpte_group + slot_offset; - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); if ((hpte_v & HPTE_V_VALID) && !(hpte_v & HPTE_V_BOLTED)) { /* retry with lock held */ native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); if ((hpte_v & HPTE_V_VALID) && !(hpte_v & HPTE_V_BOLTED)) break; @@ -294,7 +298,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); /* * We need to invalidate the TLB always because hpte_remove doesn't do * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less @@ -308,8 +312,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, } else { DBG_LOW(" -> hit\n"); /* Update the HPTE */ - hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C)); + hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & ~(HPTE_R_PP | HPTE_R_N)) | + (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C))); } native_unlock_hpte(hptep); @@ -334,7 +338,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize) slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; for (i = 0; i < HPTES_PER_GROUP; i++) { hptep = htab_address + slot; - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) /* HPTE matches */ @@ -369,8 +373,9 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, hptep = htab_address + slot; /* Update the HPTE */ - hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N)); + hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & + ~(HPTE_R_PP | HPTE_R_N)) | + (newpp & (HPTE_R_PP | HPTE_R_N))); /* * Ensure it is out of the tlb too. Bolted entries base and * actual page size will be same. @@ -392,7 +397,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, want_v = hpte_encode_avpn(vpn, bpsize, ssize); native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); /* * We need to invalidate the TLB always because hpte_remove doesn't do @@ -458,7 +463,7 @@ static void native_hugepage_invalidate(struct mm_struct *mm, hptep = htab_address + slot; want_v = hpte_encode_avpn(vpn, psize, ssize); native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); /* Even if we miss, we need to invalidate the TLB */ if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) @@ -519,11 +524,12 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, int *psize, int *apsize, int *ssize, unsigned long *vpn) { unsigned long avpn, pteg, vpi; - unsigned long hpte_v = hpte->v; + unsigned long hpte_v = be64_to_cpu(hpte->v); + unsigned long hpte_r = be64_to_cpu(hpte->r); unsigned long vsid, seg_off; int size, a_size, shift; /* Look at the 8 bit LP value */ - unsigned int lp = (hpte->r >> LP_SHIFT) & ((1 << LP_BITS) - 1); + unsigned int lp = (hpte_r >> LP_SHIFT) & ((1 << LP_BITS) - 1); if (!(hpte_v & HPTE_V_LARGE)) { size = MMU_PAGE_4K; @@ -612,7 +618,7 @@ static void native_hpte_clear(void) * running, right? and for crash dump, we probably * don't want to wait for a maybe bad cpu. */ - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); /* * Call __tlbie() here rather than tlbie() since we @@ -664,7 +670,7 @@ static void native_flush_hash_range(unsigned long number, int local) hptep = htab_address + slot; want_v = hpte_encode_avpn(vpn, psize, ssize); native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) native_unlock_hpte(hptep); diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index bde8b5589755..6176b3cdf579 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -251,19 +251,18 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node, void *data) { char *type = of_get_flat_dt_prop(node, "device_type", NULL); - u32 *prop; + __be32 *prop; unsigned long size = 0; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) return 0; - prop = (u32 *)of_get_flat_dt_prop(node, "ibm,processor-segment-sizes", - &size); + prop = of_get_flat_dt_prop(node, "ibm,processor-segment-sizes", &size); if (prop == NULL) return 0; for (; size >= 4; size -= 4, ++prop) { - if (prop[0] == 40) { + if (be32_to_cpu(prop[0]) == 40) { DBG("1T segment support detected\n"); cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT; return 1; @@ -307,23 +306,22 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, void *data) { char *type = of_get_flat_dt_prop(node, "device_type", NULL); - u32 *prop; + __be32 *prop; unsigned long size = 0; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) return 0; - prop = (u32 *)of_get_flat_dt_prop(node, - "ibm,segment-page-sizes", &size); + prop = of_get_flat_dt_prop(node, "ibm,segment-page-sizes", &size); if (prop != NULL) { pr_info("Page sizes from device-tree:\n"); size /= 4; cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE); while(size > 0) { - unsigned int base_shift = prop[0]; - unsigned int slbenc = prop[1]; - unsigned int lpnum = prop[2]; + unsigned int base_shift = be32_to_cpu(prop[0]); + unsigned int slbenc = be32_to_cpu(prop[1]); + unsigned int lpnum = be32_to_cpu(prop[2]); struct mmu_psize_def *def; int idx, base_idx; @@ -356,8 +354,8 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, def->tlbiel = 0; while (size > 0 && lpnum) { - unsigned int shift = prop[0]; - int penc = prop[1]; + unsigned int shift = be32_to_cpu(prop[0]); + int penc = be32_to_cpu(prop[1]); prop += 2; size -= 2; lpnum--; @@ -390,8 +388,8 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node, const char *uname, int depth, void *data) { char *type = of_get_flat_dt_prop(node, "device_type", NULL); - unsigned long *addr_prop; - u32 *page_count_prop; + __be64 *addr_prop; + __be32 *page_count_prop; unsigned int expected_pages; long unsigned int phys_addr; long unsigned int block_size; @@ -405,12 +403,12 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node, page_count_prop = of_get_flat_dt_prop(node, "ibm,expected#pages", NULL); if (page_count_prop == NULL) return 0; - expected_pages = (1 << page_count_prop[0]); + expected_pages = (1 << be32_to_cpu(page_count_prop[0])); addr_prop = of_get_flat_dt_prop(node, "reg", NULL); if (addr_prop == NULL) return 0; - phys_addr = addr_prop[0]; - block_size = addr_prop[1]; + phys_addr = be64_to_cpu(addr_prop[0]); + block_size = be64_to_cpu(addr_prop[1]); if (block_size != (16 * GB)) return 0; printk(KERN_INFO "Huge page(16GB) memory: " @@ -534,16 +532,16 @@ static int __init htab_dt_scan_pftsize(unsigned long node, void *data) { char *type = of_get_flat_dt_prop(node, "device_type", NULL); - u32 *prop; + __be32 *prop; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) return 0; - prop = (u32 *)of_get_flat_dt_prop(node, "ibm,pft-size", NULL); + prop = of_get_flat_dt_prop(node, "ibm,pft-size", NULL); if (prop != NULL) { /* pft_size[0] is the NUMA CEC cookie */ - ppc64_pft_size = prop[1]; + ppc64_pft_size = be32_to_cpu(prop[1]); return 1; } return 0; diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c index 8d21ab70e06c..ef0778a0ca8f 100644 --- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c +++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c @@ -48,7 +48,7 @@ struct cpm_pin { int port, pin, flags; }; -static struct __initdata cpm_pin tqm8xx_pins[] = { +static struct cpm_pin tqm8xx_pins[] __initdata = { /* SMC1 */ {CPM_PORTB, 24, CPM_PIN_INPUT}, /* RX */ {CPM_PORTB, 25, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, /* TX */ @@ -63,7 +63,7 @@ static struct __initdata cpm_pin tqm8xx_pins[] = { {CPM_PORTC, 11, CPM_PIN_INPUT | CPM_PIN_SECONDARY | CPM_PIN_GPIO}, }; -static struct __initdata cpm_pin tqm8xx_fec_pins[] = { +static struct cpm_pin tqm8xx_fec_pins[] __initdata = { /* MII */ {CPM_PORTD, 3, CPM_PIN_OUTPUT}, {CPM_PORTD, 4, CPM_PIN_OUTPUT}, diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 6fae5eb99ea6..9fced3f6d2dc 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -9,6 +9,8 @@ config PPC_POWERNV select EPAPR_BOOT select PPC_INDIRECT_PIO select PPC_UDBG_16550 + select PPC_SCOM + select ARCH_RANDOM default y config POWERNV_MSI diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 300c437d713c..050d57e0c788 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -1,6 +1,7 @@ obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o -obj-y += opal-rtc.o opal-nvram.o opal-lpc.o +obj-y += opal-rtc.o opal-nvram.o opal-lpc.o rng.o 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 diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index cf42e74514fa..02245cee7818 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -59,26 +59,60 @@ static struct notifier_block ioda_eeh_nb = { }; #ifdef CONFIG_DEBUG_FS -static int ioda_eeh_dbgfs_set(void *data, u64 val) +static int ioda_eeh_dbgfs_set(void *data, int offset, u64 val) { struct pci_controller *hose = data; struct pnv_phb *phb = hose->private_data; - out_be64(phb->regs + 0xD10, val); + out_be64(phb->regs + offset, val); return 0; } -static int ioda_eeh_dbgfs_get(void *data, u64 *val) +static int ioda_eeh_dbgfs_get(void *data, int offset, u64 *val) { struct pci_controller *hose = data; struct pnv_phb *phb = hose->private_data; - *val = in_be64(phb->regs + 0xD10); + *val = in_be64(phb->regs + offset); return 0; } -DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_dbgfs_ops, ioda_eeh_dbgfs_get, - ioda_eeh_dbgfs_set, "0x%llx\n"); +static int ioda_eeh_outb_dbgfs_set(void *data, u64 val) +{ + return ioda_eeh_dbgfs_set(data, 0xD10, val); +} + +static int ioda_eeh_outb_dbgfs_get(void *data, u64 *val) +{ + return ioda_eeh_dbgfs_get(data, 0xD10, val); +} + +static int ioda_eeh_inbA_dbgfs_set(void *data, u64 val) +{ + return ioda_eeh_dbgfs_set(data, 0xD90, val); +} + +static int ioda_eeh_inbA_dbgfs_get(void *data, u64 *val) +{ + return ioda_eeh_dbgfs_get(data, 0xD90, val); +} + +static int ioda_eeh_inbB_dbgfs_set(void *data, u64 val) +{ + return ioda_eeh_dbgfs_set(data, 0xE10, val); +} + +static int ioda_eeh_inbB_dbgfs_get(void *data, u64 *val) +{ + return ioda_eeh_dbgfs_get(data, 0xE10, val); +} + +DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_outb_dbgfs_ops, ioda_eeh_outb_dbgfs_get, + ioda_eeh_outb_dbgfs_set, "0x%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbA_dbgfs_ops, ioda_eeh_inbA_dbgfs_get, + ioda_eeh_inbA_dbgfs_set, "0x%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get, + ioda_eeh_inbB_dbgfs_set, "0x%llx\n"); #endif /* CONFIG_DEBUG_FS */ /** @@ -106,27 +140,30 @@ static int ioda_eeh_post_init(struct pci_controller *hose) ioda_eeh_nb_init = 1; } - /* FIXME: Enable it for PHB3 later */ - if (phb->type == PNV_PHB_IODA1) { + /* We needn't HUB diag-data on PHB3 */ + if (phb->type == PNV_PHB_IODA1 && !hub_diag) { + hub_diag = (char *)__get_free_page(GFP_KERNEL | __GFP_ZERO); if (!hub_diag) { - hub_diag = (char *)__get_free_page(GFP_KERNEL | - __GFP_ZERO); - if (!hub_diag) { - pr_err("%s: Out of memory !\n", - __func__); - return -ENOMEM; - } + pr_err("%s: Out of memory !\n", __func__); + return -ENOMEM; } + } #ifdef CONFIG_DEBUG_FS - if (phb->dbgfs) - debugfs_create_file("err_injct", 0600, - phb->dbgfs, hose, - &ioda_eeh_dbgfs_ops); + if (phb->dbgfs) { + debugfs_create_file("err_injct_outbound", 0600, + phb->dbgfs, hose, + &ioda_eeh_outb_dbgfs_ops); + debugfs_create_file("err_injct_inboundA", 0600, + phb->dbgfs, hose, + &ioda_eeh_inbA_dbgfs_ops); + debugfs_create_file("err_injct_inboundB", 0600, + phb->dbgfs, hose, + &ioda_eeh_inbB_dbgfs_ops); + } #endif - phb->eeh_state |= PNV_EEH_STATE_ENABLED; - } + phb->eeh_state |= PNV_EEH_STATE_ENABLED; return 0; } @@ -546,8 +583,8 @@ static int ioda_eeh_get_log(struct eeh_pe *pe, int severity, phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE); if (ret) { spin_unlock_irqrestore(&phb->lock, flags); - pr_warning("%s: Failed to get log for PHB#%x-PE#%x\n", - __func__, hose->global_number, pe->addr); + pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n", + __func__, hose->global_number, pe->addr, ret); return -EIO; } @@ -710,6 +747,73 @@ static void ioda_eeh_p7ioc_phb_diag(struct pci_controller *hose, } } +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; @@ -728,6 +832,9 @@ static void ioda_eeh_phb_diag(struct pci_controller *hose) 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); diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 79663d26e6ea..73b981438cc5 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -144,11 +144,8 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) /* * Enable EEH explicitly so that we will do EEH check * while accessing I/O stuff - * - * FIXME: Enable that for PHB3 later */ - if (phb->type == PNV_PHB_IODA1) - eeh_subsystem_enabled = 1; + eeh_subsystem_enabled = 1; /* Save memory bars */ eeh_save_bars(edev); diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c index 3f83e1ae26ac..acd9f7e96678 100644 --- a/arch/powerpc/platforms/powernv/opal-nvram.c +++ b/arch/powerpc/platforms/powernv/opal-nvram.c @@ -65,7 +65,7 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) void __init opal_nvram_init(void) { struct device_node *np; - const u32 *nbytes_p; + const __be32 *nbytes_p; np = of_find_compatible_node(NULL, NULL, "ibm,opal-nvram"); if (np == NULL) @@ -76,7 +76,7 @@ void __init opal_nvram_init(void) of_node_put(np); return; } - nvram_size = *nbytes_p; + nvram_size = be32_to_cpup(nbytes_p); printk(KERN_INFO "OPAL nvram setup, %u bytes\n", nvram_size); of_node_put(np); diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c index 2aa7641aac9b..7d07c7e80ec0 100644 --- a/arch/powerpc/platforms/powernv/opal-rtc.c +++ b/arch/powerpc/platforms/powernv/opal-rtc.c @@ -37,10 +37,12 @@ unsigned long __init opal_get_boot_time(void) struct rtc_time tm; u32 y_m_d; u64 h_m_s_ms; + __be32 __y_m_d; + __be64 __h_m_s_ms; long rc = OPAL_BUSY; while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { - rc = opal_rtc_read(&y_m_d, &h_m_s_ms); + rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); if (rc == OPAL_BUSY_EVENT) opal_poll_events(NULL); else @@ -48,6 +50,8 @@ unsigned long __init opal_get_boot_time(void) } if (rc != OPAL_SUCCESS) 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); return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec); @@ -58,9 +62,11 @@ void opal_get_rtc_time(struct rtc_time *tm) long rc = OPAL_BUSY; u32 y_m_d; u64 h_m_s_ms; + __be32 __y_m_d; + __be64 __h_m_s_ms; while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { - rc = opal_rtc_read(&y_m_d, &h_m_s_ms); + rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); if (rc == OPAL_BUSY_EVENT) opal_poll_events(NULL); else @@ -68,6 +74,8 @@ void opal_get_rtc_time(struct rtc_time *tm) } if (rc != OPAL_SUCCESS) return; + 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 8f3844535fbb..2a03e1e63c7a 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -34,7 +34,7 @@ mtmsrd r12,1; \ LOAD_REG_ADDR(r0,.opal_return); \ mtlr r0; \ - li r0,MSR_DR|MSR_IR; \ + li r0,MSR_DR|MSR_IR|MSR_LE;\ andc r12,r12,r0; \ li r0,token; \ mtspr SPRN_HSRR1,r12; \ @@ -45,6 +45,13 @@ hrfid _STATIC(opal_return) + /* + * Fixup endian on OPAL return... we should be able to simplify + * this by instead converting the below trampoline to a set of + * bytes (always BE) since MSR:LE will end up fixed up as a side + * effect of the rfid. + */ + FIXUP_ENDIAN ld r2,PACATOC(r13); ld r4,8(r1); ld r5,16(r1); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c new file mode 100644 index 000000000000..3ed5c6498324 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -0,0 +1,105 @@ +/* + * PowerNV LPC bus handling. + * + * Copyright 2013 IBM Corp. + * + * 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. + */ + +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/bug.h> +#include <linux/gfp.h> +#include <linux/slab.h> + +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/opal.h> +#include <asm/scom.h> + +/* + * We could probably fit that inside the scom_map_t + * which is a void* after all but it's really too ugly + * so let's kmalloc it for now + */ +struct opal_scom_map { + uint32_t chip; + uint32_t addr; +}; + +static scom_map_t opal_scom_map(struct device_node *dev, u64 reg, u64 count) +{ + struct opal_scom_map *m; + const __be32 *gcid; + + if (!of_get_property(dev, "scom-controller", NULL)) { + pr_err("%s: device %s is not a SCOM controller\n", + __func__, dev->full_name); + return SCOM_MAP_INVALID; + } + gcid = of_get_property(dev, "ibm,chip-id", NULL); + if (!gcid) { + pr_err("%s: device %s has no ibm,chip-id\n", + __func__, dev->full_name); + return SCOM_MAP_INVALID; + } + m = kmalloc(sizeof(struct opal_scom_map), GFP_KERNEL); + if (!m) + return NULL; + m->chip = be32_to_cpup(gcid); + m->addr = reg; + + return (scom_map_t)m; +} + +static void opal_scom_unmap(scom_map_t map) +{ + kfree(map); +} + +static int opal_xscom_err_xlate(int64_t rc) +{ + switch(rc) { + case 0: + return 0; + /* Add more translations if necessary */ + default: + return -EIO; + } +} + +static int opal_scom_read(scom_map_t map, u32 reg, u64 *value) +{ + struct opal_scom_map *m = map; + int64_t rc; + + rc = opal_xscom_read(m->chip, m->addr + reg, (uint64_t *)__pa(value)); + return opal_xscom_err_xlate(rc); +} + +static int opal_scom_write(scom_map_t map, u32 reg, u64 value) +{ + struct opal_scom_map *m = map; + int64_t rc; + + rc = opal_xscom_write(m->chip, m->addr + reg, value); + return opal_xscom_err_xlate(rc); +} + +static const struct scom_controller opal_scom_controller = { + .map = opal_scom_map, + .unmap = opal_scom_unmap, + .read = opal_scom_read, + .write = opal_scom_write +}; + +static int opal_xscom_init(void) +{ + if (firmware_has_feature(FW_FEATURE_OPALv3)) + scom_init(&opal_scom_controller); + return 0; +} +arch_initcall(opal_xscom_init); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 2911abe550f1..09336f0c54c5 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -77,6 +77,7 @@ int __init early_init_dt_scan_opal(unsigned long node, static int __init opal_register_exception_handlers(void) { +#ifdef __BIG_ENDIAN__ u64 glue; if (!(powerpc_firmware_features & FW_FEATURE_OPAL)) @@ -94,6 +95,7 @@ static int __init opal_register_exception_handlers(void) 0, glue); glue += 128; opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue); +#endif return 0; } @@ -164,27 +166,28 @@ void opal_notifier_disable(void) int opal_get_chars(uint32_t vtermno, char *buf, int count) { - s64 len, rc; - u64 evt; + s64 rc; + __be64 evt, len; if (!opal.entry) return -ENODEV; opal_poll_events(&evt); - if ((evt & OPAL_EVENT_CONSOLE_INPUT) == 0) + if ((be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_INPUT) == 0) return 0; - len = count; - rc = opal_console_read(vtermno, &len, buf); + len = cpu_to_be64(count); + rc = opal_console_read(vtermno, &len, buf); if (rc == OPAL_SUCCESS) - return len; + return be64_to_cpu(len); return 0; } int opal_put_chars(uint32_t vtermno, const char *data, int total_len) { int written = 0; + __be64 olen; s64 len, rc; unsigned long flags; - u64 evt; + __be64 evt; if (!opal.entry) return -ENODEV; @@ -199,13 +202,14 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) */ spin_lock_irqsave(&opal_write_lock, flags); if (firmware_has_feature(FW_FEATURE_OPALv2)) { - rc = opal_console_write_buffer_space(vtermno, &len); + rc = opal_console_write_buffer_space(vtermno, &olen); + len = be64_to_cpu(olen); if (rc || len < total_len) { spin_unlock_irqrestore(&opal_write_lock, flags); /* Closed -> drop characters */ if (rc) return total_len; - opal_poll_events(&evt); + opal_poll_events(NULL); return -EAGAIN; } } @@ -216,8 +220,9 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) rc = OPAL_BUSY; while(total_len > 0 && (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) { - len = total_len; - rc = opal_console_write(vtermno, &len, data); + olen = cpu_to_be64(total_len); + rc = opal_console_write(vtermno, &olen, data); + len = be64_to_cpu(olen); /* Closed or other error drop */ if (rc != OPAL_SUCCESS && rc != OPAL_BUSY && @@ -237,7 +242,8 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) */ do opal_poll_events(&evt); - while(rc == OPAL_SUCCESS && (evt & OPAL_EVENT_CONSOLE_OUTPUT)); + while(rc == OPAL_SUCCESS && + (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT)); } spin_unlock_irqrestore(&opal_write_lock, flags); return written; @@ -360,7 +366,7 @@ int opal_machine_check(struct pt_regs *regs) static irqreturn_t opal_interrupt(int irq, void *data) { - uint64_t events; + __be64 events; opal_handle_interrupt(virq_to_hw(irq), &events); @@ -372,7 +378,7 @@ static irqreturn_t opal_interrupt(int irq, void *data) static int __init opal_init(void) { struct device_node *np, *consoles; - const u32 *irqs; + const __be32 *irqs; int rc, i, irqlen; opal_node = of_find_node_by_path("/ibm,opal"); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 307015d9cd99..c639af7d4826 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -466,11 +466,11 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe, struct iommu_table *tbl, - u64 *startp, u64 *endp, bool rm) + __be64 *startp, __be64 *endp, bool rm) { - u64 __iomem *invalidate = rm ? - (u64 __iomem *)pe->tce_inval_reg_phys : - (u64 __iomem *)tbl->it_index; + __be64 __iomem *invalidate = rm ? + (__be64 __iomem *)pe->tce_inval_reg_phys : + (__be64 __iomem *)tbl->it_index; unsigned long start, end, inc; start = __pa(startp); @@ -498,9 +498,9 @@ static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe, mb(); /* Ensure above stores are visible */ while (start <= end) { if (rm) - __raw_rm_writeq(start, invalidate); + __raw_rm_writeq(cpu_to_be64(start), invalidate); else - __raw_writeq(start, invalidate); + __raw_writeq(cpu_to_be64(start), invalidate); start += inc; } @@ -512,12 +512,12 @@ static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe, static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe, struct iommu_table *tbl, - u64 *startp, u64 *endp, bool rm) + __be64 *startp, __be64 *endp, bool rm) { unsigned long start, end, inc; - u64 __iomem *invalidate = rm ? - (u64 __iomem *)pe->tce_inval_reg_phys : - (u64 __iomem *)tbl->it_index; + __be64 __iomem *invalidate = rm ? + (__be64 __iomem *)pe->tce_inval_reg_phys : + (__be64 __iomem *)tbl->it_index; /* We'll invalidate DMA address in PE scope */ start = 0x2ul << 60; @@ -534,15 +534,15 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe, while (start <= end) { if (rm) - __raw_rm_writeq(start, invalidate); + __raw_rm_writeq(cpu_to_be64(start), invalidate); else - __raw_writeq(start, invalidate); + __raw_writeq(cpu_to_be64(start), invalidate); start += inc; } } void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, - u64 *startp, u64 *endp, bool rm) + __be64 *startp, __be64 *endp, bool rm) { struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, tce32_table); @@ -811,8 +811,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, struct irq_data *idata; struct irq_chip *ichip; unsigned int xive_num = hwirq - phb->msi_base; - uint64_t addr64; - uint32_t addr32, data; + __be32 data; int rc; /* No PE assigned ? bail out ... no MSI for you ! */ @@ -836,6 +835,8 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, } if (is_64) { + __be64 addr64; + rc = opal_get_msi_64(phb->opal_id, pe->mve_number, xive_num, 1, &addr64, &data); if (rc) { @@ -843,9 +844,11 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, pci_name(dev), rc); return -EIO; } - msg->address_hi = addr64 >> 32; - msg->address_lo = addr64 & 0xfffffffful; + msg->address_hi = be64_to_cpu(addr64) >> 32; + msg->address_lo = be64_to_cpu(addr64) & 0xfffffffful; } else { + __be32 addr32; + rc = opal_get_msi_32(phb->opal_id, pe->mve_number, xive_num, 1, &addr32, &data); if (rc) { @@ -854,9 +857,9 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev, return -EIO; } msg->address_hi = 0; - msg->address_lo = addr32; + msg->address_lo = be32_to_cpu(addr32); } - msg->data = data; + msg->data = be32_to_cpu(data); /* * Change the IRQ chip for the MSI interrupts on PHB3. @@ -1131,8 +1134,8 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, struct pci_controller *hose; struct pnv_phb *phb; unsigned long size, m32map_off, iomap_off, pemap_off; - const u64 *prop64; - const u32 *prop32; + const __be64 *prop64; + const __be32 *prop32; int len; u64 phb_id; void *aux; @@ -1167,8 +1170,8 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, spin_lock_init(&phb->lock); prop32 = of_get_property(np, "bus-range", &len); if (prop32 && len == 8) { - hose->first_busno = prop32[0]; - hose->last_busno = prop32[1]; + hose->first_busno = be32_to_cpu(prop32[0]); + hose->last_busno = be32_to_cpu(prop32[1]); } else { pr_warn(" Broken <bus-range> on %s\n", np->full_name); hose->first_busno = 0; @@ -1200,7 +1203,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, if (!prop32) phb->ioda.total_pe = 1; else - phb->ioda.total_pe = *prop32; + phb->ioda.total_pe = be32_to_cpup(prop32); phb->ioda.m32_size = resource_size(&hose->mem_resources[0]); /* FW Has already off top 64k of M32 space (MSI space) */ @@ -1310,7 +1313,7 @@ void __init pnv_pci_init_ioda2_phb(struct device_node *np) void __init pnv_pci_init_ioda_hub(struct device_node *np) { struct device_node *phbn; - const u64 *prop64; + const __be64 *prop64; u64 hub_id; pr_info("Probing IODA IO-Hub %s\n", np->full_name); diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index b68db6325c1b..f8b4bd8afb2e 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -99,7 +99,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id, void *tce_mem, u64 tce_size) { struct pnv_phb *phb; - const u64 *prop64; + const __be64 *prop64; u64 phb_id; int64_t rc; static int primary = 1; @@ -178,7 +178,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id, void __init pnv_pci_init_p5ioc2_hub(struct device_node *np) { struct device_node *phbn; - const u64 *prop64; + const __be64 *prop64; u64 hub_id; void *tce_mem; uint64_t tce_per_phb; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 420abe3baab9..921ae673baf3 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -236,7 +236,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb, { s64 rc; u8 fstate; - u16 pcierr; + __be16 pcierr; u32 pe_no; /* @@ -283,16 +283,16 @@ int pnv_pci_cfg_read(struct device_node *dn, break; } case 2: { - u16 v16; + __be16 v16; rc = opal_pci_config_read_half_word(phb->opal_id, bdfn, where, &v16); - *val = (rc == OPAL_SUCCESS) ? v16 : 0xffff; + *val = (rc == OPAL_SUCCESS) ? be16_to_cpu(v16) : 0xffff; break; } case 4: { - u32 v32; + __be32 v32; rc = opal_pci_config_read_word(phb->opal_id, bdfn, where, &v32); - *val = (rc == OPAL_SUCCESS) ? v32 : 0xffffffff; + *val = (rc == OPAL_SUCCESS) ? be32_to_cpu(v32) : 0xffffffff; break; } default: @@ -404,7 +404,7 @@ static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, struct dma_attrs *attrs, bool rm) { u64 proto_tce; - u64 *tcep, *tces; + __be64 *tcep, *tces; u64 rpn; proto_tce = TCE_PCI_READ; // Read allowed @@ -412,11 +412,11 @@ static int pnv_tce_build(struct iommu_table *tbl, long index, long npages, if (direction != DMA_TO_DEVICE) proto_tce |= TCE_PCI_WRITE; - tces = tcep = ((u64 *)tbl->it_base) + index - tbl->it_offset; + tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset; rpn = __pa(uaddr) >> TCE_SHIFT; while (npages--) - *(tcep++) = proto_tce | (rpn++ << TCE_RPN_SHIFT); + *(tcep++) = cpu_to_be64(proto_tce | (rpn++ << TCE_RPN_SHIFT)); /* Some implementations won't cache invalid TCEs and thus may not * need that flush. We'll probably turn it_type into a bit mask @@ -440,12 +440,12 @@ static int pnv_tce_build_vm(struct iommu_table *tbl, long index, long npages, static void pnv_tce_free(struct iommu_table *tbl, long index, long npages, bool rm) { - u64 *tcep, *tces; + __be64 *tcep, *tces; - tces = tcep = ((u64 *)tbl->it_base) + index - tbl->it_offset; + tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset; while (npages--) - *(tcep++) = 0; + *(tcep++) = cpu_to_be64(0); if (tbl->it_type & TCE_PCI_SWINV_FREE) pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm); @@ -512,8 +512,8 @@ static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose) swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info", NULL); if (swinvp) { - tbl->it_busno = swinvp[1]; - tbl->it_index = (unsigned long)ioremap(swinvp[0], 8); + tbl->it_busno = be64_to_cpu(swinvp[1]); + tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8); tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE; } return tbl; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 170dd98629d7..64d3b12e5b6d 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -17,7 +17,7 @@ enum pnv_phb_model { PNV_PHB_MODEL_PHB3, }; -#define PNV_PCI_DIAG_BUF_SIZE 4096 +#define PNV_PCI_DIAG_BUF_SIZE 8192 #define PNV_IODA_PE_DEV (1 << 0) /* PE has single PCI device */ #define PNV_IODA_PE_BUS (1 << 1) /* PE has primary PCI bus */ #define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */ @@ -194,6 +194,6 @@ extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, - u64 *startp, u64 *endp, bool rm); + __be64 *startp, __be64 *endp, bool rm); #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c new file mode 100644 index 000000000000..02db7d73cf8b --- /dev/null +++ b/arch/powerpc/platforms/powernv/rng.c @@ -0,0 +1,122 @@ +/* + * Copyright 2013, Michael Ellerman, IBM Corporation. + * + * 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. + */ + +#define pr_fmt(fmt) "powernv-rng: " fmt + +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/slab.h> +#include <asm/archrandom.h> +#include <asm/io.h> +#include <asm/machdep.h> + + +struct powernv_rng { + void __iomem *regs; + unsigned long mask; +}; + +static DEFINE_PER_CPU(struct powernv_rng *, powernv_rng); + + +static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val) +{ + unsigned long parity; + + /* Calculate the parity of the value */ + asm ("popcntd %0,%1" : "=r" (parity) : "r" (val)); + + /* xor our value with the previous mask */ + val ^= rng->mask; + + /* update the mask based on the parity of this value */ + rng->mask = (rng->mask << 1) | (parity & 1); + + return val; +} + +int powernv_get_random_long(unsigned long *v) +{ + struct powernv_rng *rng; + + rng = get_cpu_var(powernv_rng); + + *v = rng_whiten(rng, in_be64(rng->regs)); + + put_cpu_var(rng); + + return 1; +} +EXPORT_SYMBOL_GPL(powernv_get_random_long); + +static __init void rng_init_per_cpu(struct powernv_rng *rng, + struct device_node *dn) +{ + int chip_id, cpu; + + chip_id = of_get_ibm_chip_id(dn); + if (chip_id == -1) + pr_warn("No ibm,chip-id found for %s.\n", dn->full_name); + + for_each_possible_cpu(cpu) { + if (per_cpu(powernv_rng, cpu) == NULL || + cpu_to_chip_id(cpu) == chip_id) { + per_cpu(powernv_rng, cpu) = rng; + } + } +} + +static __init int rng_create(struct device_node *dn) +{ + struct powernv_rng *rng; + unsigned long val; + + rng = kzalloc(sizeof(*rng), GFP_KERNEL); + if (!rng) + return -ENOMEM; + + rng->regs = of_iomap(dn, 0); + if (!rng->regs) { + kfree(rng); + return -ENXIO; + } + + val = in_be64(rng->regs); + rng->mask = val; + + rng_init_per_cpu(rng, dn); + + pr_info_once("Registering arch random hook.\n"); + + ppc_md.get_random_long = powernv_get_random_long; + + return 0; +} + +static __init int rng_init(void) +{ + struct device_node *dn; + int rc; + + for_each_compatible_node(dn, NULL, "ibm,power-rng") { + rc = rng_create(dn); + if (rc) { + pr_err("Failed creating rng for %s (%d).\n", + dn->full_name, rc); + continue; + } + + /* Create devices for hwrng driver */ + of_platform_device_create(dn, NULL, NULL); + } + + return 0; +} +subsys_initcall(rng_init); diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 6c61ec5ee914..fbccac9cd2dc 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -3,7 +3,7 @@ ccflags-$(CONFIG_PPC_PSERIES_DEBUG) += -DDEBUG obj-y := lpar.o hvCall.o nvram.o reconfig.o \ setup.o iommu.o event_sources.o ras.o \ - firmware.o power.o dlpar.o mobility.o + firmware.o power.o dlpar.o mobility.o rng.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SCANLOG) += scanlog.o obj-$(CONFIG_EEH) += eeh_pseries.o diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c new file mode 100644 index 000000000000..a702f1c08242 --- /dev/null +++ b/arch/powerpc/platforms/pseries/rng.c @@ -0,0 +1,44 @@ +/* + * Copyright 2013, Michael Ellerman, IBM Corporation. + * + * 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. + */ + +#define pr_fmt(fmt) "pseries-rng: " fmt + +#include <linux/kernel.h> +#include <linux/of.h> +#include <asm/archrandom.h> +#include <asm/machdep.h> + + +static int pseries_get_random_long(unsigned long *v) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + if (plpar_hcall(H_RANDOM, retbuf) == H_SUCCESS) { + *v = retbuf[0]; + return 1; + } + + return 0; +} + +static __init int rng_init(void) +{ + struct device_node *dn; + + dn = of_find_compatible_node(NULL, NULL, "ibm,random"); + if (!dn) + return -ENODEV; + + pr_info("Registering arch random hook.\n"); + + ppc_md.get_random_long = pseries_get_random_long; + + return 0; +} +subsys_initcall(rng_init); diff --git a/arch/powerpc/platforms/wsp/scom_smp.c b/arch/powerpc/platforms/wsp/scom_smp.c index b56b70aeb497..268bc899c1f7 100644 --- a/arch/powerpc/platforms/wsp/scom_smp.c +++ b/arch/powerpc/platforms/wsp/scom_smp.c @@ -116,7 +116,14 @@ static int a2_scom_ram(scom_map_t scom, int thread, u32 insn, int extmask) scom_write(scom, SCOM_RAMIC, cmd); - while (!((val = scom_read(scom, SCOM_RAMC)) & mask)) { + for (;;) { + if (scom_read(scom, SCOM_RAMC, &val) != 0) { + pr_err("SCOM error on instruction 0x%08x, thread %d\n", + insn, thread); + return -1; + } + if (val & mask) + break; pr_devel("Waiting on RAMC = 0x%llx\n", val); if (++n == 3) { pr_err("RAMC timeout on instruction 0x%08x, thread %d\n", @@ -151,9 +158,7 @@ static int a2_scom_getgpr(scom_map_t scom, int thread, int gpr, int alt, if (rc) return rc; - *out_gpr = scom_read(scom, SCOM_RAMD); - - return 0; + return scom_read(scom, SCOM_RAMD, out_gpr); } static int a2_scom_getspr(scom_map_t scom, int thread, int spr, u64 *out_spr) @@ -353,7 +358,10 @@ int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, struct device_node *np) pr_devel("Bringing up CPU%d using SCOM...\n", lcpu); - pccr0 = scom_read(scom, SCOM_PCCR0); + if (scom_read(scom, SCOM_PCCR0, &pccr0) != 0) { + printk(KERN_ERR "XSCOM failure readng PCCR0 on CPU%d\n", lcpu); + return -1; + } scom_write(scom, SCOM_PCCR0, pccr0 | SCOM_PCCR0_ENABLE_DEBUG | SCOM_PCCR0_ENABLE_RAM); diff --git a/arch/powerpc/platforms/wsp/scom_wsp.c b/arch/powerpc/platforms/wsp/scom_wsp.c index 4052e2259f30..54172c4a8a64 100644 --- a/arch/powerpc/platforms/wsp/scom_wsp.c +++ b/arch/powerpc/platforms/wsp/scom_wsp.c @@ -50,18 +50,22 @@ static void wsp_scom_unmap(scom_map_t map) iounmap((void *)map); } -static u64 wsp_scom_read(scom_map_t map, u32 reg) +static int wsp_scom_read(scom_map_t map, u32 reg, u64 *value) { u64 __iomem *addr = (u64 __iomem *)map; - return in_be64(addr + reg); + *value = in_be64(addr + reg); + + return 0; } -static void wsp_scom_write(scom_map_t map, u32 reg, u64 value) +static int wsp_scom_write(scom_map_t map, u32 reg, u64 value) { u64 __iomem *addr = (u64 __iomem *)map; - return out_be64(addr + reg, value); + out_be64(addr + reg, value); + + return 0; } static const struct scom_controller wsp_scom_controller = { diff --git a/arch/powerpc/platforms/wsp/wsp.c b/arch/powerpc/platforms/wsp/wsp.c index d25cc96c21b8..ddb6efe88914 100644 --- a/arch/powerpc/platforms/wsp/wsp.c +++ b/arch/powerpc/platforms/wsp/wsp.c @@ -89,6 +89,7 @@ void wsp_halt(void) struct device_node *dn; struct device_node *mine; struct device_node *me; + int rc; me = of_get_cpu_node(smp_processor_id(), NULL); mine = scom_find_parent(me); @@ -101,15 +102,15 @@ void wsp_halt(void) /* read-modify-write it so the HW probe does not get * confused */ - val = scom_read(m, 0); - val |= 1; - scom_write(m, 0, val); + rc = scom_read(m, 0, &val); + if (rc == 0) + scom_write(m, 0, val | 1); scom_unmap(m); } m = scom_map(mine, 0, 1); - val = scom_read(m, 0); - val |= 1; - scom_write(m, 0, val); + rc = scom_read(m, 0, &val); + if (rc == 0) + scom_write(m, 0, val | 1); /* should never return */ scom_unmap(m); } diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig index ab4cb5476472..13ec968be4c7 100644 --- a/arch/powerpc/sysdev/Kconfig +++ b/arch/powerpc/sysdev/Kconfig @@ -28,7 +28,7 @@ config PPC_SCOM config SCOM_DEBUGFS bool "Expose SCOM controllers via debugfs" - depends on PPC_SCOM + depends on PPC_SCOM && DEBUG_FS default n config GE_FPGA diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 1be54faf60dd..bdcb8588e492 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1088,8 +1088,14 @@ static int mpic_host_map(struct irq_domain *h, unsigned int virq, * is done here. */ if (!mpic_is_ipi(mpic, hw) && (mpic->flags & MPIC_NO_RESET)) { + int cpu; + + preempt_disable(); + cpu = mpic_processor_id(mpic); + preempt_enable(); + mpic_set_vector(virq, hw); - mpic_set_destination(virq, mpic_processor_id(mpic)); + mpic_set_destination(virq, cpu); mpic_irq_set_priority(virq, 8); } diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c index 9193e12df695..3963d995648a 100644 --- a/arch/powerpc/sysdev/scom.c +++ b/arch/powerpc/sysdev/scom.c @@ -53,7 +53,7 @@ scom_map_t scom_map_device(struct device_node *dev, int index) { struct device_node *parent; unsigned int cells, size; - const u32 *prop; + const __be32 *prop, *sprop; u64 reg, cnt; scom_map_t ret; @@ -62,12 +62,24 @@ scom_map_t scom_map_device(struct device_node *dev, int index) if (parent == NULL) return 0; - prop = of_get_property(parent, "#scom-cells", NULL); - cells = prop ? *prop : 1; - + /* + * We support "scom-reg" properties for adding scom registers + * to a random device-tree node with an explicit scom-parent + * + * We also support the simple "reg" property if the device is + * a direct child of a scom controller. + * + * In case both exist, "scom-reg" takes precedence. + */ prop = of_get_property(dev, "scom-reg", &size); + sprop = of_get_property(parent, "#scom-cells", NULL); + if (!prop && parent == dev->parent) { + prop = of_get_property(dev, "reg", &size); + sprop = of_get_property(parent, "#address-cells", NULL); + } if (!prop) - return 0; + return NULL; + cells = sprop ? be32_to_cpup(sprop) : 1; size >>= 2; if (index >= (size / (2*cells))) @@ -137,8 +149,7 @@ static int scom_val_get(void *data, u64 *val) if (!scom_map_ok(ent->map)) return -EFAULT; - *val = scom_read(ent->map, 0); - return 0; + return scom_read(ent->map, 0, val); } DEFINE_SIMPLE_ATTRIBUTE(scom_val_fops, scom_val_get, scom_val_set, "0x%llx\n"); @@ -169,7 +180,7 @@ static int scom_debug_init_one(struct dentry *root, struct device_node *dn, debugfs_create_file("addr", 0600, dir, ent, &scom_addr_fops); debugfs_create_file("value", 0600, dir, ent, &scom_val_fops); - debugfs_create_blob("path", 0400, dir, &ent->blob); + debugfs_create_blob("devspec", 0400, dir, &ent->blob); return 0; } @@ -185,8 +196,13 @@ static int scom_debug_init(void) return -1; i = rc = 0; - for_each_node_with_property(dn, "scom-controller") - rc |= scom_debug_init_one(root, dn, i++); + for_each_node_with_property(dn, "scom-controller") { + int id = of_get_ibm_chip_id(dn); + if (id == -1) + id = i; + rc |= scom_debug_init_one(root, dn, id); + i++; + } return rc; } diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c index 39d72212655e..3c6ee1b64e5d 100644 --- a/arch/powerpc/sysdev/xics/ics-opal.c +++ b/arch/powerpc/sysdev/xics/ics-opal.c @@ -112,6 +112,7 @@ static int ics_opal_set_affinity(struct irq_data *d, bool force) { unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); + __be16 oserver; int16_t server; int8_t priority; int64_t rc; @@ -120,13 +121,13 @@ static int ics_opal_set_affinity(struct irq_data *d, if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS) return -1; - rc = opal_get_xive(hw_irq, &server, &priority); + rc = opal_get_xive(hw_irq, &oserver, &priority); if (rc != OPAL_SUCCESS) { - pr_err("%s: opal_set_xive(irq=%d [hw 0x%x] server=%x)" - " error %lld\n", - __func__, d->irq, hw_irq, server, rc); + pr_err("%s: opal_get_xive(irq=%d [hw 0x%x]) error %lld\n", + __func__, d->irq, hw_irq, rc); return -1; } + server = be16_to_cpu(oserver); wanted_server = xics_get_irq_server(d->irq, cpumask, 1); if (wanted_server < 0) { @@ -181,7 +182,7 @@ static int ics_opal_map(struct ics *ics, unsigned int virq) { unsigned int hw_irq = (unsigned int)virq_to_hw(virq); int64_t rc; - int16_t server; + __be16 server; int8_t priority; if (WARN_ON(hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)) @@ -201,7 +202,7 @@ static int ics_opal_map(struct ics *ics, unsigned int virq) static void ics_opal_mask_unknown(struct ics *ics, unsigned long vec) { int64_t rc; - int16_t server; + __be16 server; int8_t priority; /* Check if HAL knows about this interrupt */ @@ -215,14 +216,14 @@ static void ics_opal_mask_unknown(struct ics *ics, unsigned long vec) static long ics_opal_get_server(struct ics *ics, unsigned long vec) { int64_t rc; - int16_t server; + __be16 server; int8_t priority; /* Check if HAL knows about this interrupt */ rc = opal_get_xive(vec, &server, &priority); if (rc != OPAL_SUCCESS) return -1; - return ics_opal_unmangle_server(server); + return ics_opal_unmangle_server(be16_to_cpu(server)); } int __init ics_opal_init(void) |
