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
select OLD_SIGACTION if PPC32
select HAVE_DEBUG_STACKOVERFLOW
+config GENERIC_CSUM
+ def_bool CPU_LITTLE_ENDIAN
+
config EARLY_PRINTK
bool
default y
default "0x00000000"
endif
+config ARCH_RANDOM
+ def_bool n
+
source "net/Kconfig"
source "drivers/Kconfig"
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
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) $(AR)
endif
LDFLAGS_vmlinux-y := -Bstatic
CFLAGS-$(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)
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
--- /dev/null
+#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 */
* 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);
/*
return sum;
#endif
}
+
+#endif
#endif /* __KERNEL__ */
#endif
struct hvsi_header {
uint8_t type;
uint8_t len;
- uint16_t seqno;
+ __be16 seqno;
} __attribute__((packed));
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));
/*
* 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>
/* 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; \
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" \
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; \
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" \
}
#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; \
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" \
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)
{
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__ */
/*
long index);
void (*tce_flush)(struct iommu_table *tbl);
+ /* _rm versions are for real mode use only */
+ int (*tce_build_rm)(struct iommu_table *tbl,
+ long index,
+ long npages,
+ unsigned long uaddr,
+ enum dma_data_direction direction,
+ struct dma_attrs *attrs);
+ void (*tce_free_rm)(struct iommu_table *tbl,
+ long index,
+ long npages);
+ void (*tce_flush_rm)(struct iommu_table *tbl);
+
void __iomem * (*ioremap)(phys_addr_t addr, unsigned long size,
unsigned long flags, void *caller);
void (*iounmap)(volatile void __iomem *token);
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);
#ifndef __ASSEMBLY__
struct hash_pte {
- unsigned long v;
- unsigned long r;
+ __be64 v;
+ __be64 r;
};
extern struct hash_pte *htab_address;
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 {
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,
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,
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);
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);
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);
hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
}
+struct page *realmode_pfn_to_page(unsigned long pfn);
+
static inline char *get_hpte_slot_array(pmd_t *pmdp)
{
/*
#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
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))))
#define REST_8GPRS(n, base) REST_4GPRS(n, base); REST_4GPRS(n+4, base)
#define REST_10GPRS(n, base) REST_8GPRS(n, base); REST_2GPRS(n+8, base)
-#define SAVE_FPR(n, base) stfd n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#define SAVE_FPR(n, base) stfd n,8*TS_FPRWIDTH*(n)(base)
#define SAVE_2FPRS(n, base) SAVE_FPR(n, base); SAVE_FPR(n+1, base)
#define SAVE_4FPRS(n, base) SAVE_2FPRS(n, base); SAVE_2FPRS(n+2, base)
#define SAVE_8FPRS(n, base) SAVE_4FPRS(n, base); SAVE_4FPRS(n+4, base)
#define SAVE_16FPRS(n, base) SAVE_8FPRS(n, base); SAVE_8FPRS(n+8, base)
#define SAVE_32FPRS(n, base) SAVE_16FPRS(n, base); SAVE_16FPRS(n+16, base)
-#define REST_FPR(n, base) lfd n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#define REST_FPR(n, base) lfd n,8*TS_FPRWIDTH*(n)(base)
#define REST_2FPRS(n, base) REST_FPR(n, base); REST_FPR(n+1, base)
#define REST_4FPRS(n, base) REST_2FPRS(n, base); REST_2FPRS(n+2, base)
#define REST_8FPRS(n, base) REST_4FPRS(n, base); REST_4FPRS(n+4, base)
#define REST_16FPRS(n, base) REST_8FPRS(n, base); REST_8FPRS(n+8, base)
#define REST_32FPRS(n, base) REST_16FPRS(n, base); REST_16FPRS(n+16, base)
-#define SAVE_VR(n,b,base) li b,THREAD_VR0+(16*(n)); stvx n,base,b
+#define SAVE_VR(n,b,base) li b,16*(n); stvx n,base,b
#define SAVE_2VRS(n,b,base) SAVE_VR(n,b,base); SAVE_VR(n+1,b,base)
#define SAVE_4VRS(n,b,base) SAVE_2VRS(n,b,base); SAVE_2VRS(n+2,b,base)
#define SAVE_8VRS(n,b,base) SAVE_4VRS(n,b,base); SAVE_4VRS(n+4,b,base)
#define SAVE_16VRS(n,b,base) SAVE_8VRS(n,b,base); SAVE_8VRS(n+8,b,base)
#define SAVE_32VRS(n,b,base) SAVE_16VRS(n,b,base); SAVE_16VRS(n+16,b,base)
-#define REST_VR(n,b,base) li b,THREAD_VR0+(16*(n)); lvx n,base,b
+#define REST_VR(n,b,base) li b,16*(n); lvx n,base,b
#define REST_2VRS(n,b,base) REST_VR(n,b,base); REST_VR(n+1,b,base)
#define REST_4VRS(n,b,base) REST_2VRS(n,b,base); REST_2VRS(n+2,b,base)
#define REST_8VRS(n,b,base) REST_4VRS(n,b,base); REST_4VRS(n+4,b,base)
#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)
-/* Save/restore FPRs, VRs and VSRs from their checkpointed backups in
- * thread_struct:
- */
-#define SAVE_FPR_TRANSACT(n, base) stfd n,THREAD_TRANSACT_FPR0+ \
- 8*TS_FPRWIDTH*(n)(base)
-#define SAVE_2FPRS_TRANSACT(n, base) SAVE_FPR_TRANSACT(n, base); \
- SAVE_FPR_TRANSACT(n+1, base)
-#define SAVE_4FPRS_TRANSACT(n, base) SAVE_2FPRS_TRANSACT(n, base); \
- SAVE_2FPRS_TRANSACT(n+2, base)
-#define SAVE_8FPRS_TRANSACT(n, base) SAVE_4FPRS_TRANSACT(n, base); \
- SAVE_4FPRS_TRANSACT(n+4, base)
-#define SAVE_16FPRS_TRANSACT(n, base) SAVE_8FPRS_TRANSACT(n, base); \
- SAVE_8FPRS_TRANSACT(n+8, base)
-#define SAVE_32FPRS_TRANSACT(n, base) SAVE_16FPRS_TRANSACT(n, base); \
- SAVE_16FPRS_TRANSACT(n+16, base)
-
-#define REST_FPR_TRANSACT(n, base) lfd n,THREAD_TRANSACT_FPR0+ \
- 8*TS_FPRWIDTH*(n)(base)
-#define REST_2FPRS_TRANSACT(n, base) REST_FPR_TRANSACT(n, base); \
- REST_FPR_TRANSACT(n+1, base)
-#define REST_4FPRS_TRANSACT(n, base) REST_2FPRS_TRANSACT(n, base); \
- REST_2FPRS_TRANSACT(n+2, base)
-#define REST_8FPRS_TRANSACT(n, base) REST_4FPRS_TRANSACT(n, base); \
- REST_4FPRS_TRANSACT(n+4, base)
-#define REST_16FPRS_TRANSACT(n, base) REST_8FPRS_TRANSACT(n, base); \
- REST_8FPRS_TRANSACT(n+8, base)
-#define REST_32FPRS_TRANSACT(n, base) REST_16FPRS_TRANSACT(n, base); \
- REST_16FPRS_TRANSACT(n+16, base)
-
-
-#define SAVE_VR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VR0+(16*(n)); \
- stvx n,b,base
-#define SAVE_2VRS_TRANSACT(n,b,base) SAVE_VR_TRANSACT(n,b,base); \
- SAVE_VR_TRANSACT(n+1,b,base)
-#define SAVE_4VRS_TRANSACT(n,b,base) SAVE_2VRS_TRANSACT(n,b,base); \
- SAVE_2VRS_TRANSACT(n+2,b,base)
-#define SAVE_8VRS_TRANSACT(n,b,base) SAVE_4VRS_TRANSACT(n,b,base); \
- SAVE_4VRS_TRANSACT(n+4,b,base)
-#define SAVE_16VRS_TRANSACT(n,b,base) SAVE_8VRS_TRANSACT(n,b,base); \
- SAVE_8VRS_TRANSACT(n+8,b,base)
-#define SAVE_32VRS_TRANSACT(n,b,base) SAVE_16VRS_TRANSACT(n,b,base); \
- SAVE_16VRS_TRANSACT(n+16,b,base)
-
-#define REST_VR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VR0+(16*(n)); \
- lvx n,b,base
-#define REST_2VRS_TRANSACT(n,b,base) REST_VR_TRANSACT(n,b,base); \
- REST_VR_TRANSACT(n+1,b,base)
-#define REST_4VRS_TRANSACT(n,b,base) REST_2VRS_TRANSACT(n,b,base); \
- REST_2VRS_TRANSACT(n+2,b,base)
-#define REST_8VRS_TRANSACT(n,b,base) REST_4VRS_TRANSACT(n,b,base); \
- REST_4VRS_TRANSACT(n+4,b,base)
-#define REST_16VRS_TRANSACT(n,b,base) REST_8VRS_TRANSACT(n,b,base); \
- REST_8VRS_TRANSACT(n+8,b,base)
-#define REST_32VRS_TRANSACT(n,b,base) REST_16VRS_TRANSACT(n,b,base); \
- REST_16VRS_TRANSACT(n+16,b,base)
-
-
-#define SAVE_VSR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VSR0+(16*(n)); \
- STXVD2X(n,R##base,R##b)
-#define SAVE_2VSRS_TRANSACT(n,b,base) SAVE_VSR_TRANSACT(n,b,base); \
- SAVE_VSR_TRANSACT(n+1,b,base)
-#define SAVE_4VSRS_TRANSACT(n,b,base) SAVE_2VSRS_TRANSACT(n,b,base); \
- SAVE_2VSRS_TRANSACT(n+2,b,base)
-#define SAVE_8VSRS_TRANSACT(n,b,base) SAVE_4VSRS_TRANSACT(n,b,base); \
- SAVE_4VSRS_TRANSACT(n+4,b,base)
-#define SAVE_16VSRS_TRANSACT(n,b,base) SAVE_8VSRS_TRANSACT(n,b,base); \
- SAVE_8VSRS_TRANSACT(n+8,b,base)
-#define SAVE_32VSRS_TRANSACT(n,b,base) SAVE_16VSRS_TRANSACT(n,b,base); \
- SAVE_16VSRS_TRANSACT(n+16,b,base)
-
-#define REST_VSR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VSR0+(16*(n)); \
- LXVD2X(n,R##base,R##b)
-#define REST_2VSRS_TRANSACT(n,b,base) REST_VSR_TRANSACT(n,b,base); \
- REST_VSR_TRANSACT(n+1,b,base)
-#define REST_4VSRS_TRANSACT(n,b,base) REST_2VSRS_TRANSACT(n,b,base); \
- REST_2VSRS_TRANSACT(n+2,b,base)
-#define REST_8VSRS_TRANSACT(n,b,base) REST_4VSRS_TRANSACT(n,b,base); \
- REST_4VSRS_TRANSACT(n+4,b,base)
-#define REST_16VSRS_TRANSACT(n,b,base) REST_8VSRS_TRANSACT(n,b,base); \
- REST_8VSRS_TRANSACT(n+8,b,base)
-#define REST_32VSRS_TRANSACT(n,b,base) REST_16VSRS_TRANSACT(n,b,base); \
- REST_16VSRS_TRANSACT(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,THREAD_VSR0+(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,THREAD_VSR0+(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)
#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 */
#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
unsigned long seg;
} mm_segment_t;
-#define TS_FPROFFSET 0
-#define TS_VSRLOWOFFSET 1
-#define TS_FPR(i) fpr[i][TS_FPROFFSET]
-#define TS_TRANS_FPR(i) transact_fpr[i][TS_FPROFFSET]
+#define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET]
+#define TS_TRANS_FPR(i) transact_fp.fpr[i][TS_FPROFFSET]
+
+/* FP and VSX 0-31 register set */
+struct thread_fp_state {
+ u64 fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
+ u64 fpscr; /* Floating point status */
+};
+
+/* Complete AltiVec register set including VSCR */
+struct thread_vr_state {
+ vector128 vr[32] __attribute__((aligned(16)));
+ vector128 vscr __attribute__((aligned(16)));
+};
struct thread_struct {
unsigned long ksp; /* Kernel stack pointer */
unsigned long dvc2;
#endif
#endif
- /* FP and VSX 0-31 register set */
- double fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
- struct {
-
- unsigned int pad;
- unsigned int val; /* Floating point status */
- } fpscr;
+ struct thread_fp_state fp_state;
+ struct thread_fp_state *fp_save_area;
int fpexc_mode; /* floating-point exception mode */
unsigned int align_ctl; /* alignment handling control */
#ifdef CONFIG_PPC64
struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */
unsigned long trap_nr; /* last trap # on this thread */
#ifdef CONFIG_ALTIVEC
- /* Complete AltiVec register set */
- vector128 vr[32] __attribute__((aligned(16)));
- /* AltiVec status */
- vector128 vscr __attribute__((aligned(16)));
+ struct thread_vr_state vr_state;
+ struct thread_vr_state *vr_save_area;
unsigned long vrsave;
int used_vr; /* set if process has used altivec */
#endif /* CONFIG_ALTIVEC */
* transact_fpr[] is the new set of transactional values.
* VRs work the same way.
*/
- double transact_fpr[32][TS_FPRWIDTH];
- struct {
- unsigned int pad;
- unsigned int val; /* Floating point status */
- } transact_fpscr;
- vector128 transact_vr[32] __attribute__((aligned(16)));
- vector128 transact_vscr __attribute__((aligned(16)));
+ struct thread_fp_state transact_fp;
+ struct thread_vr_state transact_vr;
unsigned long transact_vrsave;
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
.ksp = INIT_SP, \
.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
.fs = KERNEL_DS, \
- .fpr = {{0}}, \
- .fpscr = { .val = 0, }, \
.fpexc_mode = 0, \
.ppr = INIT_PPR, \
}
extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr);
extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
+extern void load_fp_state(struct thread_fp_state *fp);
+extern void store_fp_state(struct thread_fp_state *fp);
+extern void load_vr_state(struct thread_vr_state *vr);
+extern void store_vr_state(struct thread_vr_state *vr);
+
static inline unsigned int __unpack_fe01(unsigned long msr_bits)
{
return ((msr_bits & MSR_FE0) >> 10) | ((msr_bits & MSR_FE1) >> 8);
#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)
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;
* 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;
}
/**
* @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__ */
#define FP_EX_DIVZERO (1 << (31 - 5))
#define FP_EX_INEXACT (1 << (31 - 6))
-#define __FPU_FPSCR (current->thread.fpscr.val)
+#define __FPU_FPSCR (current->thread.fp_state.fpscr)
/* We only actually write to the destination register
* if exceptions signalled (if any) will not trap.
#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
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);
#include <linux/kernel.h>
#include <asm/asm-compat.h>
+#ifdef __BIG_ENDIAN__
+
struct word_at_a_time {
const unsigned long high_bits, low_bits;
};
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 */
* 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 */
/* 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
#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,
return -EFAULT;
return 1; /* exception handled and fixed up */
}
+#endif
#ifdef CONFIG_SPE
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];
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;
}
}
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[reg - 32];
+ 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) {
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;
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;
/* 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
*/
if (cpu_has_feature(CPU_FTR_PPC_LE))
swiz = 7;
+#endif
}
/* DAR has the operand effective address */
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;
* 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 */
/* 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);
* 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.dd = current->thread.TS_FPR(reg);
+ data.ll = current->thread.TS_FPR(reg);
if (flags & S) {
/* Single-precision FP store requires conversion... */
#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;
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;
}
}
#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;
/* 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)
- current->thread.TS_FPR(reg) = data.dd;
+ current->thread.TS_FPR(reg) = data.ll;
else
regs->gpr[reg] = data.ll;
DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0]));
#endif
DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode));
- DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0]));
- DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr));
+ DEFINE(THREAD_FPSTATE, offsetof(struct thread_struct, fp_state));
+ DEFINE(THREAD_FPSAVEAREA, offsetof(struct thread_struct, fp_save_area));
+ DEFINE(FPSTATE_FPSCR, offsetof(struct thread_fp_state, fpscr));
#ifdef CONFIG_ALTIVEC
- DEFINE(THREAD_VR0, offsetof(struct thread_struct, vr[0]));
+ DEFINE(THREAD_VRSTATE, offsetof(struct thread_struct, vr_state));
+ DEFINE(THREAD_VRSAVEAREA, offsetof(struct thread_struct, vr_save_area));
DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave));
- DEFINE(THREAD_VSCR, offsetof(struct thread_struct, vscr));
DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr));
+ DEFINE(VRSTATE_VSCR, offsetof(struct thread_vr_state, vscr));
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
- DEFINE(THREAD_VSR0, offsetof(struct thread_struct, fpr));
DEFINE(THREAD_USED_VSR, offsetof(struct thread_struct, used_vsr));
#endif /* CONFIG_VSX */
#ifdef CONFIG_PPC64
DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr));
DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr));
DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
- DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct,
- transact_vr[0]));
- DEFINE(THREAD_TRANSACT_VSCR, offsetof(struct thread_struct,
- transact_vscr));
+ DEFINE(THREAD_TRANSACT_VRSTATE, offsetof(struct thread_struct,
+ transact_vr));
DEFINE(THREAD_TRANSACT_VRSAVE, offsetof(struct thread_struct,
transact_vrsave));
- DEFINE(THREAD_TRANSACT_FPR0, offsetof(struct thread_struct,
- transact_fpr[0]));
- DEFINE(THREAD_TRANSACT_FPSCR, offsetof(struct thread_struct,
- transact_fpscr));
-#ifdef CONFIG_VSX
- DEFINE(THREAD_TRANSACT_VSR0, offsetof(struct thread_struct,
- transact_fpr[0]));
-#endif
+ DEFINE(THREAD_TRANSACT_FPSTATE, offsetof(struct thread_struct,
+ transact_fp));
/* Local pt_regs on stack for Transactional Memory funcs. */
DEFINE(TM_FRAME_SIZE, STACK_FRAME_OVERHEAD +
sizeof(struct pt_regs) + 16);
/* 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:
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.
pe->addr, pe->phb->global_number);
dump_stack();
+ eeh_send_failure_event(pe);
+
return 1;
dn_unlock:
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 */
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 */
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 */
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
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
2: REST_32VSRS(n,c,base); \
3:
-#define __REST_32FPVSRS_TRANSACT(n,c,base) \
-BEGIN_FTR_SECTION \
- b 2f; \
-END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
- REST_32FPRS_TRANSACT(n,base); \
- b 3f; \
-2: REST_32VSRS_TRANSACT(n,c,base); \
-3:
-
#define __SAVE_32FPVSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
3:
#else
#define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base)
-#define __REST_32FPVSRS_TRANSACT(n,b,base) REST_32FPRS(n, base)
#define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base)
#endif
#define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
-#define REST_32FPVSRS_TRANSACT(n,c,base) \
- __REST_32FPVSRS_TRANSACT(n,__REG_##c,__REG_##base)
#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Wrapper to call load_up_fpu from C.
- * void do_load_up_fpu(struct pt_regs *regs);
- */
-_GLOBAL(do_load_up_fpu)
- mflr r0
- std r0, 16(r1)
- stdu r1, -112(r1)
-
- subi r6, r3, STACK_FRAME_OVERHEAD
- /* load_up_fpu expects r12=MSR, r13=PACA, and returns
- * with r12 = new MSR.
- */
- ld r12,_MSR(r6)
- GET_PACA(r13)
-
- bl load_up_fpu
- std r12,_MSR(r6)
-
- ld r0, 112+16(r1)
- addi r1, r1, 112
- mtlr r0
- blr
-
-
/* void do_load_up_transact_fpu(struct thread_struct *thread)
*
* This is similar to load_up_fpu but for the transactional version of the FP
SYNC
MTMSRD(r5)
- lfd fr0,THREAD_TRANSACT_FPSCR(r3)
+ addi r7,r3,THREAD_TRANSACT_FPSTATE
+ lfd fr0,FPSTATE_FPSCR(r7)
MTFSF_L(fr0)
- REST_32FPVSRS_TRANSACT(0, R4, R3)
+ REST_32FPVSRS(0, R4, R7)
/* FP/VSX off again */
MTMSRD(r6)
blr
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+/*
+ * Load state from memory into FP registers including FPSCR.
+ * Assumes the caller has enabled FP in the MSR.
+ */
+_GLOBAL(load_fp_state)
+ lfd fr0,FPSTATE_FPSCR(r3)
+ MTFSF_L(fr0)
+ REST_32FPVSRS(0, R4, R3)
+ blr
+
+/*
+ * Store FP state into memory, including FPSCR
+ * Assumes the caller has enabled FP in the MSR.
+ */
+_GLOBAL(store_fp_state)
+ SAVE_32FPVSRS(0, R4, R3)
+ mffs fr0
+ stfd fr0,FPSTATE_FPSCR(r3)
+ blr
+
/*
* This task wants to use the FPU now.
* On UP, disable FP for the task which had the FPU previously,
beq 1f
toreal(r4)
addi r4,r4,THREAD /* want last_task_used_math->thread */
- SAVE_32FPVSRS(0, R5, R4)
+ addi r8,r4,THREAD_FPSTATE
+ SAVE_32FPVSRS(0, R5, R8)
mffs fr0
- stfd fr0,THREAD_FPSCR(r4)
+ stfd fr0,FPSTATE_FPSCR(r8)
PPC_LL r5,PT_REGS(r4)
toreal(r5)
PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
#endif /* CONFIG_SMP */
/* enable use of FP after return */
#ifdef CONFIG_PPC32
- mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */
+ mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */
lwz r4,THREAD_FPEXC_MODE(r5)
ori r9,r9,MSR_FP /* enable FP for current */
or r9,r9,r4
or r12,r12,r4
std r12,_MSR(r1)
#endif
- lfd fr0,THREAD_FPSCR(r5)
+ addi r7,r5,THREAD_FPSTATE
+ lfd fr0,FPSTATE_FPSCR(r7)
MTFSF_L(fr0)
- REST_32FPVSRS(0, R4, R5)
+ REST_32FPVSRS(0, R4, R7)
#ifndef CONFIG_SMP
subi r4,r5,THREAD
fromreal(r4)
PPC_LCMPI 0,r3,0
beqlr- /* if no previous owner, done */
addi r3,r3,THREAD /* want THREAD of task */
+ PPC_LL r6,THREAD_FPSAVEAREA(r3)
PPC_LL r5,PT_REGS(r3)
- PPC_LCMPI 0,r5,0
- SAVE_32FPVSRS(0, R4 ,R3)
+ PPC_LCMPI 0,r6,0
+ bne 2f
+ addi r6,r3,THREAD_FPSTATE
+2: PPC_LCMPI 0,r5,0
+ SAVE_32FPVSRS(0, R4, R6)
mffs fr0
- stfd fr0,THREAD_FPSCR(r3)
+ stfd fr0,FPSTATE_FPSCR(r6)
beq 1f
PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
li r3,MSR_FP|MSR_FE0|MSR_FE1
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)) {
_GLOBAL(__start)
/* NOP this out unconditionally */
BEGIN_FTR_SECTION
+ FIXUP_ENDIAN
b .__start_initialization_multiplatform
END_FTR_SECTION(0, 1)
*/
.globl __secondary_hold
__secondary_hold:
+ FIXUP_ENDIAN
#ifndef CONFIG_PPC_BOOK3E
mfmsr r24
ori r24,r24,MSR_RI
* as SCOM before entry).
*/
_GLOBAL(generic_secondary_smp_init)
+ FIXUP_ENDIAN
mr r24,r3
mr r25,r4
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", },
or r4,r4,r7 # LSW |= t2
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.
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. */
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,
*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);
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;
PAGE_SIZE, limit));
}
-static struct lppaca *new_lppaca(int cpu)
+static struct lppaca * __init new_lppaca(int cpu)
{
struct lppaca *lp;
return lp;
}
-static void free_lppacas(void)
+static void __init free_lppacas(void)
{
long new_size = 0, nr;
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);
#ifdef CONFIG_PPC_FPU
EXPORT_SYMBOL(giveup_fpu);
+EXPORT_SYMBOL(load_fp_state);
+EXPORT_SYMBOL(store_fp_state);
#endif
#ifdef CONFIG_ALTIVEC
EXPORT_SYMBOL(giveup_altivec);
+EXPORT_SYMBOL(load_vr_state);
+EXPORT_SYMBOL(store_vr_state);
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
EXPORT_SYMBOL(giveup_vsx);
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);
p->thread.ptrace_bps[0] = NULL;
#endif
+ p->thread.fp_save_area = NULL;
+#ifdef CONFIG_ALTIVEC
+ p->thread.vr_save_area = NULL;
+#endif
+
#ifdef CONFIG_PPC_STD_MMU_64
if (mmu_has_feature(MMU_FTR_SLB)) {
unsigned long sp_vsid;
#ifdef CONFIG_VSX
current->thread.used_vsr = 0;
#endif
- memset(current->thread.fpr, 0, sizeof(current->thread.fpr));
- current->thread.fpscr.val = 0;
+ memset(¤t->thread.fp_state, 0, sizeof(current->thread.fp_state));
+ current->thread.fp_save_area = NULL;
#ifdef CONFIG_ALTIVEC
- memset(current->thread.vr, 0, sizeof(current->thread.vr));
- memset(¤t->thread.vscr, 0, sizeof(current->thread.vscr));
- current->thread.vscr.u[3] = 0x00010000; /* Java mode disabled */
+ memset(¤t->thread.vr_state, 0, sizeof(current->thread.vr_state));
+ current->thread.vr_state.vscr.u[3] = 0x00010000; /* Java mode disabled */
+ current->thread.vr_save_area = NULL;
current->thread.vrsave = 0;
current->thread.used_vr = 0;
#endif /* CONFIG_ALTIVEC */
{
ihandle root;
prom_arg_t ret;
- __be32 *cores;
+ u32 cores;
+ unsigned char *ptcores;
root = call_prom("open", 1, 1, ADDR("/"));
if (root != 0) {
* (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 */
void *kbuf, void __user *ubuf)
{
#ifdef CONFIG_VSX
- double buf[33];
+ u64 buf[33];
int i;
#endif
flush_fp_to_thread(target);
/* copy to local buffer then write that out */
for (i = 0; i < 32 ; i++)
buf[i] = target->thread.TS_FPR(i);
- memcpy(&buf[32], &target->thread.fpscr, sizeof(double));
+ buf[32] = target->thread.fp_state.fpscr;
return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
#else
- BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
- offsetof(struct thread_struct, TS_FPR(32)));
+ BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+ offsetof(struct thread_fp_state, fpr[32][0]));
return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpr, 0, -1);
+ &target->thread.fp_state, 0, -1);
#endif
}
const void *kbuf, const void __user *ubuf)
{
#ifdef CONFIG_VSX
- double buf[33];
+ u64 buf[33];
int i;
#endif
flush_fp_to_thread(target);
return i;
for (i = 0; i < 32 ; i++)
target->thread.TS_FPR(i) = buf[i];
- memcpy(&target->thread.fpscr, &buf[32], sizeof(double));
+ target->thread.fp_state.fpscr = buf[32];
return 0;
#else
- BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
- offsetof(struct thread_struct, TS_FPR(32)));
+ BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+ offsetof(struct thread_fp_state, fpr[32][0]));
return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpr, 0, -1);
+ &target->thread.fp_state, 0, -1);
#endif
}
flush_altivec_to_thread(target);
- BUILD_BUG_ON(offsetof(struct thread_struct, vscr) !=
- offsetof(struct thread_struct, vr[32]));
+ BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+ offsetof(struct thread_vr_state, vr[32]));
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
- &target->thread.vr, 0,
+ &target->thread.vr_state, 0,
33 * sizeof(vector128));
if (!ret) {
/*
flush_altivec_to_thread(target);
- BUILD_BUG_ON(offsetof(struct thread_struct, vscr) !=
- offsetof(struct thread_struct, vr[32]));
+ BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+ offsetof(struct thread_vr_state, vr[32]));
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.vr, 0, 33 * sizeof(vector128));
+ &target->thread.vr_state, 0,
+ 33 * sizeof(vector128));
if (!ret && count > 0) {
/*
* We use only the first word of vrsave.
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
- double buf[32];
+ u64 buf[32];
int ret, i;
flush_vsx_to_thread(target);
for (i = 0; i < 32 ; i++)
- buf[i] = target->thread.fpr[i][TS_VSRLOWOFFSET];
+ buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
buf, 0, 32 * sizeof(double));
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- double buf[32];
+ u64 buf[32];
int ret,i;
flush_vsx_to_thread(target);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
buf, 0, 32 * sizeof(double));
for (i = 0; i < 32 ; i++)
- target->thread.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+ target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
return ret;
flush_fp_to_thread(child);
if (fpidx < (PT_FPSCR - PT_FPR0))
- tmp = ((unsigned long *)child->thread.fpr)
- [fpidx * TS_FPRWIDTH];
+ memcpy(&tmp, &child->thread.fp_state.fpr,
+ sizeof(long));
else
- tmp = child->thread.fpscr.val;
+ tmp = child->thread.fp_state.fpscr;
}
ret = put_user(tmp, datalp);
break;
flush_fp_to_thread(child);
if (fpidx < (PT_FPSCR - PT_FPR0))
- ((unsigned long *)child->thread.fpr)
- [fpidx * TS_FPRWIDTH] = data;
+ memcpy(&child->thread.fp_state.fpr, &data,
+ sizeof(long));
else
- child->thread.fpscr.val = data;
+ child->thread.fp_state.fpscr = data;
ret = 0;
}
break;
#define FPRNUMBER(i) (((i) - PT_FPR0) >> 1)
#define FPRHALF(i) (((i) - PT_FPR0) & 1)
#define FPRINDEX(i) TS_FPRWIDTH * FPRNUMBER(i) * 2 + FPRHALF(i)
-#define FPRINDEX_3264(i) (TS_FPRWIDTH * ((i) - PT_FPR0))
long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
compat_ulong_t caddr, compat_ulong_t cdata)
* to be an array of unsigned int (32 bits) - the
* index passed in is based on this assumption.
*/
- tmp = ((unsigned int *)child->thread.fpr)
+ tmp = ((unsigned int *)child->thread.fp_state.fpr)
[FPRINDEX(index)];
}
ret = put_user((unsigned int)tmp, (u32 __user *)data);
if (numReg >= PT_FPR0) {
flush_fp_to_thread(child);
/* get 64 bit FPR */
- tmp = ((u64 *)child->thread.fpr)
- [FPRINDEX_3264(numReg)];
+ tmp = child->thread.fp_state.fpr[numReg - PT_FPR0][0];
} else { /* register within PT_REGS struct */
unsigned long tmp2;
ret = ptrace_get_reg(child, numReg, &tmp2);
* to be an array of unsigned int (32 bits) - the
* index passed in is based on this assumption.
*/
- ((unsigned int *)child->thread.fpr)
+ ((unsigned int *)child->thread.fp_state.fpr)
[FPRINDEX(index)] = data;
ret = 0;
}
u64 *tmp;
flush_fp_to_thread(child);
/* get 64 bit FPR ... */
- tmp = &(((u64 *)child->thread.fpr)
- [FPRINDEX_3264(numReg)]);
+ tmp = &child->thread.fp_state.fpr[numReg - PT_FPR0][0];
/* ... write the 32 bit part we want */
((u32 *)tmp)[index % 2] = data;
ret = 0;
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);
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;
}
unsigned long copy_fpr_to_user(void __user *to,
struct task_struct *task)
{
- double buf[ELF_NFPREG];
+ u64 buf[ELF_NFPREG];
int i;
/* save FPR copy to local buffer then write to the thread_struct */
for (i = 0; i < (ELF_NFPREG - 1) ; i++)
buf[i] = task->thread.TS_FPR(i);
- memcpy(&buf[i], &task->thread.fpscr, sizeof(double));
+ buf[i] = task->thread.fp_state.fpscr;
return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
}
unsigned long copy_fpr_from_user(struct task_struct *task,
void __user *from)
{
- double buf[ELF_NFPREG];
+ u64 buf[ELF_NFPREG];
int i;
if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
return 1;
for (i = 0; i < (ELF_NFPREG - 1) ; i++)
task->thread.TS_FPR(i) = buf[i];
- memcpy(&task->thread.fpscr, &buf[i], sizeof(double));
+ task->thread.fp_state.fpscr = buf[i];
return 0;
}
unsigned long copy_vsx_to_user(void __user *to,
struct task_struct *task)
{
- double buf[ELF_NVSRHALFREG];
+ u64 buf[ELF_NVSRHALFREG];
int i;
/* save FPR copy to local buffer then write to the thread_struct */
for (i = 0; i < ELF_NVSRHALFREG; i++)
- buf[i] = task->thread.fpr[i][TS_VSRLOWOFFSET];
+ buf[i] = task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
}
unsigned long copy_vsx_from_user(struct task_struct *task,
void __user *from)
{
- double buf[ELF_NVSRHALFREG];
+ u64 buf[ELF_NVSRHALFREG];
int i;
if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
return 1;
for (i = 0; i < ELF_NVSRHALFREG ; i++)
- task->thread.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+ task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
return 0;
}
unsigned long copy_transact_fpr_to_user(void __user *to,
struct task_struct *task)
{
- double buf[ELF_NFPREG];
+ u64 buf[ELF_NFPREG];
int i;
/* save FPR copy to local buffer then write to the thread_struct */
for (i = 0; i < (ELF_NFPREG - 1) ; i++)
buf[i] = task->thread.TS_TRANS_FPR(i);
- memcpy(&buf[i], &task->thread.transact_fpscr, sizeof(double));
+ buf[i] = task->thread.transact_fp.fpscr;
return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
}
unsigned long copy_transact_fpr_from_user(struct task_struct *task,
void __user *from)
{
- double buf[ELF_NFPREG];
+ u64 buf[ELF_NFPREG];
int i;
if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
return 1;
for (i = 0; i < (ELF_NFPREG - 1) ; i++)
task->thread.TS_TRANS_FPR(i) = buf[i];
- memcpy(&task->thread.transact_fpscr, &buf[i], sizeof(double));
+ task->thread.transact_fp.fpscr = buf[i];
return 0;
}
unsigned long copy_transact_vsx_to_user(void __user *to,
struct task_struct *task)
{
- double buf[ELF_NVSRHALFREG];
+ u64 buf[ELF_NVSRHALFREG];
int i;
/* save FPR copy to local buffer then write to the thread_struct */
for (i = 0; i < ELF_NVSRHALFREG; i++)
- buf[i] = task->thread.transact_fpr[i][TS_VSRLOWOFFSET];
+ buf[i] = task->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET];
return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
}
unsigned long copy_transact_vsx_from_user(struct task_struct *task,
void __user *from)
{
- double buf[ELF_NVSRHALFREG];
+ u64 buf[ELF_NVSRHALFREG];
int i;
if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
return 1;
for (i = 0; i < ELF_NVSRHALFREG ; i++)
- task->thread.transact_fpr[i][TS_VSRLOWOFFSET] = buf[i];
+ task->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = buf[i];
return 0;
}
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
inline unsigned long copy_fpr_to_user(void __user *to,
struct task_struct *task)
{
- return __copy_to_user(to, task->thread.fpr,
+ return __copy_to_user(to, task->thread.fp_state.fpr,
ELF_NFPREG * sizeof(double));
}
inline unsigned long copy_fpr_from_user(struct task_struct *task,
void __user *from)
{
- return __copy_from_user(task->thread.fpr, from,
+ return __copy_from_user(task->thread.fp_state.fpr, from,
ELF_NFPREG * sizeof(double));
}
inline unsigned long copy_transact_fpr_to_user(void __user *to,
struct task_struct *task)
{
- return __copy_to_user(to, task->thread.transact_fpr,
+ return __copy_to_user(to, task->thread.transact_fp.fpr,
ELF_NFPREG * sizeof(double));
}
inline unsigned long copy_transact_fpr_from_user(struct task_struct *task,
void __user *from)
{
- return __copy_from_user(task->thread.transact_fpr, from,
+ return __copy_from_user(task->thread.transact_fp.fpr, from,
ELF_NFPREG * sizeof(double));
}
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
/* save altivec registers */
if (current->thread.used_vr) {
flush_altivec_to_thread(current);
- if (__copy_to_user(&frame->mc_vregs, current->thread.vr,
+ if (__copy_to_user(&frame->mc_vregs, ¤t->thread.vr_state,
ELF_NVRREG * sizeof(vector128)))
return 1;
/* set MSR_VEC in the saved MSR value to indicate that
/* save altivec registers */
if (current->thread.used_vr) {
flush_altivec_to_thread(current);
- if (__copy_to_user(&frame->mc_vregs, current->thread.vr,
+ if (__copy_to_user(&frame->mc_vregs, ¤t->thread.vr_state,
ELF_NVRREG * sizeof(vector128)))
return 1;
if (msr & MSR_VEC) {
if (__copy_to_user(&tm_frame->mc_vregs,
- current->thread.transact_vr,
+ ¤t->thread.transact_vr,
ELF_NVRREG * sizeof(vector128)))
return 1;
} else {
if (__copy_to_user(&tm_frame->mc_vregs,
- current->thread.vr,
+ ¤t->thread.vr_state,
ELF_NVRREG * sizeof(vector128)))
return 1;
}
regs->msr &= ~MSR_VEC;
if (msr & MSR_VEC) {
/* restore altivec registers from the stack */
- if (__copy_from_user(current->thread.vr, &sr->mc_vregs,
+ if (__copy_from_user(¤t->thread.vr_state, &sr->mc_vregs,
sizeof(sr->mc_vregs)))
return 1;
} else if (current->thread.used_vr)
- memset(current->thread.vr, 0, ELF_NVRREG * sizeof(vector128));
+ memset(¤t->thread.vr_state, 0,
+ ELF_NVRREG * sizeof(vector128));
/* Always get VRSAVE back */
if (__get_user(current->thread.vrsave, (u32 __user *)&sr->mc_vregs[32]))
return 1;
} else if (current->thread.used_vsr)
for (i = 0; i < 32 ; i++)
- current->thread.fpr[i][TS_VSRLOWOFFSET] = 0;
+ current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
#endif /* CONFIG_VSX */
/*
* force the process to reload the FP registers from
regs->msr &= ~MSR_VEC;
if (msr & MSR_VEC) {
/* restore altivec registers from the stack */
- if (__copy_from_user(current->thread.vr, &sr->mc_vregs,
+ if (__copy_from_user(¤t->thread.vr_state, &sr->mc_vregs,
sizeof(sr->mc_vregs)) ||
- __copy_from_user(current->thread.transact_vr,
+ __copy_from_user(¤t->thread.transact_vr,
&tm_sr->mc_vregs,
sizeof(sr->mc_vregs)))
return 1;
} else if (current->thread.used_vr) {
- memset(current->thread.vr, 0, ELF_NVRREG * sizeof(vector128));
- memset(current->thread.transact_vr, 0,
+ memset(¤t->thread.vr_state, 0,
+ ELF_NVRREG * sizeof(vector128));
+ memset(¤t->thread.transact_vr, 0,
ELF_NVRREG * sizeof(vector128));
}
return 1;
} else if (current->thread.used_vsr)
for (i = 0; i < 32 ; i++) {
- current->thread.fpr[i][TS_VSRLOWOFFSET] = 0;
- current->thread.transact_fpr[i][TS_VSRLOWOFFSET] = 0;
+ current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
+ current->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = 0;
}
#endif /* CONFIG_VSX */
if (__put_user(0, &rt_sf->uc.uc_link))
goto badframe;
- current->thread.fpscr.val = 0; /* turn off all fp exceptions */
+ current->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */
/* create a stack frame for the caller of the handler */
newsp = ((unsigned long)rt_sf) - (__SIGNAL_FRAMESIZE + 16);
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
regs->link = tramp;
- current->thread.fpscr.val = 0; /* turn off all fp exceptions */
+ current->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */
/* create a stack frame for the caller of the handler */
newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE;
if (current->thread.used_vr) {
flush_altivec_to_thread(current);
/* Copy 33 vec registers (vr0..31 and vscr) to the stack */
- err |= __copy_to_user(v_regs, current->thread.vr, 33 * sizeof(vector128));
+ err |= __copy_to_user(v_regs, ¤t->thread.vr_state,
+ 33 * sizeof(vector128));
/* set MSR_VEC in the MSR value in the frame to indicate that sc->v_reg)
* contains valid data.
*/
if (current->thread.used_vr) {
flush_altivec_to_thread(current);
/* Copy 33 vec registers (vr0..31 and vscr) to the stack */
- err |= __copy_to_user(v_regs, current->thread.vr,
+ err |= __copy_to_user(v_regs, ¤t->thread.vr_state,
33 * sizeof(vector128));
/* If VEC was enabled there are transactional VRs valid too,
* else they're a copy of the checkpointed VRs.
*/
if (msr & MSR_VEC)
err |= __copy_to_user(tm_v_regs,
- current->thread.transact_vr,
+ ¤t->thread.transact_vr,
33 * sizeof(vector128));
else
err |= __copy_to_user(tm_v_regs,
- current->thread.vr,
+ ¤t->thread.vr_state,
33 * sizeof(vector128));
/* set MSR_VEC in the MSR value in the frame to indicate
return -EFAULT;
/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
if (v_regs != NULL && (msr & MSR_VEC) != 0)
- err |= __copy_from_user(current->thread.vr, v_regs,
+ err |= __copy_from_user(¤t->thread.vr_state, v_regs,
33 * sizeof(vector128));
else if (current->thread.used_vr)
- memset(current->thread.vr, 0, 33 * sizeof(vector128));
+ memset(¤t->thread.vr_state, 0, 33 * sizeof(vector128));
/* Always get VRSAVE back */
if (v_regs != NULL)
err |= __get_user(current->thread.vrsave, (u32 __user *)&v_regs[33]);
err |= copy_vsx_from_user(current, v_regs);
else
for (i = 0; i < 32 ; i++)
- current->thread.fpr[i][TS_VSRLOWOFFSET] = 0;
+ current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
#endif
return err;
}
return -EFAULT;
/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
if (v_regs != NULL && tm_v_regs != NULL && (msr & MSR_VEC) != 0) {
- err |= __copy_from_user(current->thread.vr, v_regs,
+ err |= __copy_from_user(¤t->thread.vr_state, v_regs,
33 * sizeof(vector128));
- err |= __copy_from_user(current->thread.transact_vr, tm_v_regs,
+ err |= __copy_from_user(¤t->thread.transact_vr, tm_v_regs,
33 * sizeof(vector128));
}
else if (current->thread.used_vr) {
- memset(current->thread.vr, 0, 33 * sizeof(vector128));
- memset(current->thread.transact_vr, 0, 33 * sizeof(vector128));
+ memset(¤t->thread.vr_state, 0, 33 * sizeof(vector128));
+ memset(¤t->thread.transact_vr, 0, 33 * sizeof(vector128));
}
/* Always get VRSAVE back */
if (v_regs != NULL && tm_v_regs != NULL) {
err |= copy_transact_vsx_from_user(current, tm_v_regs);
} else {
for (i = 0; i < 32 ; i++) {
- current->thread.fpr[i][TS_VSRLOWOFFSET] = 0;
- current->thread.transact_fpr[i][TS_VSRLOWOFFSET] = 0;
+ current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
+ current->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = 0;
}
}
#endif
goto badframe;
/* Make sure signal handler doesn't get spurious FP exceptions */
- current->thread.fpscr.val = 0;
+ current->thread.fp_state.fpscr = 0;
#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
/* 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;
#include <asm/reg.h>
#ifdef CONFIG_VSX
-/* See fpu.S, this is very similar but to save/restore checkpointed FPRs/VSRs */
-#define __SAVE_32FPRS_VSRS_TRANSACT(n,c,base) \
+/* See fpu.S, this is borrowed from there */
+#define __SAVE_32FPRS_VSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
- SAVE_32FPRS_TRANSACT(n,base); \
+ SAVE_32FPRS(n,base); \
b 3f; \
-2: SAVE_32VSRS_TRANSACT(n,c,base); \
+2: SAVE_32VSRS(n,c,base); \
3:
-/* ...and this is just plain borrowed from there. */
#define __REST_32FPRS_VSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
2: REST_32VSRS(n,c,base); \
3:
#else
-#define __SAVE_32FPRS_VSRS_TRANSACT(n,c,base) SAVE_32FPRS_TRANSACT(n, base)
-#define __REST_32FPRS_VSRS(n,c,base) REST_32FPRS(n, base)
+#define __SAVE_32FPRS_VSRS(n,c,base) SAVE_32FPRS(n, base)
+#define __REST_32FPRS_VSRS(n,c,base) REST_32FPRS(n, base)
#endif
-#define SAVE_32FPRS_VSRS_TRANSACT(n,c,base) \
- __SAVE_32FPRS_VSRS_TRANSACT(n,__REG_##c,__REG_##base)
+#define SAVE_32FPRS_VSRS(n,c,base) \
+ __SAVE_32FPRS_VSRS(n,__REG_##c,__REG_##base)
#define REST_32FPRS_VSRS(n,c,base) \
__REST_32FPRS_VSRS(n,__REG_##c,__REG_##base)
andis. r0, r4, MSR_VEC@h
beq dont_backup_vec
- SAVE_32VRS_TRANSACT(0, r6, r3) /* r6 scratch, r3 thread */
+ addi r7, r3, THREAD_TRANSACT_VRSTATE
+ SAVE_32VRS(0, r6, r7) /* r6 scratch, r7 transact vr state */
mfvscr vr0
- li r6, THREAD_TRANSACT_VSCR
- stvx vr0, r3, r6
+ li r6, VRSTATE_VSCR
+ stvx vr0, r7, r6
dont_backup_vec:
mfspr r0, SPRN_VRSAVE
std r0, THREAD_TRANSACT_VRSAVE(r3)
andi. r0, r4, MSR_FP
beq dont_backup_fp
- SAVE_32FPRS_VSRS_TRANSACT(0, R6, R3) /* r6 scratch, r3 thread */
+ addi r7, r3, THREAD_TRANSACT_FPSTATE
+ SAVE_32FPRS_VSRS(0, R6, R7) /* r6 scratch, r7 transact fp state */
mffs fr0
- stfd fr0,THREAD_TRANSACT_FPSCR(r3)
+ stfd fr0,FPSTATE_FPSCR(r7)
dont_backup_fp:
/* The moment we treclaim, ALL of our GPRs will switch
andis. r0, r4, MSR_VEC@h
beq dont_restore_vec
- li r5, THREAD_VSCR
- lvx vr0, r3, r5
+ addi r8, r3, THREAD_VRSTATE
+ li r5, VRSTATE_VSCR
+ lvx vr0, r8, r5
mtvscr vr0
- REST_32VRS(0, r5, r3) /* r5 scratch, r3 THREAD ptr */
+ REST_32VRS(0, r5, r8) /* r5 scratch, r8 ptr */
dont_restore_vec:
ld r5, THREAD_VRSAVE(r3)
mtspr SPRN_VRSAVE, r5
andi. r0, r4, MSR_FP
beq dont_restore_fp
- lfd fr0, THREAD_FPSCR(r3)
+ addi r8, r3, THREAD_FPSTATE
+ lfd fr0, FPSTATE_FPSCR(r8)
MTFSF_L(fr0)
- REST_32FPRS_VSRS(0, R4, R3)
+ REST_32FPRS_VSRS(0, R4, R8)
dont_restore_fp:
mtmsr r6 /* FP/Vec off again! */
flush_fp_to_thread(current);
- code = __parse_fpscr(current->thread.fpscr.val);
+ code = __parse_fpscr(current->thread.fp_state.fpscr);
_exception(SIGFPE, regs, code, regs->nip);
}
return 0;
case 1: {
int code = 0;
- code = __parse_fpscr(current->thread.fpscr.val);
+ code = __parse_fpscr(current->thread.fp_state.fpscr);
_exception(SIGFPE, regs, code, regs->nip);
return 0;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-extern void do_load_up_fpu(struct pt_regs *regs);
-
void fp_unavailable_tm(struct pt_regs *regs)
{
/* Note: This does not handle any kind of FP laziness. */
}
#ifdef CONFIG_ALTIVEC
-extern void do_load_up_altivec(struct pt_regs *regs);
-
void altivec_unavailable_tm(struct pt_regs *regs)
{
/* See the comments in fp_unavailable_tm(). This function operates
/* XXX quick hack for now: set the non-Java bit in the VSCR */
printk_ratelimited(KERN_ERR "Unrecognized altivec instruction "
"in %s at %lx\n", current->comm, regs->nip);
- current->thread.vscr.u[3] |= 0x10000;
+ current->thread.vr_state.vscr.u[3] |= 0x10000;
}
}
#endif /* CONFIG_ALTIVEC */
*/
#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)
*/
#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)
vb = (instr >> 11) & 0x1f;
vc = (instr >> 6) & 0x1f;
- vrs = current->thread.vr;
+ vrs = current->thread.vr_state.vr;
switch (instr & 0x3f) {
case 10:
switch (vc) {
case 14: /* vctuxs */
for (i = 0; i < 4; ++i)
vrs[vd].u[i] = ctuxs(vrs[vb].u[i], va,
- ¤t->thread.vscr.u[3]);
+ ¤t->thread.vr_state.vscr.u[3]);
break;
case 15: /* vctsxs */
for (i = 0; i < 4; ++i)
vrs[vd].u[i] = ctsxs(vrs[vb].u[i], va,
- ¤t->thread.vscr.u[3]);
+ ¤t->thread.vr_state.vscr.u[3]);
break;
default:
return -EINVAL;
#include <asm/ptrace.h>
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Wrapper to call load_up_altivec from C.
- * void do_load_up_altivec(struct pt_regs *regs);
- */
-_GLOBAL(do_load_up_altivec)
- mflr r0
- std r0, 16(r1)
- stdu r1, -112(r1)
-
- subi r6, r3, STACK_FRAME_OVERHEAD
- /* load_up_altivec expects r12=MSR, r13=PACA, and returns
- * with r12 = new MSR.
- */
- ld r12,_MSR(r6)
- GET_PACA(r13)
- bl load_up_altivec
- std r12,_MSR(r6)
-
- ld r0, 112+16(r1)
- addi r1, r1, 112
- mtlr r0
- blr
-
/* void do_load_up_transact_altivec(struct thread_struct *thread)
*
* This is similar to load_up_altivec but for the transactional version of the
li r4,1
stw r4,THREAD_USED_VR(r3)
- li r10,THREAD_TRANSACT_VSCR
+ li r10,THREAD_TRANSACT_VRSTATE+VRSTATE_VSCR
lvx vr0,r10,r3
mtvscr vr0
- REST_32VRS_TRANSACT(0,r4,r3)
+ addi r10,r3,THREAD_TRANSACT_VRSTATE
+ REST_32VRS(0,r4,r10)
/* Disable VEC again. */
MTMSRD(r6)
#endif
/*
- * load_up_altivec(unused, unused, tsk)
+ * Load state from memory into VMX registers including VSCR.
+ * Assumes the caller has enabled VMX in the MSR.
+ */
+_GLOBAL(load_vr_state)
+ li r4,VRSTATE_VSCR
+ lvx vr0,r4,r3
+ mtvscr vr0
+ REST_32VRS(0,r4,r3)
+ blr
+
+/*
+ * Store VMX state into memory, including VSCR.
+ * Assumes the caller has enabled VMX in the MSR.
+ */
+_GLOBAL(store_vr_state)
+ SAVE_32VRS(0, r4, r3)
+ mfvscr vr0
+ li r4, VRSTATE_VSCR
+ stvx vr0, r4, r3
+ blr
+
+/*
* Disable VMX for the task which had it previously,
* and save its vector registers in its thread_struct.
* Enables the VMX for use in the kernel on return.
/* Save VMX state to last_task_used_altivec's THREAD struct */
toreal(r4)
addi r4,r4,THREAD
- SAVE_32VRS(0,r5,r4)
+ addi r7,r4,THREAD_VRSTATE
+ SAVE_32VRS(0,r5,r7)
mfvscr vr0
- li r10,THREAD_VSCR
- stvx vr0,r10,r4
+ li r10,VRSTATE_VSCR
+ stvx vr0,r10,r7
/* Disable VMX for last_task_used_altivec */
PPC_LL r5,PT_REGS(r4)
toreal(r5)
oris r12,r12,MSR_VEC@h
std r12,_MSR(r1)
#endif
+ addi r7,r5,THREAD_VRSTATE
li r4,1
- li r10,THREAD_VSCR
+ li r10,VRSTATE_VSCR
stw r4,THREAD_USED_VR(r5)
- lvx vr0,r10,r5
+ lvx vr0,r10,r7
mtvscr vr0
- REST_32VRS(0,r4,r5)
+ REST_32VRS(0,r4,r7)
#ifndef CONFIG_SMP
/* Update last_task_used_altivec to 'current' */
subi r4,r5,THREAD /* Back to 'current' */
PPC_LCMPI 0,r3,0
beqlr /* if no previous owner, done */
addi r3,r3,THREAD /* want THREAD of task */
+ PPC_LL r7,THREAD_VRSAVEAREA(r3)
PPC_LL r5,PT_REGS(r3)
- PPC_LCMPI 0,r5,0
- SAVE_32VRS(0,r4,r3)
+ PPC_LCMPI 0,r7,0
+ bne 2f
+ addi r7,r3,THREAD_VRSTATE
+2: PPC_LCMPI 0,r5,0
+ SAVE_32VRS(0,r4,r7)
mfvscr vr0
- li r4,THREAD_VSCR
- stvx vr0,r4,r3
+ li r4,VRSTATE_VSCR
+ stvx vr0,r4,r7
beq 1f
PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
#ifdef CONFIG_VSX
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).
#ifdef CONFIG_VSX
u64 *vcpu_vsx = vcpu->arch.vsr;
#endif
- u64 *thread_fpr = (u64*)t->fpr;
+ u64 *thread_fpr = &t->fp_state.fpr[0][0];
int i;
/*
/*
* Note that on CPUs with VSX, giveup_fpu stores
* both the traditional FP registers and the added VSX
- * registers into thread.fpr[].
+ * registers into thread.fp_state.fpr[].
*/
if (current->thread.regs->msr & MSR_FP)
giveup_fpu(current);
for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];
- vcpu->arch.fpscr = t->fpscr.val;
+ vcpu->arch.fpscr = t->fp_state.fpscr;
#ifdef CONFIG_VSX
if (cpu_has_feature(CPU_FTR_VSX))
if (msr & MSR_VEC) {
if (current->thread.regs->msr & MSR_VEC)
giveup_altivec(current);
- memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
- vcpu->arch.vscr = t->vscr;
+ memcpy(vcpu->arch.vr, t->vr_state.vr, sizeof(vcpu->arch.vr));
+ vcpu->arch.vscr = t->vr_state.vscr;
}
#endif
#ifdef CONFIG_VSX
u64 *vcpu_vsx = vcpu->arch.vsr;
#endif
- u64 *thread_fpr = (u64*)t->fpr;
+ u64 *thread_fpr = &t->fp_state.fpr[0][0];
int i;
/* When we have paired singles, we emulate in software */
for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++)
thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
#endif
- t->fpscr.val = vcpu->arch.fpscr;
+ t->fp_state.fpscr = vcpu->arch.fpscr;
t->fpexc_mode = 0;
kvmppc_load_up_fpu();
}
if (msr & MSR_VEC) {
#ifdef CONFIG_ALTIVEC
- memcpy(t->vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
- t->vscr = vcpu->arch.vscr;
+ memcpy(t->vr_state.vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
+ t->vr_state.vscr = vcpu->arch.vscr;
t->vrsave = -1;
kvmppc_load_up_altivec();
#endif
int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
int ret;
- double fpr[32][TS_FPRWIDTH];
- unsigned int fpscr;
+ struct thread_fp_state fp;
int fpexc_mode;
#ifdef CONFIG_ALTIVEC
- vector128 vr[32];
- vector128 vscr;
+ struct thread_vr_state vr;
unsigned long uninitialized_var(vrsave);
int used_vr;
#endif
/* Save FPU state in stack */
if (current->thread.regs->msr & MSR_FP)
giveup_fpu(current);
- memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
- fpscr = current->thread.fpscr.val;
+ fp = current->thread.fp_state;
fpexc_mode = current->thread.fpexc_mode;
#ifdef CONFIG_ALTIVEC
if (used_vr) {
if (current->thread.regs->msr & MSR_VEC)
giveup_altivec(current);
- memcpy(vr, current->thread.vr, sizeof(current->thread.vr));
- vscr = current->thread.vscr;
+ vr = current->thread.vr_state;
vrsave = current->thread.vrsave;
}
#endif
current->thread.regs->msr = ext_msr;
/* Restore FPU/VSX state from stack */
- memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
- current->thread.fpscr.val = fpscr;
+ current->thread.fp_state = fp;
current->thread.fpexc_mode = fpexc_mode;
#ifdef CONFIG_ALTIVEC
/* Restore Altivec state from stack */
if (used_vr && current->thread.used_vr) {
- memcpy(current->thread.vr, vr, sizeof(current->thread.vr));
- current->thread.vscr = vscr;
+ current->thread.vr_state = vr;
current->thread.vrsave = vrsave;
}
current->thread.used_vr = used_vr;
{
int ret, s;
#ifdef CONFIG_PPC_FPU
- unsigned int fpscr;
+ struct thread_fp_state fp;
int fpexc_mode;
- u64 fpr[32];
#endif
if (!vcpu->arch.sane) {
#ifdef CONFIG_PPC_FPU
/* Save userspace FPU state in stack */
enable_kernel_fp();
- memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
- fpscr = current->thread.fpscr.val;
+ fp = current->thread.fp_state;
fpexc_mode = current->thread.fpexc_mode;
/* Restore guest FPU state to thread */
- memcpy(current->thread.fpr, vcpu->arch.fpr, sizeof(vcpu->arch.fpr));
- current->thread.fpscr.val = vcpu->arch.fpscr;
+ memcpy(current->thread.fp_state.fpr, vcpu->arch.fpr,
+ sizeof(vcpu->arch.fpr));
+ current->thread.fp_state.fpscr = vcpu->arch.fpscr;
/*
* Since we can't trap on MSR_FP in GS-mode, we consider the guest
vcpu->fpu_active = 0;
/* Save guest FPU state from thread */
- memcpy(vcpu->arch.fpr, current->thread.fpr, sizeof(vcpu->arch.fpr));
- vcpu->arch.fpscr = current->thread.fpscr.val;
+ memcpy(vcpu->arch.fpr, current->thread.fp_state.fpr,
+ sizeof(vcpu->arch.fpr));
+ vcpu->arch.fpscr = current->thread.fp_state.fpscr;
/* Restore userspace FPU state from stack */
- memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
- current->thread.fpscr.val = fpscr;
+ current->thread.fp_state = fp;
current->thread.fpexc_mode = fpexc_mode;
#endif
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)
*/
#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"
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
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
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
.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
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
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
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
#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
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
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
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
.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
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
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
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
#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);
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))
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);
}
}
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);
}
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");
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;
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
} 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);
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 */
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.
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
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))
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;
* 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
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);
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;
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;
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--;
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;
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: "
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;
struct page *start_page, unsigned long size)
{
}
-#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+/*
+ * We do not have access to the sparsemem vmemmap, so we fallback to
+ * walking the list of sparsemem blocks which we already maintain for
+ * the sake of crashdump. In the long run, we might want to maintain
+ * a tree if performance of that linear walk becomes a problem.
+ *
+ * realmode_pfn_to_page functions can fail due to:
+ * 1) As real sparsemem blocks do not lay in RAM continously (they
+ * are in virtual address space which is not available in the real mode),
+ * the requested page struct can be split between blocks so get_page/put_page
+ * may fail.
+ * 2) When huge pages are used, the get_page/put_page API will fail
+ * in real mode as the linked addresses in the page struct are virtual
+ * too.
+ */
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+ struct vmemmap_backing *vmem_back;
+ struct page *page;
+ unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
+ unsigned long pg_va = (unsigned long) pfn_to_page(pfn);
+
+ for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
+ if (pg_va < vmem_back->virt_addr)
+ continue;
+
+ /* Check that page struct is not split between real pages */
+ if ((pg_va + sizeof(struct page)) >
+ (vmem_back->virt_addr + page_size))
+ return NULL;
+
+ page = (struct page *) (vmem_back->phys + pg_va -
+ vmem_back->virt_addr);
+ return page;
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#elif defined(CONFIG_FLATMEM)
+
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+ struct page *page = pfn_to_page(pfn);
+ return page;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */
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 */
{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},
select EPAPR_BOOT
select PPC_INDIRECT_PIO
select PPC_UDBG_16550
+ select PPC_SCOM
+ select ARCH_RANDOM
default y
config POWERNV_MSI
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
};
#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 */
/**
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;
}
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;
}
}
}
+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;
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);
/*
* 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);
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)
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);
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
}
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);
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
}
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);
}
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; \
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);
--- /dev/null
+/*
+ * 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);
static int __init opal_register_exception_handlers(void)
{
+#ifdef __BIG_ENDIAN__
u64 glue;
if (!(powerpc_firmware_features & FW_FEATURE_OPAL))
0, glue);
glue += 128;
opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue);
+#endif
return 0;
}
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;
*/
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;
}
}
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 &&
*/
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;
static irqreturn_t opal_interrupt(int irq, void *data)
{
- uint64_t events;
+ __be64 events;
opal_handle_interrupt(virq_to_hw(irq), &events);
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");
define_pe_printk_level(pe_warn, KERN_WARNING);
define_pe_printk_level(pe_info, KERN_INFO);
+/*
+ * stdcix is only supposed to be used in hypervisor real mode as per
+ * the architecture spec
+ */
+static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr)
+{
+ __asm__ __volatile__("stdcix %0,0,%1"
+ : : "r" (val), "r" (paddr) : "memory");
+}
+
static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
{
unsigned long pe;
}
}
-static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
- u64 *startp, u64 *endp)
+static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe,
+ struct iommu_table *tbl,
+ __be64 *startp, __be64 *endp, bool rm)
{
- u64 __iomem *invalidate = (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);
mb(); /* Ensure above stores are visible */
while (start <= end) {
- __raw_writeq(start, invalidate);
+ if (rm)
+ __raw_rm_writeq(cpu_to_be64(start), invalidate);
+ else
+ __raw_writeq(cpu_to_be64(start), invalidate);
start += inc;
}
static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
struct iommu_table *tbl,
- u64 *startp, u64 *endp)
+ __be64 *startp, __be64 *endp, bool rm)
{
unsigned long start, end, inc;
- u64 __iomem *invalidate = (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;
mb();
while (start <= end) {
- __raw_writeq(start, invalidate);
+ if (rm)
+ __raw_rm_writeq(cpu_to_be64(start), invalidate);
+ else
+ __raw_writeq(cpu_to_be64(start), invalidate);
start += inc;
}
}
void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
- u64 *startp, u64 *endp)
+ __be64 *startp, __be64 *endp, bool rm)
{
struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
tce32_table);
struct pnv_phb *phb = pe->phb;
if (phb->type == PNV_PHB_IODA1)
- pnv_pci_ioda1_tce_invalidate(tbl, startp, endp);
+ pnv_pci_ioda1_tce_invalidate(pe, tbl, startp, endp, rm);
else
- pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp);
+ pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp, rm);
}
static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
* bus number, print that out instead.
*/
tbl->it_busno = 0;
- tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
+ pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
+ tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
+ 8);
tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE |
TCE_PCI_SWINV_PAIR;
}
* bus number, print that out instead.
*/
tbl->it_busno = 0;
- tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
+ pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
+ tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
+ 8);
tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
}
iommu_init_table(tbl, phb->hose->node);
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 ! */
}
if (is_64) {
+ __be64 addr64;
+
rc = opal_get_msi_64(phb->opal_id, pe->mve_number, xive_num, 1,
&addr64, &data);
if (rc) {
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) {
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.
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;
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;
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) */
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);
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;
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;
{
s64 rc;
u8 fstate;
- u16 pcierr;
+ __be16 pcierr;
u32 pe_no;
/*
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:
static int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
unsigned long uaddr, enum dma_data_direction direction,
- struct dma_attrs *attrs)
+ struct dma_attrs *attrs, bool rm)
{
u64 proto_tce;
- u64 *tcep, *tces;
+ __be64 *tcep, *tces;
u64 rpn;
proto_tce = TCE_PCI_READ; // Read allowed
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
* of flags if that becomes the case
*/
if (tbl->it_type & TCE_PCI_SWINV_CREATE)
- pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1);
+ pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
return 0;
}
-static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
+static int pnv_tce_build_vm(struct iommu_table *tbl, long index, long npages,
+ unsigned long uaddr,
+ enum dma_data_direction direction,
+ struct dma_attrs *attrs)
{
- u64 *tcep, *tces;
+ return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs,
+ false);
+}
+
+static void pnv_tce_free(struct iommu_table *tbl, long index, long npages,
+ bool rm)
+{
+ __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);
+ pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
+}
+
+static void pnv_tce_free_vm(struct iommu_table *tbl, long index, long npages)
+{
+ pnv_tce_free(tbl, index, npages, false);
}
static unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
return ((u64 *)tbl->it_base)[index - tbl->it_offset];
}
+static int pnv_tce_build_rm(struct iommu_table *tbl, long index, long npages,
+ unsigned long uaddr,
+ enum dma_data_direction direction,
+ struct dma_attrs *attrs)
+{
+ return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs, true);
+}
+
+static void pnv_tce_free_rm(struct iommu_table *tbl, long index, long npages)
+{
+ pnv_tce_free(tbl, index, npages, true);
+}
+
void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
void *tce_mem, u64 tce_size,
u64 dma_offset)
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;
/* Configure IOMMU DMA hooks */
ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup;
- ppc_md.tce_build = pnv_tce_build;
- ppc_md.tce_free = pnv_tce_free;
+ ppc_md.tce_build = pnv_tce_build_vm;
+ ppc_md.tce_free = pnv_tce_free_vm;
+ ppc_md.tce_build_rm = pnv_tce_build_rm;
+ ppc_md.tce_free_rm = pnv_tce_free_rm;
ppc_md.tce_get = pnv_tce_get;
ppc_md.pci_probe_mode = pnv_pci_probe_mode;
set_pci_dma_ops(&dma_iommu_ops);
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 */
int tce32_seg;
int tce32_segcount;
struct iommu_table tce32_table;
+ phys_addr_t tce_inval_reg_phys;
/* XXX TODO: Add support for additional 64-bit iommus */
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);
+ __be64 *startp, __be64 *endp, bool rm);
#endif /* __POWERNV_PCI_H */
--- /dev/null
+/*
+ * 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);
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
--- /dev/null
+/*
+ * 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);
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",
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)
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);
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 = {
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);
/* 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);
}
config SCOM_DEBUGFS
bool "Expose SCOM controllers via debugfs"
- depends on PPC_SCOM
+ depends on PPC_SCOM && DEBUG_FS
default n
config GE_FPGA
* 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);
}
{
struct device_node *parent;
unsigned int cells, size;
- const u32 *prop;
+ const __be32 *prop, *sprop;
u64 reg, cnt;
scom_map_t ret;
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)))
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");
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;
}
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;
}
bool force)
{
unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+ __be16 oserver;
int16_t server;
int8_t priority;
int64_t rc;
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) {
{
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))
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 */
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)
If unsure, say Y.
+config HW_RANDOM_POWERNV
+ tristate "PowerNV Random Number Generator support"
+ depends on HW_RANDOM && PPC_POWERNV
+ default HW_RANDOM
+ ---help---
+ This is the driver for Random Number Generator hardware found
+ in POWER7+ and above machines for PowerNV platform.
+
+ To compile this driver as a module, choose M here: the
+ module will be called powernv-rng.
+
+ If unsure, say Y.
+
config HW_RANDOM_EXYNOS
tristate "EXYNOS HW random number generator support"
depends on HW_RANDOM && HAS_IOMEM && HAVE_CLK
obj-$(CONFIG_HW_RANDOM_PICOXCELL) += picoxcell-rng.o
obj-$(CONFIG_HW_RANDOM_PPC4XX) += ppc4xx-rng.o
obj-$(CONFIG_HW_RANDOM_PSERIES) += pseries-rng.o
+obj-$(CONFIG_HW_RANDOM_POWERNV) += powernv-rng.o
obj-$(CONFIG_HW_RANDOM_EXYNOS) += exynos-rng.o
obj-$(CONFIG_HW_RANDOM_TPM) += tpm-rng.o
obj-$(CONFIG_HW_RANDOM_BCM2835) += bcm2835-rng.o
--- /dev/null
+/*
+ * Copyright 2013 Michael Ellerman, Guo Chao, 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/random.h>
+#include <linux/hw_random.h>
+
+static int powernv_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+ unsigned long *buf;
+ int i, len;
+
+ /* We rely on rng_buffer_size() being >= sizeof(unsigned long) */
+ len = max / sizeof(unsigned long);
+
+ buf = (unsigned long *)data;
+
+ for (i = 0; i < len; i++)
+ powernv_get_random_long(buf++);
+
+ return len * sizeof(unsigned long);
+}
+
+static struct hwrng powernv_hwrng = {
+ .name = "powernv-rng",
+ .read = powernv_rng_read,
+};
+
+static int powernv_rng_remove(struct platform_device *pdev)
+{
+ hwrng_unregister(&powernv_hwrng);
+
+ return 0;
+}
+
+static int powernv_rng_probe(struct platform_device *pdev)
+{
+ int rc;
+
+ rc = hwrng_register(&powernv_hwrng);
+ if (rc) {
+ /* We only register one device, ignore any others */
+ if (rc == -EEXIST)
+ rc = -ENODEV;
+
+ return rc;
+ }
+
+ pr_info("Registered powernv hwrng.\n");
+
+ return 0;
+}
+
+static struct of_device_id powernv_rng_match[] = {
+ { .compatible = "ibm,power-rng",},
+ {},
+};
+MODULE_DEVICE_TABLE(of, powernv_rng_match);
+
+static struct platform_driver powernv_rng_driver = {
+ .driver = {
+ .name = "powernv_rng",
+ .of_match_table = powernv_rng_match,
+ },
+ .probe = powernv_rng_probe,
+ .remove = powernv_rng_remove,
+};
+module_platform_driver(powernv_rng_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Bare metal HWRNG driver for POWER7+ and above");
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/hw_random.h>
#include <asm/vio.h>
static int pseries_rng_data_read(struct hwrng *rng, u32 *data)
{
- if (plpar_hcall(H_RANDOM, (unsigned long *)data) != H_SUCCESS) {
- printk(KERN_ERR "pseries rng hcall error\n");
- return 0;
+ int rc;
+
+ rc = plpar_hcall(H_RANDOM, (unsigned long *)data);
+ if (rc != H_SUCCESS) {
+ pr_err_ratelimited("H_RANDOM call failed %d\n", rc);
+ return -EIO;
}
+
+ /* The hypervisor interface returns 64 bits */
return 8;
}
void __init hvc_opal_init_early(void)
{
struct device_node *stdout_node = NULL;
- const u32 *termno;
+ const __be32 *termno;
const char *name = NULL;
const struct hv_ops *ops;
u32 index;
if (!stdout_node)
return;
termno = of_get_property(stdout_node, "reg", NULL);
- index = termno ? *termno : 0;
+ index = termno ? be32_to_cpup(termno) : 0;
if (index >= MAX_NR_HVC_CONSOLES)
return;
hvc_opal_privs[index] = &hvc_opal_boot_priv;
static int hvsi_send_packet(struct hvsi_priv *pv, struct hvsi_header *packet)
{
- packet->seqno = atomic_inc_return(&pv->seqno);
+ packet->seqno = cpu_to_be16(atomic_inc_return(&pv->seqno));
/* Assumes that always succeeds, works in practice */
return pv->put_chars(pv->termno, (char *)packet, packet->len);
/* Send version query */
q.hdr.type = VS_QUERY_PACKET_HEADER;
q.hdr.len = sizeof(struct hvsi_query);
- q.verb = VSV_SEND_VERSION_NUMBER;
+ q.verb = cpu_to_be16(VSV_SEND_VERSION_NUMBER);
hvsi_send_packet(pv, &q.hdr);
}
ctrl.hdr.type = VS_CONTROL_PACKET_HEADER;
ctrl.hdr.len = sizeof(struct hvsi_control);
- ctrl.verb = VSV_CLOSE_PROTOCOL;
+ ctrl.verb = cpu_to_be16(VSV_CLOSE_PROTOCOL);
return hvsi_send_packet(pv, &ctrl.hdr);
}
{
struct hvsi_control *pkt = (struct hvsi_control *)pv->inbuf;
- switch (pkt->verb) {
+ switch (be16_to_cpu(pkt->verb)) {
case VSV_CLOSE_PROTOCOL:
/* We restart the handshaking */
hvsi_start_handshake(pv);
break;
case VSV_MODEM_CTL_UPDATE:
/* Transition of carrier detect */
- hvsi_cd_change(pv, pkt->word & HVSI_TSCD);
+ hvsi_cd_change(pv, be32_to_cpu(pkt->word) & HVSI_TSCD);
break;
}
}
struct hvsi_query_response r;
/* We only handle version queries */
- if (pkt->verb != VSV_SEND_VERSION_NUMBER)
+ if (be16_to_cpu(pkt->verb) != VSV_SEND_VERSION_NUMBER)
return;
pr_devel("HVSI@%x: Got version query, sending response...\n",
/* Send version response */
r.hdr.type = VS_QUERY_RESPONSE_PACKET_HEADER;
r.hdr.len = sizeof(struct hvsi_query_response);
- r.verb = VSV_SEND_VERSION_NUMBER;
+ r.verb = cpu_to_be16(VSV_SEND_VERSION_NUMBER);
r.u.version = HVSI_VERSION;
r.query_seqno = pkt->hdr.seqno;
hvsi_send_packet(pv, &r.hdr);
switch(r->verb) {
case VSV_SEND_MODEM_CTL_STATUS:
- hvsi_cd_change(pv, r->u.mctrl_word & HVSI_TSCD);
+ hvsi_cd_change(pv, be32_to_cpu(r->u.mctrl_word) & HVSI_TSCD);
pv->mctrl_update = 1;
break;
}
pv->mctrl_update = 0;
q.hdr.type = VS_QUERY_PACKET_HEADER;
q.hdr.len = sizeof(struct hvsi_query);
- q.hdr.seqno = atomic_inc_return(&pv->seqno);
- q.verb = VSV_SEND_MODEM_CTL_STATUS;
+ q.verb = cpu_to_be16(VSV_SEND_MODEM_CTL_STATUS);
rc = hvsi_send_packet(pv, &q.hdr);
if (rc <= 0) {
pr_devel("HVSI@%x: Error %d...\n", pv->termno, rc);
ctrl.hdr.type = VS_CONTROL_PACKET_HEADER,
ctrl.hdr.len = sizeof(struct hvsi_control);
- ctrl.verb = VSV_SET_MODEM_CTL;
- ctrl.mask = HVSI_TSDTR;
- ctrl.word = dtr ? HVSI_TSDTR : 0;
+ ctrl.verb = cpu_to_be16(VSV_SET_MODEM_CTL);
+ ctrl.mask = cpu_to_be32(HVSI_TSDTR);
+ ctrl.word = cpu_to_be32(dtr ? HVSI_TSDTR : 0);
return hvsi_send_packet(pv, &ctrl.hdr);
}
hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\
member)
+/**
+ * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing
+ * to the same bucket in an rcu enabled hashtable in a rcu enabled hashtable
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ *
+ * This is the same as hash_for_each_possible_rcu() except that it does
+ * not do any RCU debugging or tracing.
+ */
+#define hash_for_each_possible_rcu_notrace(name, obj, member, key) \
+ hlist_for_each_entry_rcu_notrace(obj, \
+ &name[hash_min(key, HASH_BITS(name))], member)
+
/**
* hash_for_each_possible_safe - iterate over all possible objects hashing to the
* same bucket safe against removals
/*
* Try to grab a ref unless the page has a refcount of zero, return false if
* that is the case.
+ * This can be called when MMU is off so it must not access
+ * any of the virtual mappings.
*/
static inline int get_page_unless_zero(struct page *page)
{
return atomic_inc_not_zero(&page->_count);
}
+/*
+ * Try to drop a ref unless the page has a refcount of one, return false if
+ * that is the case.
+ * This is to make sure that the refcount won't become zero after this drop.
+ * This can be called when MMU is off so it must not access
+ * any of the virtual mappings.
+ */
+static inline int put_page_unless_one(struct page *page)
+{
+ return atomic_add_unless(&page->_count, -1, 1);
+}
+
extern int page_is_ram(unsigned long pfn);
/* Support for virtually mapped pages */
* System with lots of page flags available. This allows separate
* flags for PageHead() and PageTail() checks of compound pages so that bit
* tests can be used in performance sensitive paths. PageCompound is
- * generally not used in hot code paths.
+ * generally not used in hot code paths except arch/powerpc/mm/init_64.c
+ * and arch/powerpc/kvm/book3s_64_vio_hv.c which use it to detect huge pages
+ * and avoid handling those in real mode.
*/
__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
__PAGEFLAG(Tail, tail)
projects / karo-tx-linux.git / commitdiff