diff options
Diffstat (limited to 'arch')
263 files changed, 3247 insertions, 4633 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index acda512da2e2..4877a8c8ee16 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -151,4 +151,11 @@ config HAVE_MIXED_BREAKPOINTS_REGS config HAVE_USER_RETURN_NOTIFIER bool +config HAVE_PERF_EVENTS_NMI + bool + help + System hardware can generate an NMI using the perf event + subsystem. Also has support for calculating CPU cycle events + to determine how many clock cycles in a given period. + source "kernel/gcov/Kconfig" diff --git a/arch/alpha/include/asm/local64.h b/arch/alpha/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/alpha/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h index 67af4b841984..08265993227f 100644 --- a/arch/arm/include/asm/kgdb.h +++ b/arch/arm/include/asm/kgdb.h @@ -70,11 +70,11 @@ extern int kgdb_fault_expected; #define _GP_REGS 16 #define _FP_REGS 8 #define _EXTRA_REGS 2 -#define GDB_MAX_REGS (_GP_REGS + (_FP_REGS * 3) + _EXTRA_REGS) +#define DBG_MAX_REG_NUM (_GP_REGS + (_FP_REGS * 3) + _EXTRA_REGS) #define KGDB_MAX_NO_CPUS 1 #define BUFMAX 400 -#define NUMREGBYTES (GDB_MAX_REGS << 2) +#define NUMREGBYTES (DBG_MAX_REG_NUM << 2) #define NUMCRITREGBYTES (32 << 2) #define _R0 0 @@ -93,7 +93,7 @@ extern int kgdb_fault_expected; #define _SPT 13 #define _LR 14 #define _PC 15 -#define _CPSR (GDB_MAX_REGS - 1) +#define _CPSR (DBG_MAX_REG_NUM - 1) /* * So that we can denote the end of a frame for tracing, diff --git a/arch/arm/include/asm/local64.h b/arch/arm/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/arm/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index c868a8864117..778c2f7024ff 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -10,57 +10,62 @@ * Deepak Saxena <dsaxena@plexity.net> */ #include <linux/irq.h> +#include <linux/kdebug.h> #include <linux/kgdb.h> #include <asm/traps.h> -/* Make a local copy of the registers passed into the handler (bletch) */ -void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs) +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { - int regno; - - /* Initialize all to zero. */ - for (regno = 0; regno < GDB_MAX_REGS; regno++) - gdb_regs[regno] = 0; + { "r0", 4, offsetof(struct pt_regs, ARM_r0)}, + { "r1", 4, offsetof(struct pt_regs, ARM_r1)}, + { "r2", 4, offsetof(struct pt_regs, ARM_r2)}, + { "r3", 4, offsetof(struct pt_regs, ARM_r3)}, + { "r4", 4, offsetof(struct pt_regs, ARM_r4)}, + { "r5", 4, offsetof(struct pt_regs, ARM_r5)}, + { "r6", 4, offsetof(struct pt_regs, ARM_r6)}, + { "r7", 4, offsetof(struct pt_regs, ARM_r7)}, + { "r8", 4, offsetof(struct pt_regs, ARM_r8)}, + { "r9", 4, offsetof(struct pt_regs, ARM_r9)}, + { "r10", 4, offsetof(struct pt_regs, ARM_r10)}, + { "fp", 4, offsetof(struct pt_regs, ARM_fp)}, + { "ip", 4, offsetof(struct pt_regs, ARM_ip)}, + { "sp", 4, offsetof(struct pt_regs, ARM_sp)}, + { "lr", 4, offsetof(struct pt_regs, ARM_lr)}, + { "pc", 4, offsetof(struct pt_regs, ARM_pc)}, + { "f0", 12, -1 }, + { "f1", 12, -1 }, + { "f2", 12, -1 }, + { "f3", 12, -1 }, + { "f4", 12, -1 }, + { "f5", 12, -1 }, + { "f6", 12, -1 }, + { "f7", 12, -1 }, + { "fps", 4, -1 }, + { "cpsr", 4, offsetof(struct pt_regs, ARM_cpsr)}, +}; - gdb_regs[_R0] = kernel_regs->ARM_r0; - gdb_regs[_R1] = kernel_regs->ARM_r1; - gdb_regs[_R2] = kernel_regs->ARM_r2; - gdb_regs[_R3] = kernel_regs->ARM_r3; - gdb_regs[_R4] = kernel_regs->ARM_r4; - gdb_regs[_R5] = kernel_regs->ARM_r5; - gdb_regs[_R6] = kernel_regs->ARM_r6; - gdb_regs[_R7] = kernel_regs->ARM_r7; - gdb_regs[_R8] = kernel_regs->ARM_r8; - gdb_regs[_R9] = kernel_regs->ARM_r9; - gdb_regs[_R10] = kernel_regs->ARM_r10; - gdb_regs[_FP] = kernel_regs->ARM_fp; - gdb_regs[_IP] = kernel_regs->ARM_ip; - gdb_regs[_SPT] = kernel_regs->ARM_sp; - gdb_regs[_LR] = kernel_regs->ARM_lr; - gdb_regs[_PC] = kernel_regs->ARM_pc; - gdb_regs[_CPSR] = kernel_regs->ARM_cpsr; +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1) + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + else + memset(mem, 0, dbg_reg_def[regno].size); + return dbg_reg_def[regno].name; } -/* Copy local gdb registers back to kgdb regs, for later copy to kernel */ -void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs) +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) { - kernel_regs->ARM_r0 = gdb_regs[_R0]; - kernel_regs->ARM_r1 = gdb_regs[_R1]; - kernel_regs->ARM_r2 = gdb_regs[_R2]; - kernel_regs->ARM_r3 = gdb_regs[_R3]; - kernel_regs->ARM_r4 = gdb_regs[_R4]; - kernel_regs->ARM_r5 = gdb_regs[_R5]; - kernel_regs->ARM_r6 = gdb_regs[_R6]; - kernel_regs->ARM_r7 = gdb_regs[_R7]; - kernel_regs->ARM_r8 = gdb_regs[_R8]; - kernel_regs->ARM_r9 = gdb_regs[_R9]; - kernel_regs->ARM_r10 = gdb_regs[_R10]; - kernel_regs->ARM_fp = gdb_regs[_FP]; - kernel_regs->ARM_ip = gdb_regs[_IP]; - kernel_regs->ARM_sp = gdb_regs[_SPT]; - kernel_regs->ARM_lr = gdb_regs[_LR]; - kernel_regs->ARM_pc = gdb_regs[_PC]; - kernel_regs->ARM_cpsr = gdb_regs[_CPSR]; + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return -EINVAL; + + if (dbg_reg_def[regno].offset != -1) + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + return 0; } void @@ -176,6 +181,33 @@ void kgdb_roundup_cpus(unsigned long flags) local_irq_disable(); } +static int __kgdb_notify(struct die_args *args, unsigned long cmd) +{ + struct pt_regs *regs = args->regs; + + if (kgdb_handle_exception(1, args->signr, cmd, regs)) + return NOTIFY_DONE; + return NOTIFY_STOP; +} +static int +kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = __kgdb_notify(ptr, cmd); + local_irq_restore(flags); + + return ret; +} + +static struct notifier_block kgdb_notifier = { + .notifier_call = kgdb_notify, + .priority = -INT_MAX, +}; + + /** * kgdb_arch_init - Perform any architecture specific initalization. * @@ -184,6 +216,11 @@ void kgdb_roundup_cpus(unsigned long flags) */ int kgdb_arch_init(void) { + int ret = register_die_notifier(&kgdb_notifier); + + if (ret != 0) + return ret; + register_undef_hook(&kgdb_brkpt_hook); register_undef_hook(&kgdb_compiled_brkpt_hook); @@ -200,6 +237,7 @@ void kgdb_arch_exit(void) { unregister_undef_hook(&kgdb_brkpt_hook); unregister_undef_hook(&kgdb_compiled_brkpt_hook); + unregister_die_notifier(&kgdb_notifier); } /* diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index de12536d687f..417c392ddf1c 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -164,20 +164,20 @@ armpmu_event_set_period(struct perf_event *event, struct hw_perf_event *hwc, int idx) { - s64 left = atomic64_read(&hwc->period_left); + s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0; if (unlikely(left <= -period)) { left = period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } @@ -185,7 +185,7 @@ armpmu_event_set_period(struct perf_event *event, if (left > (s64)armpmu->max_period) left = armpmu->max_period; - atomic64_set(&hwc->prev_count, (u64)-left); + local64_set(&hwc->prev_count, (u64)-left); armpmu->write_counter(idx, (u64)(-left) & 0xffffffff); @@ -204,18 +204,18 @@ armpmu_event_update(struct perf_event *event, u64 delta; again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); new_raw_count = armpmu->read_counter(idx); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &hwc->period_left); + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); return new_raw_count; } @@ -478,7 +478,7 @@ __hw_perf_event_init(struct perf_event *event) if (!hwc->sample_period) { hwc->sample_period = armpmu->max_period; hwc->last_period = hwc->sample_period; - atomic64_set(&hwc->period_left, hwc->sample_period); + local64_set(&hwc->period_left, hwc->sample_period); } err = 0; diff --git a/arch/avr32/Makefile b/arch/avr32/Makefile index ead8a75203a9..22fb66590dcd 100644 --- a/arch/avr32/Makefile +++ b/arch/avr32/Makefile @@ -13,7 +13,7 @@ KBUILD_DEFCONFIG := atstk1002_defconfig KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic KBUILD_AFLAGS += -mrelax -mno-pic -CFLAGS_MODULE += -mno-relax +KBUILD_CFLAGS_MODULE += -mno-relax LDFLAGS_vmlinux += --relax cpuflags-$(CONFIG_PLATFORM_AT32AP) += -march=ap diff --git a/arch/avr32/include/asm/local64.h b/arch/avr32/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/avr32/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/blackfin/Makefile b/arch/blackfin/Makefile index 5a97a31d4bbd..9d5ffaf5492a 100644 --- a/arch/blackfin/Makefile +++ b/arch/blackfin/Makefile @@ -18,8 +18,8 @@ ifeq ($(CONFIG_ROMKERNEL),y) KBUILD_CFLAGS += -mlong-calls endif KBUILD_AFLAGS += $(call cc-option,-mno-fdpic) -CFLAGS_MODULE += -mlong-calls -LDFLAGS_MODULE += -m elf32bfin +KBUILD_CFLAGS_MODULE += -mlong-calls +KBUILD_LDFLAGS_MODULE += -m elf32bfin KALLSYMS += --symbol-prefix=_ KBUILD_DEFCONFIG := BF537-STAMP_defconfig diff --git a/arch/blackfin/include/asm/local64.h b/arch/blackfin/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/blackfin/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/cris/include/asm/local64.h b/arch/cris/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/cris/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/frv/Makefile b/arch/frv/Makefile index 310c47a663f8..7ff84575b186 100644 --- a/arch/frv/Makefile +++ b/arch/frv/Makefile @@ -23,20 +23,14 @@ # Copyright (C) 1994 by Hamish Macdonald # -CCSPECS := $(shell $(CC) -v 2>&1 | grep "^Reading specs from " | head -1 | cut -c20-) -CCDIR := $(strip $(patsubst %/specs,%,$(CCSPECS))) -CPUCLASS := fr400 - -# test for cross compiling -COMPILE_ARCH = $(shell uname -m) - ifdef CONFIG_MMU UTS_SYSNAME = -DUTS_SYSNAME=\"Linux\" else UTS_SYSNAME = -DUTS_SYSNAME=\"uClinux\" endif -ARCHMODFLAGS += -G0 -mlong-calls +KBUILD_AFLAGS_MODULE += -G0 -mlong-calls +KBUILD_CFLAGS_MODULE += -G0 -mlong-calls ifdef CONFIG_GPREL_DATA_8 KBUILD_CFLAGS += -G8 @@ -54,7 +48,6 @@ endif ifdef CONFIG_GC_SECTIONS KBUILD_CFLAGS += -ffunction-sections -fdata-sections -LINKFLAGS += --gc-sections endif ifndef CONFIG_FRAME_POINTER @@ -64,16 +57,13 @@ endif ifdef CONFIG_CPU_FR451_COMPILE KBUILD_CFLAGS += -mcpu=fr450 KBUILD_AFLAGS += -mcpu=fr450 -ASFLAGS += -mcpu=fr450 else ifdef CONFIG_CPU_FR551_COMPILE KBUILD_CFLAGS += -mcpu=fr550 KBUILD_AFLAGS += -mcpu=fr550 -ASFLAGS += -mcpu=fr550 else KBUILD_CFLAGS += -mcpu=fr400 KBUILD_AFLAGS += -mcpu=fr400 -ASFLAGS += -mcpu=fr400 endif endif @@ -83,14 +73,12 @@ endif KBUILD_CFLAGS += -mno-fdpic -mgpr-32 -msoft-float -mno-media KBUILD_CFLAGS += -ffixed-fcc3 -ffixed-cc3 -ffixed-gr15 -ffixed-icc2 KBUILD_AFLAGS += -mno-fdpic -ASFLAGS += -mno-fdpic # make sure the .S files get compiled with debug info # and disable optimisations that are unhelpful whilst debugging ifdef CONFIG_DEBUG_INFO #KBUILD_CFLAGS += -O1 KBUILD_AFLAGS += -Wa,--gdwarf2 -ASFLAGS += -Wa,--gdwarf2 endif head-y := arch/frv/kernel/head.o arch/frv/kernel/init_task.o @@ -105,11 +93,5 @@ all: Image Image: vmlinux $(Q)$(MAKE) $(build)=arch/frv/boot $@ -bootstrap: - $(Q)$(MAKEBOOT) bootstrap - archclean: $(Q)$(MAKE) $(clean)=arch/frv/boot - -archdep: scripts/mkdep symlinks - $(Q)$(MAKE) $(build)=arch/frv/boot dep diff --git a/arch/frv/include/asm/local64.h b/arch/frv/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/frv/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/frv/kernel/local64.h b/arch/frv/kernel/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/frv/kernel/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/h8300/include/asm/local64.h b/arch/h8300/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/h8300/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index 8ae0d2604ce1..be7bfa12b705 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -22,13 +22,13 @@ CHECKFLAGS += -m64 -D__ia64=1 -D__ia64__=1 -D_LP64 -D__LP64__ OBJCOPYFLAGS := --strip-all LDFLAGS_vmlinux := -static -LDFLAGS_MODULE += -T $(srctree)/arch/ia64/module.lds -AFLAGS_KERNEL := -mconstant-gp +KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/ia64/module.lds +KBUILD_AFLAGS_KERNEL := -mconstant-gp EXTRA := cflags-y := -pipe $(EXTRA) -ffixed-r13 -mfixed-range=f12-f15,f32-f127 \ -falign-functions=32 -frename-registers -fno-optimize-sibling-calls -CFLAGS_KERNEL := -mconstant-gp +KBUILD_CFLAGS_KERNEL := -mconstant-gp GAS_STATUS = $(shell $(srctree)/arch/ia64/scripts/check-gas "$(CC)" "$(OBJDUMP)") KBUILD_CPPFLAGS += $(shell $(srctree)/arch/ia64/scripts/toolchain-flags "$(CC)" "$(OBJDUMP)" "$(READELF)") diff --git a/arch/ia64/include/asm/local64.h b/arch/ia64/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/ia64/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/m32r/Makefile b/arch/m32r/Makefile index 469766b24e22..8ff5ba0ea26c 100644 --- a/arch/m32r/Makefile +++ b/arch/m32r/Makefile @@ -12,8 +12,8 @@ OBJCOPYFLAGS := -O binary -R .note -R .comment -S LDFLAGS_vmlinux := KBUILD_CFLAGS += -pipe -fno-schedule-insns -CFLAGS_KERNEL += -mmodel=medium -CFLAGS_MODULE += -mmodel=large +KBUILD_CFLAGS_KERNEL += -mmodel=medium +KBUILD_CFLAGS_MODULE += -mmodel=large ifdef CONFIG_CHIP_VDEC2 cflags-$(CONFIG_ISA_M32R2) += -DNO_FPU -Wa,-bitinst diff --git a/arch/m32r/include/asm/local64.h b/arch/m32r/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/m32r/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile index 570d85c3f97f..b06a7e3cbcd6 100644 --- a/arch/m68k/Makefile +++ b/arch/m68k/Makefile @@ -18,7 +18,7 @@ KBUILD_DEFCONFIG := multi_defconfig # override top level makefile AS += -m68020 LDFLAGS := -m m68kelf -LDFLAGS_MODULE += -T $(srctree)/arch/m68k/kernel/module.lds +KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/m68k/kernel/module.lds ifneq ($(SUBARCH),$(ARCH)) ifeq ($(CROSS_COMPILE),) CROSS_COMPILE := $(call cc-cross-prefix, \ diff --git a/arch/m68k/include/asm/local64.h b/arch/m68k/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/m68k/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index be3855250db6..9bd64b4b2b0c 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -18,6 +18,8 @@ config MICROBLAZE select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG select TRACING_SUPPORT + select OF + select OF_FLATTREE config SWAP def_bool n @@ -76,9 +78,6 @@ config LOCKDEP_SUPPORT config HAVE_LATENCYTOP_SUPPORT def_bool y -config DTC - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" @@ -125,18 +124,6 @@ config CMDLINE_FORCE Set this to have arguments from the default kernel command string override those passed by the boot loader. -config OF - def_bool y - select OF_FLATTREE - -config PROC_DEVICETREE - bool "Support for device tree in /proc" - depends on PROC_FS - help - This option adds a device-tree directory under /proc which contains - an image of the device tree that the kernel copies from Open - Firmware or other boot firmware. If unsure, say Y here. - endmenu menu "Advanced setup" diff --git a/arch/microblaze/include/asm/irq.h b/arch/microblaze/include/asm/irq.h index 31a35c33df63..ec5583d6111c 100644 --- a/arch/microblaze/include/asm/irq.h +++ b/arch/microblaze/include/asm/irq.h @@ -27,17 +27,6 @@ extern unsigned int nr_irq; struct pt_regs; extern void do_IRQ(struct pt_regs *regs); -/** - * irq_of_parse_and_map - Parse and Map an interrupt into linux virq space - * @device: Device node of the device whose interrupt is to be mapped - * @index: Index of the interrupt to map - * - * This function is a wrapper that chains of_irq_map_one() and - * irq_create_of_mapping() to make things easier to callers - */ -struct device_node; -extern unsigned int irq_of_parse_and_map(struct device_node *dev, int index); - /** FIXME - not implement * irq_dispose_mapping - Unmap an interrupt * @virq: linux virq number of the interrupt to unmap @@ -62,17 +51,4 @@ struct irq_host; extern unsigned int irq_create_mapping(struct irq_host *host, irq_hw_number_t hwirq); -/** - * irq_create_of_mapping - Map a hardware interrupt into linux virq space - * @controller: Device node of the interrupt controller - * @inspec: Interrupt specifier from the device-tree - * @intsize: Size of the interrupt specifier from the device-tree - * - * This function is identical to irq_create_mapping except that it takes - * as input informations straight from the device-tree (typically the results - * of the of_irq_map_*() functions. - */ -extern unsigned int irq_create_of_mapping(struct device_node *controller, - u32 *intspec, unsigned int intsize); - #endif /* _ASM_MICROBLAZE_IRQ_H */ diff --git a/arch/microblaze/include/asm/local64.h b/arch/microblaze/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/microblaze/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/microblaze/include/asm/of_device.h b/arch/microblaze/include/asm/of_device.h deleted file mode 100644 index 73cb98040982..000000000000 --- a/arch/microblaze/include/asm/of_device.h +++ /dev/null @@ -1,44 +0,0 @@ -/* - * Copyright (C) 2007-2008 Michal Simek <monstr@monstr.eu> - * - * based on PowerPC of_device.h - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#ifndef _ASM_MICROBLAZE_OF_DEVICE_H -#define _ASM_MICROBLAZE_OF_DEVICE_H -#ifdef __KERNEL__ - -#include <linux/device.h> -#include <linux/of.h> - -/* - * The of_device is a kind of "base class" that is a superset of - * struct device for use by devices attached to an OF node and - * probed using OF properties. - */ -struct of_device { - struct device dev; /* Generic device interface */ - struct pdev_archdata archdata; -}; - -extern ssize_t of_device_get_modalias(struct of_device *ofdev, - char *str, ssize_t len); - -extern struct of_device *of_device_alloc(struct device_node *np, - const char *bus_id, - struct device *parent); - -extern int of_device_uevent(struct device *dev, - struct kobj_uevent_env *env); - -extern void of_device_make_bus_id(struct of_device *dev); - -/* This is just here during the transition */ -#include <linux/of_device.h> - -#endif /* __KERNEL__ */ -#endif /* _ASM_MICROBLAZE_OF_DEVICE_H */ diff --git a/arch/microblaze/include/asm/of_platform.h b/arch/microblaze/include/asm/of_platform.h deleted file mode 100644 index 37491276c6ca..000000000000 --- a/arch/microblaze/include/asm/of_platform.h +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * - * 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. - */ - -#ifndef _ASM_MICROBLAZE_OF_PLATFORM_H -#define _ASM_MICROBLAZE_OF_PLATFORM_H - -/* This is just here during the transition */ -#include <linux/of_platform.h> - -/* - * The list of OF IDs below is used for matching bus types in the - * system whose devices are to be exposed as of_platform_devices. - * - * This is the default list valid for most platforms. This file provides - * functions who can take an explicit list if necessary though - * - * The search is always performed recursively looking for children of - * the provided device_node and recursively if such a children matches - * a bus type in the list - */ - -static const struct of_device_id of_default_bus_ids[] = { - { .type = "soc", }, - { .compatible = "soc", }, - { .type = "plb5", }, - { .type = "plb4", }, - { .type = "opb", }, - { .type = "simple", }, - {}, -}; - -/* Platform devices and busses creation */ -extern struct of_device *of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent); -/* pseudo "matches" value to not do deep probe */ -#define OF_NO_DEEP_PROBE ((struct of_device_id *)-1) - -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); - -extern struct of_device *of_find_device_by_phandle(phandle ph); - -extern void of_instantiate_rtc(void); - -#endif /* _ASM_MICROBLAZE_OF_PLATFORM_H */ diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h index c12c6dfafd9f..4f268faa0126 100644 --- a/arch/microblaze/include/asm/page.h +++ b/arch/microblaze/include/asm/page.h @@ -47,13 +47,6 @@ #define PAGE_UP(addr) (((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1))) #define PAGE_DOWN(addr) ((addr)&(~((PAGE_SIZE)-1))) -/* align addr on a size boundary - adjust address up/down if needed */ -#define _ALIGN_UP(addr, size) (((addr)+((size)-1))&(~((size)-1))) -#define _ALIGN_DOWN(addr, size) ((addr)&(~((size)-1))) - -/* align addr on a size boundary - adjust address up if needed */ -#define _ALIGN(addr, size) _ALIGN_UP(addr, size) - #ifndef CONFIG_MMU /* * PAGE_OFFSET -- the first address of the first page of memory. When not diff --git a/arch/microblaze/include/asm/pci-bridge.h b/arch/microblaze/include/asm/pci-bridge.h index 0c77cda9f5d8..0c68764ab547 100644 --- a/arch/microblaze/include/asm/pci-bridge.h +++ b/arch/microblaze/include/asm/pci-bridge.h @@ -172,13 +172,8 @@ static inline int pci_has_flag(int flag) extern struct list_head hose_list; -extern unsigned long pci_address_to_pio(phys_addr_t address); extern int pcibios_vaddr_is_ioport(void __iomem *address); #else -static inline unsigned long pci_address_to_pio(phys_addr_t address) -{ - return (unsigned long)-1; -} static inline int pcibios_vaddr_is_ioport(void __iomem *address) { return 0; diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h index e7d67a329bd7..101fa098f62a 100644 --- a/arch/microblaze/include/asm/prom.h +++ b/arch/microblaze/include/asm/prom.h @@ -20,9 +20,6 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> -#include <linux/of_fdt.h> -#include <linux/proc_fs.h> -#include <linux/platform_device.h> #include <asm/irq.h> #include <asm/atomic.h> @@ -50,29 +47,10 @@ extern void pci_create_OF_bus_map(void); * OF address retreival & translation */ -/* Translate an OF address block into a CPU physical address - */ -extern u64 of_translate_address(struct device_node *np, const u32 *addr); - -/* Extract an address from a device, returns the region size and - * the address space flags too. The PCI version uses a BAR number - * instead of an absolute index - */ -extern const u32 *of_get_address(struct device_node *dev, int index, - u64 *size, unsigned int *flags); -extern const u32 *of_get_pci_address(struct device_node *dev, int bar_no, - u64 *size, unsigned int *flags); - -/* Get an address as a resource. Note that if your address is - * a PIO address, the conversion will fail if the physical address - * can't be internally converted to an IO token with - * pci_address_to_pio(), that is because it's either called to early - * or it can't be matched to any host bridge IO space - */ -extern int of_address_to_resource(struct device_node *dev, int index, - struct resource *r); -extern int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r); +#ifdef CONFIG_PCI +extern unsigned long pci_address_to_pio(phys_addr_t address); +#define pci_address_to_pio pci_address_to_pio +#endif /* CONFIG_PCI */ /* Parse the ibm,dma-window property of an OF node into the busno, phys and * size parameters. @@ -88,69 +66,6 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); /* Get the MAC address */ extern const void *of_get_mac_address(struct device_node *np); -/* - * OF interrupt mapping - */ - -/* This structure is returned when an interrupt is mapped. The controller - * field needs to be put() after use - */ - -#define OF_MAX_IRQ_SPEC 4 /* We handle specifiers of at most 4 cells */ - -struct of_irq { - struct device_node *controller; /* Interrupt controller node */ - u32 size; /* Specifier size */ - u32 specifier[OF_MAX_IRQ_SPEC]; /* Specifier copy */ -}; - -/** - * of_irq_map_init - Initialize the irq remapper - * @flags: flags defining workarounds to enable - * - * Some machines have bugs in the device-tree which require certain workarounds - * to be applied. Call this before any interrupt mapping attempts to enable - * those workarounds. - */ -#define OF_IMAP_OLDWORLD_MAC 0x00000001 -#define OF_IMAP_NO_PHANDLE 0x00000002 - -extern void of_irq_map_init(unsigned int flags); - -/** - * of_irq_map_raw - Low level interrupt tree parsing - * @parent: the device interrupt parent - * @intspec: interrupt specifier ("interrupts" property of the device) - * @ointsize: size of the passed in interrupt specifier - * @addr: address specifier (start of "reg" property of the device) - * @out_irq: structure of_irq filled by this function - * - * Returns 0 on success and a negative number on error - * - * This function is a low-level interrupt tree walking function. It - * can be used to do a partial walk with synthetized reg and interrupts - * properties, for example when resolving PCI interrupts when no device - * node exist for the parent. - * - */ - -extern int of_irq_map_raw(struct device_node *parent, const u32 *intspec, - u32 ointsize, const u32 *addr, - struct of_irq *out_irq); - -/** - * of_irq_map_one - Resolve an interrupt for a device - * @device: the device whose interrupt is to be resolved - * @index: index of the interrupt to resolve - * @out_irq: structure of_irq filled by this function - * - * This function resolves an interrupt, walking the tree, for a given - * device-tree node. It's the high level pendant to of_irq_map_raw(). - * It also implements the workarounds for OldWolrd Macs. - */ -extern int of_irq_map_one(struct device_node *device, int index, - struct of_irq *out_irq); - /** * of_irq_map_pci - Resolve the interrupt for a PCI device * @pdev: the device whose interrupt is to be resolved @@ -163,20 +78,18 @@ extern int of_irq_map_one(struct device_node *device, int index, * resolving using the OF tree walking. */ struct pci_dev; +struct of_irq; extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq); -extern int of_irq_to_resource(struct device_node *dev, int index, - struct resource *r); - -/** - * of_iomap - Maps the memory mapped IO for a given device_node - * @device: the device whose io range will be mapped - * @index: index of the io range - * - * Returns a pointer to the mapped memory - */ -extern void __iomem *of_iomap(struct device_node *device, int index); - #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ + +/* These includes are put at the bottom because they may contain things + * that are overridden by this file. Ideally they shouldn't be included + * by this file, but there are a bunch of .c files that currently depend + * on it. Eventually they will be cleaned up. */ +#include <linux/of_fdt.h> +#include <linux/of_irq.h> +#include <linux/platform_device.h> + #endif /* _ASM_MICROBLAZE_PROM_H */ diff --git a/arch/microblaze/include/asm/topology.h b/arch/microblaze/include/asm/topology.h index 96bcea5a9920..5428f333a02c 100644 --- a/arch/microblaze/include/asm/topology.h +++ b/arch/microblaze/include/asm/topology.h @@ -1,11 +1 @@ #include <asm-generic/topology.h> - -#ifndef _ASM_MICROBLAZE_TOPOLOGY_H -#define _ASM_MICROBLAZE_TOPOLOGY_H - -struct device_node; -static inline int of_node_to_nid(struct device_node *device) -{ - return 0; -} -#endif /* _ASM_MICROBLAZE_TOPOLOGY_H */ diff --git a/arch/microblaze/kernel/Makefile b/arch/microblaze/kernel/Makefile index 5eecc9f1fbd9..f0cb5c26c81c 100644 --- a/arch/microblaze/kernel/Makefile +++ b/arch/microblaze/kernel/Makefile @@ -15,8 +15,8 @@ endif extra-y := head.o vmlinux.lds obj-y += dma.o exceptions.o \ - hw_exception_handler.o init_task.o intc.o irq.o of_device.o \ - of_platform.o process.o prom.o prom_parse.o ptrace.o \ + hw_exception_handler.o init_task.o intc.o irq.o \ + process.o prom.o prom_parse.o ptrace.o \ reset.o setup.o signal.o sys_microblaze.o timer.o traps.o unwind.o obj-y += cpu/ diff --git a/arch/microblaze/kernel/irq.c b/arch/microblaze/kernel/irq.c index 598f1fd61c89..a9345fb4906a 100644 --- a/arch/microblaze/kernel/irq.c +++ b/arch/microblaze/kernel/irq.c @@ -17,20 +17,10 @@ #include <linux/seq_file.h> #include <linux/kernel_stat.h> #include <linux/irq.h> +#include <linux/of_irq.h> #include <asm/prom.h> -unsigned int irq_of_parse_and_map(struct device_node *dev, int index) -{ - struct of_irq oirq; - - if (of_irq_map_one(dev, index, &oirq)) - return NO_IRQ; - - return oirq.specifier[0]; -} -EXPORT_SYMBOL_GPL(irq_of_parse_and_map); - static u32 concurrent_irq; void __irq_entry do_IRQ(struct pt_regs *regs) @@ -106,7 +96,7 @@ unsigned int irq_create_mapping(struct irq_host *host, irq_hw_number_t hwirq) EXPORT_SYMBOL_GPL(irq_create_mapping); unsigned int irq_create_of_mapping(struct device_node *controller, - u32 *intspec, unsigned int intsize) + const u32 *intspec, unsigned int intsize) { return intspec[0]; } diff --git a/arch/microblaze/kernel/of_device.c b/arch/microblaze/kernel/of_device.c deleted file mode 100644 index b372787886ed..000000000000 --- a/arch/microblaze/kernel/of_device.c +++ /dev/null @@ -1,112 +0,0 @@ -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/mod_devicetable.h> -#include <linux/slab.h> -#include <linux/of_device.h> - -#include <linux/errno.h> - -void of_device_make_bus_id(struct of_device *dev) -{ - static atomic_t bus_no_reg_magic; - struct device_node *node = dev->dev.of_node; - const u32 *reg; - u64 addr; - int magic; - - /* - * For MMIO, get the physical address - */ - reg = of_get_property(node, "reg", NULL); - if (reg) { - addr = of_translate_address(node, reg); - if (addr != OF_BAD_ADDR) { - dev_set_name(&dev->dev, "%llx.%s", - (unsigned long long)addr, node->name); - return; - } - } - - /* - * No BusID, use the node name and add a globally incremented - * counter (and pray...) - */ - magic = atomic_add_return(1, &bus_no_reg_magic); - dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1); -} -EXPORT_SYMBOL(of_device_make_bus_id); - -struct of_device *of_device_alloc(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - struct of_device *dev; - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return NULL; - - dev->dev.of_node = of_node_get(np); - dev->dev.dma_mask = &dev->archdata.dma_mask; - dev->dev.parent = parent; - dev->dev.release = of_release_dev; - - if (bus_id) - dev_set_name(&dev->dev, bus_id); - else - of_device_make_bus_id(dev); - - return dev; -} -EXPORT_SYMBOL(of_device_alloc); - -int of_device_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - struct of_device *ofdev; - const char *compat; - int seen = 0, cplen, sl; - - if (!dev) - return -ENODEV; - - ofdev = to_of_device(dev); - - if (add_uevent_var(env, "OF_NAME=%s", ofdev->dev.of_node->name)) - return -ENOMEM; - - if (add_uevent_var(env, "OF_TYPE=%s", ofdev->dev.of_node->type)) - return -ENOMEM; - - /* Since the compatible field can contain pretty much anything - * it's not really legal to split it out with commas. We split it - * up using a number of environment variables instead. */ - - compat = of_get_property(ofdev->dev.of_node, "compatible", &cplen); - while (compat && *compat && cplen > 0) { - if (add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat)) - return -ENOMEM; - - sl = strlen(compat) + 1; - compat += sl; - cplen -= sl; - seen++; - } - - if (add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen)) - return -ENOMEM; - - /* modalias is trickier, we add it in 2 steps */ - if (add_uevent_var(env, "MODALIAS=")) - return -ENOMEM; - sl = of_device_get_modalias(ofdev, &env->buf[env->buflen-1], - sizeof(env->buf) - env->buflen); - if (sl >= (sizeof(env->buf) - env->buflen)) - return -ENOMEM; - env->buflen += sl; - - return 0; -} -EXPORT_SYMBOL(of_device_uevent); diff --git a/arch/microblaze/kernel/of_platform.c b/arch/microblaze/kernel/of_platform.c deleted file mode 100644 index ccf6f4257f4b..000000000000 --- a/arch/microblaze/kernel/of_platform.c +++ /dev/null @@ -1,200 +0,0 @@ -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * and Arnd Bergmann, 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. - * - */ - -#undef DEBUG - -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/mod_devicetable.h> -#include <linux/pci.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/of_platform.h> - -#include <linux/errno.h> -#include <linux/topology.h> -#include <asm/atomic.h> - -struct bus_type of_platform_bus_type = { - .uevent = of_device_uevent, -}; -EXPORT_SYMBOL(of_platform_bus_type); - -static int __init of_bus_driver_init(void) -{ - return of_bus_type_init(&of_platform_bus_type, "of_platform"); -} -postcore_initcall(of_bus_driver_init); - -struct of_device *of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - struct of_device *dev; - - dev = of_device_alloc(np, bus_id, parent); - if (!dev) - return NULL; - - dev->archdata.dma_mask = 0xffffffffUL; - dev->dev.bus = &of_platform_bus_type; - - /* We do not fill the DMA ops for platform devices by default. - * This is currently the responsibility of the platform code - * to do such, possibly using a device notifier - */ - - if (of_device_register(dev) != 0) { - of_device_free(dev); - return NULL; - } - - return dev; -} -EXPORT_SYMBOL(of_platform_device_create); - -/** - * of_platform_bus_create - Create an OF device for a bus node and all its - * children. Optionally recursively instanciate matching busses. - * @bus: device node of the bus to instanciate - * @matches: match table, NULL to use the default, OF_NO_DEEP_PROBE to - * disallow recursive creation of child busses - */ -static int of_platform_bus_create(const struct device_node *bus, - const struct of_device_id *matches, - struct device *parent) -{ - struct device_node *child; - struct of_device *dev; - int rc = 0; - - for_each_child_of_node(bus, child) { - pr_debug(" create child: %s\n", child->full_name); - dev = of_platform_device_create(child, NULL, parent); - if (dev == NULL) - rc = -ENOMEM; - else if (!of_match_node(matches, child)) - continue; - if (rc == 0) { - pr_debug(" and sub busses\n"); - rc = of_platform_bus_create(child, matches, &dev->dev); - } - if (rc) { - of_node_put(child); - break; - } - } - return rc; -} - - -/** - * of_platform_bus_probe - Probe the device-tree for platform busses - * @root: parent of the first level to probe or NULL for the root of the tree - * @matches: match table, NULL to use the default - * @parent: parent to hook devices from, NULL for toplevel - * - * Note that children of the provided root are not instanciated as devices - * unless the specified root itself matches the bus list and is not NULL. - */ - -int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent) -{ - struct device_node *child; - struct of_device *dev; - int rc = 0; - - if (matches == NULL) - matches = of_default_bus_ids; - if (matches == OF_NO_DEEP_PROBE) - return -EINVAL; - if (root == NULL) - root = of_find_node_by_path("/"); - else - of_node_get(root); - - pr_debug("of_platform_bus_probe()\n"); - pr_debug(" starting at: %s\n", root->full_name); - - /* Do a self check of bus type, if there's a match, create - * children - */ - if (of_match_node(matches, root)) { - pr_debug(" root match, create all sub devices\n"); - dev = of_platform_device_create(root, NULL, parent); - if (dev == NULL) { - rc = -ENOMEM; - goto bail; - } - pr_debug(" create all sub busses\n"); - rc = of_platform_bus_create(root, matches, &dev->dev); - goto bail; - } - for_each_child_of_node(root, child) { - if (!of_match_node(matches, child)) - continue; - - pr_debug(" match: %s\n", child->full_name); - dev = of_platform_device_create(child, NULL, parent); - if (dev == NULL) - rc = -ENOMEM; - else - rc = of_platform_bus_create(child, matches, &dev->dev); - if (rc) { - of_node_put(child); - break; - } - } - bail: - of_node_put(root); - return rc; -} -EXPORT_SYMBOL(of_platform_bus_probe); - -static int of_dev_node_match(struct device *dev, void *data) -{ - return to_of_device(dev)->dev.of_node == data; -} - -struct of_device *of_find_device_by_node(struct device_node *np) -{ - struct device *dev; - - dev = bus_find_device(&of_platform_bus_type, - NULL, np, of_dev_node_match); - if (dev) - return to_of_device(dev); - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_node); - -static int of_dev_phandle_match(struct device *dev, void *data) -{ - phandle *ph = data; - return to_of_device(dev)->dev.of_node->phandle == *ph; -} - -struct of_device *of_find_device_by_phandle(phandle ph) -{ - struct device *dev; - - dev = bus_find_device(&of_platform_bus_type, - NULL, &ph, of_dev_phandle_match); - if (dev) - return to_of_device(dev); - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_phandle); diff --git a/arch/microblaze/kernel/prom_parse.c b/arch/microblaze/kernel/prom_parse.c index bf7e6c27e318..d33ba17601fa 100644 --- a/arch/microblaze/kernel/prom_parse.c +++ b/arch/microblaze/kernel/prom_parse.c @@ -6,219 +6,11 @@ #include <linux/module.h> #include <linux/ioport.h> #include <linux/etherdevice.h> +#include <linux/of_address.h> #include <asm/prom.h> #include <asm/pci-bridge.h> -#define PRu64 "%llx" - -/* Max address size we deal with */ -#define OF_MAX_ADDR_CELLS 4 -#define OF_CHECK_COUNTS(na, ns) ((na) > 0 && (na) <= OF_MAX_ADDR_CELLS && \ - (ns) > 0) - -static struct of_bus *of_match_bus(struct device_node *np); -static int __of_address_to_resource(struct device_node *dev, - const u32 *addrp, u64 size, unsigned int flags, - struct resource *r); - -/* Debug utility */ -#ifdef DEBUG -static void of_dump_addr(const char *s, const u32 *addr, int na) -{ - printk(KERN_INFO "%s", s); - while (na--) - printk(KERN_INFO " %08x", *(addr++)); - printk(KERN_INFO "\n"); -} -#else -static void of_dump_addr(const char *s, const u32 *addr, int na) { } -#endif - -/* Callbacks for bus specific translators */ -struct of_bus { - const char *name; - const char *addresses; - int (*match)(struct device_node *parent); - void (*count_cells)(struct device_node *child, - int *addrc, int *sizec); - u64 (*map)(u32 *addr, const u32 *range, - int na, int ns, int pna); - int (*translate)(u32 *addr, u64 offset, int na); - unsigned int (*get_flags)(const u32 *addr); -}; - -/* - * Default translator (generic bus) - */ - -static void of_bus_default_count_cells(struct device_node *dev, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = of_n_addr_cells(dev); - if (sizec) - *sizec = of_n_size_cells(dev); -} - -static u64 of_bus_default_map(u32 *addr, const u32 *range, - int na, int ns, int pna) -{ - u64 cp, s, da; - - cp = of_read_number(range, na); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr, na); - - pr_debug("OF: default map, cp="PRu64", s="PRu64", da="PRu64"\n", - cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_default_translate(u32 *addr, u64 offset, int na) -{ - u64 a = of_read_number(addr, na); - memset(addr, 0, na * 4); - a += offset; - if (na > 1) - addr[na - 2] = a >> 32; - addr[na - 1] = a & 0xffffffffu; - - return 0; -} - -static unsigned int of_bus_default_get_flags(const u32 *addr) -{ - return IORESOURCE_MEM; -} - #ifdef CONFIG_PCI -/* - * PCI bus specific translator - */ - -static int of_bus_pci_match(struct device_node *np) -{ - /* "vci" is for the /chaos bridge on 1st-gen PCI powermacs */ - return !strcmp(np->type, "pci") || !strcmp(np->type, "vci"); -} - -static void of_bus_pci_count_cells(struct device_node *np, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = 3; - if (sizec) - *sizec = 2; -} - -static u64 of_bus_pci_map(u32 *addr, const u32 *range, int na, int ns, int pna) -{ - u64 cp, s, da; - - /* Check address type match */ - if ((addr[0] ^ range[0]) & 0x03000000) - return OF_BAD_ADDR; - - /* Read address values, skipping high cell */ - cp = of_read_number(range + 1, na - 1); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr + 1, na - 1); - - pr_debug("OF: PCI map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_pci_translate(u32 *addr, u64 offset, int na) -{ - return of_bus_default_translate(addr + 1, offset, na - 1); -} - -static unsigned int of_bus_pci_get_flags(const u32 *addr) -{ - unsigned int flags = 0; - u32 w = addr[0]; - - switch ((w >> 24) & 0x03) { - case 0x01: - flags |= IORESOURCE_IO; - break; - case 0x02: /* 32 bits */ - case 0x03: /* 64 bits */ - flags |= IORESOURCE_MEM; - break; - } - if (w & 0x40000000) - flags |= IORESOURCE_PREFETCH; - return flags; -} - -const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, - unsigned int *flags) -{ - const u32 *prop; - unsigned int psize; - struct device_node *parent; - struct of_bus *bus; - int onesize, i, na, ns; - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - return NULL; - bus = of_match_bus(parent); - if (strcmp(bus->name, "pci")) { - of_node_put(parent); - return NULL; - } - bus->count_cells(dev, &na, &ns); - of_node_put(parent); - if (!OF_CHECK_COUNTS(na, ns)) - return NULL; - - /* Get "reg" or "assigned-addresses" property */ - prop = of_get_property(dev, bus->addresses, &psize); - if (prop == NULL) - return NULL; - psize /= 4; - - onesize = na + ns; - for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) - if ((prop[0] & 0xff) == ((bar_no * 4) + PCI_BASE_ADDRESS_0)) { - if (size) - *size = of_read_number(prop + na, ns); - if (flags) - *flags = bus->get_flags(prop); - return prop; - } - return NULL; -} -EXPORT_SYMBOL(of_get_pci_address); - -int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r) -{ - const u32 *addrp; - u64 size; - unsigned int flags; - - addrp = of_get_pci_address(dev, bar, &size, &flags); - if (addrp == NULL) - return -EINVAL; - return __of_address_to_resource(dev, addrp, size, flags, r); -} -EXPORT_SYMBOL_GPL(of_pci_address_to_resource); - -static u8 of_irq_pci_swizzle(u8 slot, u8 pin) -{ - return (((pin - 1) + slot) % 4) + 1; -} - int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) { struct device_node *dn, *ppnode; @@ -293,331 +85,6 @@ int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) EXPORT_SYMBOL_GPL(of_irq_map_pci); #endif /* CONFIG_PCI */ -/* - * ISA bus specific translator - */ - -static int of_bus_isa_match(struct device_node *np) -{ - return !strcmp(np->name, "isa"); -} - -static void of_bus_isa_count_cells(struct device_node *child, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = 2; - if (sizec) - *sizec = 1; -} - -static u64 of_bus_isa_map(u32 *addr, const u32 *range, int na, int ns, int pna) -{ - u64 cp, s, da; - - /* Check address type match */ - if ((addr[0] ^ range[0]) & 0x00000001) - return OF_BAD_ADDR; - - /* Read address values, skipping high cell */ - cp = of_read_number(range + 1, na - 1); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr + 1, na - 1); - - pr_debug("OF: ISA map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_isa_translate(u32 *addr, u64 offset, int na) -{ - return of_bus_default_translate(addr + 1, offset, na - 1); -} - -static unsigned int of_bus_isa_get_flags(const u32 *addr) -{ - unsigned int flags = 0; - u32 w = addr[0]; - - if (w & 1) - flags |= IORESOURCE_IO; - else - flags |= IORESOURCE_MEM; - return flags; -} - -/* - * Array of bus specific translators - */ - -static struct of_bus of_busses[] = { -#ifdef CONFIG_PCI - /* PCI */ - { - .name = "pci", - .addresses = "assigned-addresses", - .match = of_bus_pci_match, - .count_cells = of_bus_pci_count_cells, - .map = of_bus_pci_map, - .translate = of_bus_pci_translate, - .get_flags = of_bus_pci_get_flags, - }, -#endif /* CONFIG_PCI */ - /* ISA */ - { - .name = "isa", - .addresses = "reg", - .match = of_bus_isa_match, - .count_cells = of_bus_isa_count_cells, - .map = of_bus_isa_map, - .translate = of_bus_isa_translate, - .get_flags = of_bus_isa_get_flags, - }, - /* Default */ - { - .name = "default", - .addresses = "reg", - .match = NULL, - .count_cells = of_bus_default_count_cells, - .map = of_bus_default_map, - .translate = of_bus_default_translate, - .get_flags = of_bus_default_get_flags, - }, -}; - -static struct of_bus *of_match_bus(struct device_node *np) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(of_busses); i++) - if (!of_busses[i].match || of_busses[i].match(np)) - return &of_busses[i]; - BUG(); - return NULL; -} - -static int of_translate_one(struct device_node *parent, struct of_bus *bus, - struct of_bus *pbus, u32 *addr, - int na, int ns, int pna) -{ - const u32 *ranges; - unsigned int rlen; - int rone; - u64 offset = OF_BAD_ADDR; - - /* Normally, an absence of a "ranges" property means we are - * crossing a non-translatable boundary, and thus the addresses - * below the current not cannot be converted to CPU physical ones. - * Unfortunately, while this is very clear in the spec, it's not - * what Apple understood, and they do have things like /uni-n or - * /ht nodes with no "ranges" property and a lot of perfectly - * useable mapped devices below them. Thus we treat the absence of - * "ranges" as equivalent to an empty "ranges" property which means - * a 1:1 translation at that level. It's up to the caller not to try - * to translate addresses that aren't supposed to be translated in - * the first place. --BenH. - */ - ranges = of_get_property(parent, "ranges", (int *) &rlen); - if (ranges == NULL || rlen == 0) { - offset = of_read_number(addr, na); - memset(addr, 0, pna * 4); - pr_debug("OF: no ranges, 1:1 translation\n"); - goto finish; - } - - pr_debug("OF: walking ranges...\n"); - - /* Now walk through the ranges */ - rlen /= 4; - rone = na + pna + ns; - for (; rlen >= rone; rlen -= rone, ranges += rone) { - offset = bus->map(addr, ranges, na, ns, pna); - if (offset != OF_BAD_ADDR) - break; - } - if (offset == OF_BAD_ADDR) { - pr_debug("OF: not found !\n"); - return 1; - } - memcpy(addr, ranges + na, 4 * pna); - - finish: - of_dump_addr("OF: parent translation for:", addr, pna); - pr_debug("OF: with offset: "PRu64"\n", offset); - - /* Translate it into parent bus space */ - return pbus->translate(addr, offset, pna); -} - -/* - * Translate an address from the device-tree into a CPU physical address, - * this walks up the tree and applies the various bus mappings on the - * way. - * - * Note: We consider that crossing any level with #size-cells == 0 to mean - * that translation is impossible (that is we are not dealing with a value - * that can be mapped to a cpu physical address). This is not really specified - * that way, but this is traditionally the way IBM at least do things - */ -u64 of_translate_address(struct device_node *dev, const u32 *in_addr) -{ - struct device_node *parent = NULL; - struct of_bus *bus, *pbus; - u32 addr[OF_MAX_ADDR_CELLS]; - int na, ns, pna, pns; - u64 result = OF_BAD_ADDR; - - pr_debug("OF: ** translation for device %s **\n", dev->full_name); - - /* Increase refcount at current level */ - of_node_get(dev); - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - goto bail; - bus = of_match_bus(parent); - - /* Cound address cells & copy address locally */ - bus->count_cells(dev, &na, &ns); - if (!OF_CHECK_COUNTS(na, ns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", - dev->full_name); - goto bail; - } - memcpy(addr, in_addr, na * 4); - - pr_debug("OF: bus is %s (na=%d, ns=%d) on %s\n", - bus->name, na, ns, parent->full_name); - of_dump_addr("OF: translating address:", addr, na); - - /* Translate */ - for (;;) { - /* Switch to parent bus */ - of_node_put(dev); - dev = parent; - parent = of_get_parent(dev); - - /* If root, we have finished */ - if (parent == NULL) { - pr_debug("OF: reached root node\n"); - result = of_read_number(addr, na); - break; - } - - /* Get new parent bus and counts */ - pbus = of_match_bus(parent); - pbus->count_cells(dev, &pna, &pns); - if (!OF_CHECK_COUNTS(pna, pns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", - dev->full_name); - break; - } - - pr_debug("OF: parent bus is %s (na=%d, ns=%d) on %s\n", - pbus->name, pna, pns, parent->full_name); - - /* Apply bus translation */ - if (of_translate_one(dev, bus, pbus, addr, na, ns, pna)) - break; - - /* Complete the move up one level */ - na = pna; - ns = pns; - bus = pbus; - - of_dump_addr("OF: one level translation:", addr, na); - } - bail: - of_node_put(parent); - of_node_put(dev); - - return result; -} -EXPORT_SYMBOL(of_translate_address); - -const u32 *of_get_address(struct device_node *dev, int index, u64 *size, - unsigned int *flags) -{ - const u32 *prop; - unsigned int psize; - struct device_node *parent; - struct of_bus *bus; - int onesize, i, na, ns; - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - return NULL; - bus = of_match_bus(parent); - bus->count_cells(dev, &na, &ns); - of_node_put(parent); - if (!OF_CHECK_COUNTS(na, ns)) - return NULL; - - /* Get "reg" or "assigned-addresses" property */ - prop = of_get_property(dev, bus->addresses, (int *) &psize); - if (prop == NULL) - return NULL; - psize /= 4; - - onesize = na + ns; - for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) - if (i == index) { - if (size) - *size = of_read_number(prop + na, ns); - if (flags) - *flags = bus->get_flags(prop); - return prop; - } - return NULL; -} -EXPORT_SYMBOL(of_get_address); - -static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, - u64 size, unsigned int flags, - struct resource *r) -{ - u64 taddr; - - if ((flags & (IORESOURCE_IO | IORESOURCE_MEM)) == 0) - return -EINVAL; - taddr = of_translate_address(dev, addrp); - if (taddr == OF_BAD_ADDR) - return -EINVAL; - memset(r, 0, sizeof(struct resource)); - if (flags & IORESOURCE_IO) { - unsigned long port; - port = -1; /* pci_address_to_pio(taddr); */ - if (port == (unsigned long)-1) - return -EINVAL; - r->start = port; - r->end = port + size - 1; - } else { - r->start = taddr; - r->end = taddr + size - 1; - } - r->flags = flags; - r->name = dev->name; - return 0; -} - -int of_address_to_resource(struct device_node *dev, int index, - struct resource *r) -{ - const u32 *addrp; - u64 size; - unsigned int flags; - - addrp = of_get_address(dev, index, &size, &flags); - if (addrp == NULL) - return -EINVAL; - return __of_address_to_resource(dev, addrp, size, flags, r); -} -EXPORT_SYMBOL_GPL(of_address_to_resource); - void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, unsigned long *busno, unsigned long *phys, unsigned long *size) { @@ -644,308 +111,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, *size = of_read_number(dma_window, cells); } -/* - * Interrupt remapper - */ - -static unsigned int of_irq_workarounds; -static struct device_node *of_irq_dflt_pic; - -static struct device_node *of_irq_find_parent(struct device_node *child) -{ - struct device_node *p; - const phandle *parp; - - if (!of_node_get(child)) - return NULL; - - do { - parp = of_get_property(child, "interrupt-parent", NULL); - if (parp == NULL) - p = of_get_parent(child); - else { - if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) - p = of_node_get(of_irq_dflt_pic); - else - p = of_find_node_by_phandle(*parp); - } - of_node_put(child); - child = p; - } while (p && of_get_property(p, "#interrupt-cells", NULL) == NULL); - - return p; -} - -/* This doesn't need to be called if you don't have any special workaround - * flags to pass - */ -void of_irq_map_init(unsigned int flags) -{ - of_irq_workarounds = flags; - - /* OldWorld, don't bother looking at other things */ - if (flags & OF_IMAP_OLDWORLD_MAC) - return; - - /* If we don't have phandles, let's try to locate a default interrupt - * controller (happens when booting with BootX). We do a first match - * here, hopefully, that only ever happens on machines with one - * controller. - */ - if (flags & OF_IMAP_NO_PHANDLE) { - struct device_node *np; - - for (np = NULL; (np = of_find_all_nodes(np)) != NULL;) { - if (of_get_property(np, "interrupt-controller", NULL) - == NULL) - continue; - /* Skip /chosen/interrupt-controller */ - if (strcmp(np->name, "chosen") == 0) - continue; - /* It seems like at least one person on this planet - * wants to use BootX on a machine with an AppleKiwi - * controller which happens to pretend to be an - * interrupt controller too. - */ - if (strcmp(np->name, "AppleKiwi") == 0) - continue; - /* I think we found one ! */ - of_irq_dflt_pic = np; - break; - } - } - -} - -int of_irq_map_raw(struct device_node *parent, const u32 *intspec, u32 ointsize, - const u32 *addr, struct of_irq *out_irq) -{ - struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL; - const u32 *tmp, *imap, *imask; - u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0; - int imaplen, match, i; - - pr_debug("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...]," - "ointsize=%d\n", - parent->full_name, intspec[0], intspec[1], ointsize); - - ipar = of_node_get(parent); - - /* First get the #interrupt-cells property of the current cursor - * that tells us how to interpret the passed-in intspec. If there - * is none, we are nice and just walk up the tree - */ - do { - tmp = of_get_property(ipar, "#interrupt-cells", NULL); - if (tmp != NULL) { - intsize = *tmp; - break; - } - tnode = ipar; - ipar = of_irq_find_parent(ipar); - of_node_put(tnode); - } while (ipar); - if (ipar == NULL) { - pr_debug(" -> no parent found !\n"); - goto fail; - } - - pr_debug("of_irq_map_raw: ipar=%s, size=%d\n", - ipar->full_name, intsize); - - if (ointsize != intsize) - return -EINVAL; - - /* Look for this #address-cells. We have to implement the old linux - * trick of looking for the parent here as some device-trees rely on it - */ - old = of_node_get(ipar); - do { - tmp = of_get_property(old, "#address-cells", NULL); - tnode = of_get_parent(old); - of_node_put(old); - old = tnode; - } while (old && tmp == NULL); - of_node_put(old); - old = NULL; - addrsize = (tmp == NULL) ? 2 : *tmp; - - pr_debug(" -> addrsize=%d\n", addrsize); - - /* Now start the actual "proper" walk of the interrupt tree */ - while (ipar != NULL) { - /* Now check if cursor is an interrupt-controller and if it is - * then we are done - */ - if (of_get_property(ipar, "interrupt-controller", NULL) != - NULL) { - pr_debug(" -> got it !\n"); - memcpy(out_irq->specifier, intspec, - intsize * sizeof(u32)); - out_irq->size = intsize; - out_irq->controller = ipar; - of_node_put(old); - return 0; - } - - /* Now look for an interrupt-map */ - imap = of_get_property(ipar, "interrupt-map", &imaplen); - /* No interrupt map, check for an interrupt parent */ - if (imap == NULL) { - pr_debug(" -> no map, getting parent\n"); - newpar = of_irq_find_parent(ipar); - goto skiplevel; - } - imaplen /= sizeof(u32); - - /* Look for a mask */ - imask = of_get_property(ipar, "interrupt-map-mask", NULL); - - /* If we were passed no "reg" property and we attempt to parse - * an interrupt-map, then #address-cells must be 0. - * Fail if it's not. - */ - if (addr == NULL && addrsize != 0) { - pr_debug(" -> no reg passed in when needed !\n"); - goto fail; - } - - /* Parse interrupt-map */ - match = 0; - while (imaplen > (addrsize + intsize + 1) && !match) { - /* Compare specifiers */ - match = 1; - for (i = 0; i < addrsize && match; ++i) { - u32 mask = imask ? imask[i] : 0xffffffffu; - match = ((addr[i] ^ imap[i]) & mask) == 0; - } - for (; i < (addrsize + intsize) && match; ++i) { - u32 mask = imask ? imask[i] : 0xffffffffu; - match = - ((intspec[i-addrsize] ^ imap[i]) - & mask) == 0; - } - imap += addrsize + intsize; - imaplen -= addrsize + intsize; - - pr_debug(" -> match=%d (imaplen=%d)\n", match, imaplen); - - /* Get the interrupt parent */ - if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) - newpar = of_node_get(of_irq_dflt_pic); - else - newpar = - of_find_node_by_phandle((phandle)*imap); - imap++; - --imaplen; - - /* Check if not found */ - if (newpar == NULL) { - pr_debug(" -> imap parent not found !\n"); - goto fail; - } - - /* Get #interrupt-cells and #address-cells of new - * parent - */ - tmp = of_get_property(newpar, "#interrupt-cells", NULL); - if (tmp == NULL) { - pr_debug(" -> parent lacks " - "#interrupt-cells!\n"); - goto fail; - } - newintsize = *tmp; - tmp = of_get_property(newpar, "#address-cells", NULL); - newaddrsize = (tmp == NULL) ? 0 : *tmp; - - pr_debug(" -> newintsize=%d, newaddrsize=%d\n", - newintsize, newaddrsize); - - /* Check for malformed properties */ - if (imaplen < (newaddrsize + newintsize)) - goto fail; - - imap += newaddrsize + newintsize; - imaplen -= newaddrsize + newintsize; - - pr_debug(" -> imaplen=%d\n", imaplen); - } - if (!match) - goto fail; - - of_node_put(old); - old = of_node_get(newpar); - addrsize = newaddrsize; - intsize = newintsize; - intspec = imap - intsize; - addr = intspec - addrsize; - -skiplevel: - /* Iterate again with new parent */ - pr_debug(" -> new parent: %s\n", - newpar ? newpar->full_name : "<>"); - of_node_put(ipar); - ipar = newpar; - newpar = NULL; - } -fail: - of_node_put(ipar); - of_node_put(old); - of_node_put(newpar); - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(of_irq_map_raw); - -int of_irq_map_one(struct device_node *device, - int index, struct of_irq *out_irq) -{ - struct device_node *p; - const u32 *intspec, *tmp, *addr; - u32 intsize, intlen; - int res; - - pr_debug("of_irq_map_one: dev=%s, index=%d\n", - device->full_name, index); - - /* Get the interrupts property */ - intspec = of_get_property(device, "interrupts", (int *) &intlen); - if (intspec == NULL) - return -EINVAL; - intlen /= sizeof(u32); - - pr_debug(" intspec=%d intlen=%d\n", *intspec, intlen); - - /* Get the reg property (if any) */ - addr = of_get_property(device, "reg", NULL); - - /* Look for the interrupt parent. */ - p = of_irq_find_parent(device); - if (p == NULL) - return -EINVAL; - - /* Get size of interrupt specifier */ - tmp = of_get_property(p, "#interrupt-cells", NULL); - if (tmp == NULL) { - of_node_put(p); - return -EINVAL; - } - intsize = *tmp; - - pr_debug(" intsize=%d intlen=%d\n", intsize, intlen); - - /* Check index */ - if ((index + 1) * intsize > intlen) - return -EINVAL; - - /* Get new specifier and map it */ - res = of_irq_map_raw(p, intspec + index * intsize, intsize, - addr, out_irq); - of_node_put(p); - return res; -} -EXPORT_SYMBOL_GPL(of_irq_map_one); - /** * Search the device tree for the best MAC address to use. 'mac-address' is * checked first, because that is supposed to contain to "most recent" MAC @@ -983,43 +148,3 @@ const void *of_get_mac_address(struct device_node *np) return NULL; } EXPORT_SYMBOL(of_get_mac_address); - -int of_irq_to_resource(struct device_node *dev, int index, struct resource *r) -{ - struct of_irq out_irq; - int irq; - int res; - - res = of_irq_map_one(dev, index, &out_irq); - - /* Get irq for the device */ - if (res) { - pr_debug("IRQ not found... code = %d", res); - return NO_IRQ; - } - /* Assuming single interrupt controller... */ - irq = out_irq.specifier[0]; - - pr_debug("IRQ found = %d", irq); - - /* Only dereference the resource if both the - * resource and the irq are valid. */ - if (r && irq != NO_IRQ) { - r->start = r->end = irq; - r->flags = IORESOURCE_IRQ; - } - - return irq; -} -EXPORT_SYMBOL_GPL(of_irq_to_resource); - -void __iomem *of_iomap(struct device_node *np, int index) -{ - struct resource res; - - if (of_address_to_resource(np, index, &res)) - return NULL; - - return ioremap(res.start, 1 + res.end - res.start); -} -EXPORT_SYMBOL(of_iomap); diff --git a/arch/microblaze/kernel/reset.c b/arch/microblaze/kernel/reset.c index a1721a33042e..bd8ccab5ceff 100644 --- a/arch/microblaze/kernel/reset.c +++ b/arch/microblaze/kernel/reset.c @@ -24,8 +24,8 @@ static int of_reset_gpio_handle(void) int ret; /* variable which stored handle reset gpio pin */ struct device_node *root; /* root node */ struct device_node *gpio; /* gpio node */ - struct of_gpio_chip *of_gc = NULL; - enum of_gpio_flags flags ; + struct gpio_chip *gc; + u32 flags; const void *gpio_spec; /* find out root node */ @@ -39,19 +39,19 @@ static int of_reset_gpio_handle(void) goto err0; } - of_gc = gpio->data; - if (!of_gc) { + gc = of_node_to_gpiochip(gpio); + if (!gc) { pr_debug("%s: gpio controller %s isn't registered\n", root->full_name, gpio->full_name); ret = -ENODEV; goto err1; } - ret = of_gc->xlate(of_gc, root, gpio_spec, &flags); + ret = gc->of_xlate(gc, root, gpio_spec, &flags); if (ret < 0) goto err1; - ret += of_gc->gc.base; + ret += gc->base; err1: of_node_put(gpio); err0: diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c index 17c98dbcec88..f5f768842354 100644 --- a/arch/microblaze/kernel/setup.c +++ b/arch/microblaze/kernel/setup.c @@ -213,15 +213,9 @@ static struct notifier_block dflt_plat_bus_notifier = { .priority = INT_MAX, }; -static struct notifier_block dflt_of_bus_notifier = { - .notifier_call = dflt_bus_notify, - .priority = INT_MAX, -}; - static int __init setup_bus_notifier(void) { bus_register_notifier(&platform_bus_type, &dflt_plat_bus_notifier); - bus_register_notifier(&of_platform_bus_type, &dflt_of_bus_notifier); return 0; } diff --git a/arch/mips/Makefile b/arch/mips/Makefile index f0d196090e94..f4a4b663ebb3 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -93,7 +93,8 @@ all-$(CONFIG_SYS_SUPPORTS_ZBOOT)+= vmlinuz cflags-y += -G 0 -mno-abicalls -fno-pic -pipe cflags-y += -msoft-float LDFLAGS_vmlinux += -G 0 -static -n -nostdlib -MODFLAGS += -mlong-calls +KBUILD_AFLAGS_MODULE += -mlong-calls +KBUILD_CFLAGS_MODULE += -mlong-calls cflags-y += -ffreestanding @@ -165,7 +166,8 @@ cflags-$(CONFIG_CPU_DADDI_WORKAROUNDS) += $(call cc-option,-mno-daddi,) ifdef CONFIG_CPU_SB1 ifdef CONFIG_SB1_PASS_1_WORKAROUNDS -MODFLAGS += -msb1-pass1-workarounds +KBUILD_AFLAGS_MODULE += -msb1-pass1-workarounds +KBUILD_CFLAGS_MODULE += -msb1-pass1-workarounds endif endif diff --git a/arch/mips/include/asm/kgdb.h b/arch/mips/include/asm/kgdb.h index 19002d605ac4..e6c0b0e14ccb 100644 --- a/arch/mips/include/asm/kgdb.h +++ b/arch/mips/include/asm/kgdb.h @@ -8,28 +8,27 @@ #if (_MIPS_ISA == _MIPS_ISA_MIPS1) || (_MIPS_ISA == _MIPS_ISA_MIPS2) || \ (_MIPS_ISA == _MIPS_ISA_MIPS32) -#define KGDB_GDB_REG_SIZE 32 +#define KGDB_GDB_REG_SIZE 32 +#define GDB_SIZEOF_REG sizeof(u32) #elif (_MIPS_ISA == _MIPS_ISA_MIPS3) || (_MIPS_ISA == _MIPS_ISA_MIPS4) || \ (_MIPS_ISA == _MIPS_ISA_MIPS64) #ifdef CONFIG_32BIT -#define KGDB_GDB_REG_SIZE 32 +#define KGDB_GDB_REG_SIZE 32 +#define GDB_SIZEOF_REG sizeof(u32) #else /* CONFIG_CPU_32BIT */ -#define KGDB_GDB_REG_SIZE 64 +#define KGDB_GDB_REG_SIZE 64 +#define GDB_SIZEOF_REG sizeof(u64) #endif #else #error "Need to set KGDB_GDB_REG_SIZE for MIPS ISA" #endif /* _MIPS_ISA */ #define BUFMAX 2048 -#if (KGDB_GDB_REG_SIZE == 32) -#define NUMREGBYTES (90*sizeof(u32)) -#define NUMCRITREGBYTES (12*sizeof(u32)) -#else -#define NUMREGBYTES (90*sizeof(u64)) -#define NUMCRITREGBYTES (12*sizeof(u64)) -#endif +#define DBG_MAX_REG_NUM 72 +#define NUMREGBYTES (DBG_MAX_REG_NUM * sizeof(GDB_SIZEOF_REG)) +#define NUMCRITREGBYTES (12 * sizeof(GDB_SIZEOF_REG)) #define BREAK_INSTR_SIZE 4 #define CACHE_FLUSH_IS_SAFE 0 diff --git a/arch/mips/include/asm/local64.h b/arch/mips/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/mips/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c index 9b78ff6e9b84..1f4e2fa64140 100644 --- a/arch/mips/kernel/kgdb.c +++ b/arch/mips/kernel/kgdb.c @@ -50,6 +50,151 @@ static struct hard_trap_info { { 0, 0} /* Must be last */ }; +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = +{ + { "zero", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[0]) }, + { "at", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[1]) }, + { "v0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[2]) }, + { "v1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[3]) }, + { "a0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[4]) }, + { "a1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[5]) }, + { "a2", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[6]) }, + { "a3", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[7]) }, + { "t0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[8]) }, + { "t1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[9]) }, + { "t2", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[10]) }, + { "t3", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[11]) }, + { "t4", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[12]) }, + { "t5", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[13]) }, + { "t6", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[14]) }, + { "t7", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[15]) }, + { "s0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[16]) }, + { "s1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[17]) }, + { "s2", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[18]) }, + { "s3", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[19]) }, + { "s4", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[20]) }, + { "s5", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[21]) }, + { "s6", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[22]) }, + { "s7", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[23]) }, + { "t8", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[24]) }, + { "t9", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[25]) }, + { "k0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[26]) }, + { "k1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[27]) }, + { "gp", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[28]) }, + { "sp", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[29]) }, + { "s8", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[30]) }, + { "ra", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[31]) }, + { "sr", GDB_SIZEOF_REG, offsetof(struct pt_regs, cp0_status) }, + { "lo", GDB_SIZEOF_REG, offsetof(struct pt_regs, lo) }, + { "hi", GDB_SIZEOF_REG, offsetof(struct pt_regs, hi) }, + { "bad", GDB_SIZEOF_REG, offsetof(struct pt_regs, cp0_badvaddr) }, + { "cause", GDB_SIZEOF_REG, offsetof(struct pt_regs, cp0_cause) }, + { "pc", GDB_SIZEOF_REG, offsetof(struct pt_regs, cp0_epc) }, + { "f0", GDB_SIZEOF_REG, 0 }, + { "f1", GDB_SIZEOF_REG, 1 }, + { "f2", GDB_SIZEOF_REG, 2 }, + { "f3", GDB_SIZEOF_REG, 3 }, + { "f4", GDB_SIZEOF_REG, 4 }, + { "f5", GDB_SIZEOF_REG, 5 }, + { "f6", GDB_SIZEOF_REG, 6 }, + { "f7", GDB_SIZEOF_REG, 7 }, + { "f8", GDB_SIZEOF_REG, 8 }, + { "f9", GDB_SIZEOF_REG, 9 }, + { "f10", GDB_SIZEOF_REG, 10 }, + { "f11", GDB_SIZEOF_REG, 11 }, + { "f12", GDB_SIZEOF_REG, 12 }, + { "f13", GDB_SIZEOF_REG, 13 }, + { "f14", GDB_SIZEOF_REG, 14 }, + { "f15", GDB_SIZEOF_REG, 15 }, + { "f16", GDB_SIZEOF_REG, 16 }, + { "f17", GDB_SIZEOF_REG, 17 }, + { "f18", GDB_SIZEOF_REG, 18 }, + { "f19", GDB_SIZEOF_REG, 19 }, + { "f20", GDB_SIZEOF_REG, 20 }, + { "f21", GDB_SIZEOF_REG, 21 }, + { "f22", GDB_SIZEOF_REG, 22 }, + { "f23", GDB_SIZEOF_REG, 23 }, + { "f24", GDB_SIZEOF_REG, 24 }, + { "f25", GDB_SIZEOF_REG, 25 }, + { "f26", GDB_SIZEOF_REG, 26 }, + { "f27", GDB_SIZEOF_REG, 27 }, + { "f28", GDB_SIZEOF_REG, 28 }, + { "f29", GDB_SIZEOF_REG, 29 }, + { "f30", GDB_SIZEOF_REG, 30 }, + { "f31", GDB_SIZEOF_REG, 31 }, + { "fsr", GDB_SIZEOF_REG, 0 }, + { "fir", GDB_SIZEOF_REG, 0 }, +}; + +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) +{ + int fp_reg; + + if (regno < 0 || regno >= DBG_MAX_REG_NUM) + return -EINVAL; + + if (dbg_reg_def[regno].offset != -1 && regno < 38) { + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + } else if (current && dbg_reg_def[regno].offset != -1 && regno < 72) { + /* FP registers 38 -> 69 */ + if (!(regs->cp0_status & ST0_CU1)) + return 0; + if (regno == 70) { + /* Process the fcr31/fsr (register 70) */ + memcpy((void *)¤t->thread.fpu.fcr31, mem, + dbg_reg_def[regno].size); + goto out_save; + } else if (regno == 71) { + /* Ignore the fir (register 71) */ + goto out_save; + } + fp_reg = dbg_reg_def[regno].offset; + memcpy((void *)¤t->thread.fpu.fpr[fp_reg], mem, + dbg_reg_def[regno].size); +out_save: + restore_fp(current); + } + + return 0; +} + +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + int fp_reg; + + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1 && regno < 38) { + /* First 38 registers */ + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + } else if (current && dbg_reg_def[regno].offset != -1 && regno < 72) { + /* FP registers 38 -> 69 */ + if (!(regs->cp0_status & ST0_CU1)) + goto out; + save_fp(current); + if (regno == 70) { + /* Process the fcr31/fsr (register 70) */ + memcpy(mem, (void *)¤t->thread.fpu.fcr31, + dbg_reg_def[regno].size); + goto out; + } else if (regno == 71) { + /* Ignore the fir (register 71) */ + memset(mem, 0, dbg_reg_def[regno].size); + goto out; + } + fp_reg = dbg_reg_def[regno].offset; + memcpy(mem, (void *)¤t->thread.fpu.fpr[fp_reg], + dbg_reg_def[regno].size); + } + +out: + return dbg_reg_def[regno].name; + +} + void arch_kgdb_breakpoint(void) { __asm__ __volatile__( @@ -84,64 +229,6 @@ static int compute_signal(int tt) return SIGHUP; /* default for things we don't know about */ } -void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) -{ - int reg; - -#if (KGDB_GDB_REG_SIZE == 32) - u32 *ptr = (u32 *)gdb_regs; -#else - u64 *ptr = (u64 *)gdb_regs; -#endif - - for (reg = 0; reg < 32; reg++) - *(ptr++) = regs->regs[reg]; - - *(ptr++) = regs->cp0_status; - *(ptr++) = regs->lo; - *(ptr++) = regs->hi; - *(ptr++) = regs->cp0_badvaddr; - *(ptr++) = regs->cp0_cause; - *(ptr++) = regs->cp0_epc; - - /* FP REGS */ - if (!(current && (regs->cp0_status & ST0_CU1))) - return; - - save_fp(current); - for (reg = 0; reg < 32; reg++) - *(ptr++) = current->thread.fpu.fpr[reg]; -} - -void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) -{ - int reg; - -#if (KGDB_GDB_REG_SIZE == 32) - const u32 *ptr = (u32 *)gdb_regs; -#else - const u64 *ptr = (u64 *)gdb_regs; -#endif - - for (reg = 0; reg < 32; reg++) - regs->regs[reg] = *(ptr++); - - regs->cp0_status = *(ptr++); - regs->lo = *(ptr++); - regs->hi = *(ptr++); - regs->cp0_badvaddr = *(ptr++); - regs->cp0_cause = *(ptr++); - regs->cp0_epc = *(ptr++); - - /* FP REGS from current */ - if (!(current && (regs->cp0_status & ST0_CU1))) - return; - - for (reg = 0; reg < 32; reg++) - current->thread.fpu.fpr[reg] = *(ptr++); - restore_fp(current); -} - /* * Similar to regs_to_gdb_regs() except that process is sleeping and so * we may not be able to get all the info. @@ -242,7 +329,7 @@ static struct notifier_block kgdb_notifier = { }; /* - * Handle the 's' and 'c' commands + * Handle the 'c' command */ int kgdb_arch_handle_exception(int vector, int signo, int err_code, char *remcom_in_buffer, char *remcom_out_buffer, @@ -250,20 +337,14 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code, { char *ptr; unsigned long address; - int cpu = smp_processor_id(); switch (remcom_in_buffer[0]) { - case 's': case 'c': /* handle the optional parameter */ ptr = &remcom_in_buffer[1]; if (kgdb_hex2long(&ptr, &address)) regs->cp0_epc = address; - atomic_set(&kgdb_cpu_doing_single_step, -1); - if (remcom_in_buffer[0] == 's') - atomic_set(&kgdb_cpu_doing_single_step, cpu); - return 0; } diff --git a/arch/mn10300/include/asm/local64.h b/arch/mn10300/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/mn10300/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/parisc/include/asm/local64.h b/arch/parisc/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/parisc/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 9877372ffdba..5beb97bafbb1 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -82,7 +82,7 @@ unsigned long ftrace_return_to_handler(unsigned long retval0, unsigned long ret; pop_return_trace(&trace, &ret); - trace.rettime = cpu_clock(raw_smp_processor_id()); + trace.rettime = local_clock(); ftrace_graph_return(&trace); if (unlikely(!ret)) { @@ -126,7 +126,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - calltime = cpu_clock(raw_smp_processor_id()); + calltime = local_clock(); if (push_return_trace(old, calltime, self_addr, &trace.depth) == -EBUSY) { diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e4545f85ee9f..e2bf40a2ce5a 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -120,6 +120,8 @@ config ARCH_NO_VIRT_TO_BUS config PPC bool default y + select OF + select OF_FLATTREE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER @@ -173,10 +175,6 @@ config ARCH_MAY_HAVE_PC_FDC config PPC_OF def_bool y -config OF - def_bool y - select OF_FLATTREE - config PPC_UDBG_16550 bool default n @@ -199,10 +197,6 @@ config SYS_SUPPORTS_APM_EMULATION default y if PMAC_APM_EMU bool -config DTC - bool - default y - config DEFAULT_UIMAGE bool help @@ -579,14 +573,6 @@ config SCHED_SMT when dealing with POWER5 cpus at a cost of slightly increased overhead in some places. If unsure say N here. -config PROC_DEVICETREE - bool "Support for device tree in /proc" - depends on PROC_FS - help - This option adds a device-tree directory under /proc which contains - an image of the device tree that the kernel copies from Open - Firmware or other boot firmware. If unsure, say Y here. - config CMDLINE_BOOL bool "Default bootloader kernel arguments" diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 77cfe7a29e25..5d42f5eae70f 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -94,7 +94,7 @@ else endif endif -LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o +KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o ifeq ($(CONFIG_TUNE_CELL),y) KBUILD_CFLAGS += $(call cc-option,-mtune=cell) diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 5e2e2cfcc81b..3a40a992e594 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -197,6 +197,7 @@ extern const char *powerpc_base_platform; #define CPU_FTR_SAO LONG_ASM_CONST(0x0020000000000000) #define CPU_FTR_CP_USE_DCBTZ LONG_ASM_CONST(0x0040000000000000) #define CPU_FTR_UNALIGNED_LD_STD LONG_ASM_CONST(0x0080000000000000) +#define CPU_FTR_ASYM_SMT LONG_ASM_CONST(0x0100000000000000) #ifndef __ASSEMBLY__ @@ -412,7 +413,7 @@ extern const char *powerpc_base_platform; CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | CPU_FTR_SAO) + CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index ecba37a91749..67ab5fb7d153 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -300,34 +300,6 @@ extern unsigned int irq_alloc_virt(struct irq_host *host, */ extern void irq_free_virt(unsigned int virq, unsigned int count); - -/* -- OF helpers -- */ - -/** - * irq_create_of_mapping - Map a hardware interrupt into linux virq space - * @controller: Device node of the interrupt controller - * @inspec: Interrupt specifier from the device-tree - * @intsize: Size of the interrupt specifier from the device-tree - * - * This function is identical to irq_create_mapping except that it takes - * as input informations straight from the device-tree (typically the results - * of the of_irq_map_*() functions. - */ -extern unsigned int irq_create_of_mapping(struct device_node *controller, - const u32 *intspec, unsigned int intsize); - -/** - * irq_of_parse_and_map - Parse and Map an interrupt into linux virq space - * @device: Device node of the device whose interrupt is to be mapped - * @index: Index of the interrupt to map - * - * This function is a wrapper that chains of_irq_map_one() and - * irq_create_of_mapping() to make things easier to callers - */ -extern unsigned int irq_of_parse_and_map(struct device_node *dev, int index); - -/* -- End OF helpers -- */ - /** * irq_early_init - Init irq remapping subsystem */ diff --git a/arch/powerpc/include/asm/local64.h b/arch/powerpc/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/powerpc/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h index 675e159b5ef4..7ab82c825a03 100644 --- a/arch/powerpc/include/asm/macio.h +++ b/arch/powerpc/include/asm/macio.h @@ -38,7 +38,7 @@ struct macio_dev { struct macio_bus *bus; /* macio bus this device is on */ struct macio_dev *media_bay; /* Device is part of a media bay */ - struct of_device ofdev; + struct platform_device ofdev; struct device_dma_parameters dma_parms; /* ide needs that */ int n_resources; struct resource resource[MACIO_DEV_COUNT_RESOURCES]; diff --git a/arch/powerpc/include/asm/of_device.h b/arch/powerpc/include/asm/of_device.h deleted file mode 100644 index 444e97e2982e..000000000000 --- a/arch/powerpc/include/asm/of_device.h +++ /dev/null @@ -1,27 +0,0 @@ -#ifndef _ASM_POWERPC_OF_DEVICE_H -#define _ASM_POWERPC_OF_DEVICE_H -#ifdef __KERNEL__ - -#include <linux/device.h> -#include <linux/of.h> - -/* - * The of_device is a kind of "base class" that is a superset of - * struct device for use by devices attached to an OF node and - * probed using OF properties. - */ -struct of_device -{ - struct device dev; /* Generic device interface */ - struct pdev_archdata archdata; -}; - -extern struct of_device *of_device_alloc(struct device_node *np, - const char *bus_id, - struct device *parent); - -extern int of_device_uevent(struct device *dev, - struct kobj_uevent_env *env); - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_OF_DEVICE_H */ diff --git a/arch/powerpc/include/asm/of_platform.h b/arch/powerpc/include/asm/of_platform.h deleted file mode 100644 index d4aaa3489440..000000000000 --- a/arch/powerpc/include/asm/of_platform.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef _ASM_POWERPC_OF_PLATFORM_H -#define _ASM_POWERPC_OF_PLATFORM_H -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * - * 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. - * - */ - -/* Platform devices and busses creation */ -extern struct of_device *of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent); -/* pseudo "matches" value to not do deep probe */ -#define OF_NO_DEEP_PROBE ((struct of_device_id *)-1) - -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); - -extern struct of_device *of_find_device_by_phandle(phandle ph); - -extern void of_instantiate_rtc(void); - -#endif /* _ASM_POWERPC_OF_PLATFORM_H */ diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 76e1f313a58e..51e9e6f90d12 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -303,13 +303,8 @@ extern void pcibios_free_controller(struct pci_controller *phb); extern void pcibios_setup_phb_resources(struct pci_controller *hose); #ifdef CONFIG_PCI -extern unsigned long pci_address_to_pio(phys_addr_t address); extern int pcibios_vaddr_is_ioport(void __iomem *address); #else -static inline unsigned long pci_address_to_pio(phys_addr_t address) -{ - return (unsigned long)-1; -} static inline int pcibios_vaddr_is_ioport(void __iomem *address) { return 0; diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index e6d4ce69b126..5c16b891d501 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -21,3 +21,15 @@ #ifdef CONFIG_FSL_EMB_PERF_EVENT #include <asm/perf_event_fsl_emb.h> #endif + +#ifdef CONFIG_PERF_EVENTS +#include <asm/ptrace.h> +#include <asm/reg.h> + +#define perf_arch_fetch_caller_regs(regs, __ip) \ + do { \ + (regs)->nip = __ip; \ + (regs)->gpr[1] = *(unsigned long *)__get_SP(); \ + asm volatile("mfmsr %0" : "=r" ((regs)->msr)); \ + } while (0) +#endif diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index ddd408a93b5a..ae26f2efd089 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -17,9 +17,6 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/types.h> -#include <linux/of_fdt.h> -#include <linux/proc_fs.h> -#include <linux/platform_device.h> #include <asm/irq.h> #include <asm/atomic.h> @@ -43,49 +40,14 @@ extern void pci_create_OF_bus_map(void); * OF address retreival & translation */ -/* Translate an OF address block into a CPU physical address - */ -extern u64 of_translate_address(struct device_node *np, const u32 *addr); - /* Translate a DMA address from device space to CPU space */ extern u64 of_translate_dma_address(struct device_node *dev, const u32 *in_addr); -/* Extract an address from a device, returns the region size and - * the address space flags too. The PCI version uses a BAR number - * instead of an absolute index - */ -extern const u32 *of_get_address(struct device_node *dev, int index, - u64 *size, unsigned int *flags); #ifdef CONFIG_PCI -extern const u32 *of_get_pci_address(struct device_node *dev, int bar_no, - u64 *size, unsigned int *flags); -#else -static inline const u32 *of_get_pci_address(struct device_node *dev, - int bar_no, u64 *size, unsigned int *flags) -{ - return NULL; -} -#endif /* CONFIG_PCI */ - -/* Get an address as a resource. Note that if your address is - * a PIO address, the conversion will fail if the physical address - * can't be internally converted to an IO token with - * pci_address_to_pio(), that is because it's either called to early - * or it can't be matched to any host bridge IO space - */ -extern int of_address_to_resource(struct device_node *dev, int index, - struct resource *r); -#ifdef CONFIG_PCI -extern int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r); -#else -static inline int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r) -{ - return -ENOSYS; -} -#endif /* CONFIG_PCI */ +extern unsigned long pci_address_to_pio(phys_addr_t address); +#define pci_address_to_pio pci_address_to_pio +#endif /* CONFIG_PCI */ /* Parse the ibm,dma-window property of an OF node into the busno, phys and * size parameters. @@ -104,69 +66,12 @@ struct device_node *of_find_next_cache_node(struct device_node *np); /* Get the MAC address */ extern const void *of_get_mac_address(struct device_node *np); -/* - * OF interrupt mapping - */ - -/* This structure is returned when an interrupt is mapped. The controller - * field needs to be put() after use - */ - -#define OF_MAX_IRQ_SPEC 4 /* We handle specifiers of at most 4 cells */ - -struct of_irq { - struct device_node *controller; /* Interrupt controller node */ - u32 size; /* Specifier size */ - u32 specifier[OF_MAX_IRQ_SPEC]; /* Specifier copy */ -}; - -/** - * of_irq_map_init - Initialize the irq remapper - * @flags: flags defining workarounds to enable - * - * Some machines have bugs in the device-tree which require certain workarounds - * to be applied. Call this before any interrupt mapping attempts to enable - * those workarounds. - */ -#define OF_IMAP_OLDWORLD_MAC 0x00000001 -#define OF_IMAP_NO_PHANDLE 0x00000002 - -extern void of_irq_map_init(unsigned int flags); - -/** - * of_irq_map_raw - Low level interrupt tree parsing - * @parent: the device interrupt parent - * @intspec: interrupt specifier ("interrupts" property of the device) - * @ointsize: size of the passed in interrupt specifier - * @addr: address specifier (start of "reg" property of the device) - * @out_irq: structure of_irq filled by this function - * - * Returns 0 on success and a negative number on error - * - * This function is a low-level interrupt tree walking function. It - * can be used to do a partial walk with synthetized reg and interrupts - * properties, for example when resolving PCI interrupts when no device - * node exist for the parent. - * - */ - -extern int of_irq_map_raw(struct device_node *parent, const u32 *intspec, - u32 ointsize, const u32 *addr, - struct of_irq *out_irq); - - -/** - * of_irq_map_one - Resolve an interrupt for a device - * @device: the device whose interrupt is to be resolved - * @index: index of the interrupt to resolve - * @out_irq: structure of_irq filled by this function - * - * This function resolves an interrupt, walking the tree, for a given - * device-tree node. It's the high level pendant to of_irq_map_raw(). - * It also implements the workarounds for OldWolrd Macs. - */ -extern int of_irq_map_one(struct device_node *device, int index, - struct of_irq *out_irq); +#ifdef CONFIG_NUMA +extern int of_node_to_nid(struct device_node *device); +#else +static inline int of_node_to_nid(struct device_node *device) { return 0; } +#endif +#define of_node_to_nid of_node_to_nid /** * of_irq_map_pci - Resolve the interrupt for a PCI device @@ -180,19 +85,19 @@ extern int of_irq_map_one(struct device_node *device, int index, * resolving using the OF tree walking. */ struct pci_dev; +struct of_irq; extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq); -extern int of_irq_to_resource(struct device_node *dev, int index, - struct resource *r); +extern void of_instantiate_rtc(void); -/** - * of_iomap - Maps the memory mapped IO for a given device_node - * @device: the device whose io range will be mapped - * @index: index of the io range - * - * Returns a pointer to the mapped memory - */ -extern void __iomem *of_iomap(struct device_node *device, int index); +/* These includes are put at the bottom because they may contain things + * that are overridden by this file. Ideally they shouldn't be included + * by this file, but there are a bunch of .c files that currently depend + * on it. Eventually they will be cleaned up. */ +#include <linux/of_fdt.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/platform_device.h> #endif /* __KERNEL__ */ #endif /* _POWERPC_PROM_H */ diff --git a/arch/powerpc/include/asm/smu.h b/arch/powerpc/include/asm/smu.h index 7ae2753da565..e3bdada8c542 100644 --- a/arch/powerpc/include/asm/smu.h +++ b/arch/powerpc/include/asm/smu.h @@ -457,8 +457,8 @@ extern void smu_poll(void); */ extern int smu_init(void); extern int smu_present(void); -struct of_device; -extern struct of_device *smu_get_ofdev(void); +struct platform_device; +extern struct platform_device *smu_get_ofdev(void); /* diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 3033c1b30745..afe4aaa65c3b 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -41,8 +41,6 @@ static inline int cpu_to_node(int cpu) cpu_all_mask : \ node_to_cpumask_map[node]) -int of_node_to_nid(struct device_node *device); - struct pci_bus; #ifdef CONFIG_PCI extern int pcibus_to_node(struct pci_bus *bus); @@ -97,11 +95,6 @@ extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid); #else -static inline int of_node_to_nid(struct device_node *device) -{ - return 0; -} - static inline void dump_numa_cpu_topology(void) {} static inline int sysfs_add_device_to_node(struct sys_device *dev, int nid) diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 77d831a1cc32..1dda70129141 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -41,7 +41,7 @@ obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o -obj-$(CONFIG_PPC_OF) += of_device.o of_platform.o prom_parse.o +obj-$(CONFIG_PPC_OF) += of_platform.o prom_parse.o obj-$(CONFIG_PPC_CLOCK) += clock.o procfs-y := proc_powerpc.o obj-$(CONFIG_PROC_FS) += $(procfs-y) diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 02f724f36753..4295e0b94b2d 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -82,17 +82,9 @@ static struct notifier_block ppc_swiotlb_plat_bus_notifier = { .priority = 0, }; -static struct notifier_block ppc_swiotlb_of_bus_notifier = { - .notifier_call = ppc_swiotlb_bus_notify, - .priority = 0, -}; - int __init swiotlb_setup_bus_notifier(void) { bus_register_notifier(&platform_bus_type, &ppc_swiotlb_plat_bus_notifier); - bus_register_notifier(&of_platform_bus_type, - &ppc_swiotlb_of_bus_notifier); - return 0; } diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 21266abfbda6..9b626cfffce1 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -140,19 +140,19 @@ static struct dma_map_ops ibmebus_dma_ops = { static int ibmebus_match_path(struct device *dev, void *data) { - struct device_node *dn = to_of_device(dev)->dev.of_node; + struct device_node *dn = to_platform_device(dev)->dev.of_node; return (dn->full_name && (strcasecmp((char *)data, dn->full_name) == 0)); } static int ibmebus_match_node(struct device *dev, void *data) { - return to_of_device(dev)->dev.of_node == data; + return to_platform_device(dev)->dev.of_node == data; } static int ibmebus_create_device(struct device_node *dn) { - struct of_device *dev; + struct platform_device *dev; int ret; dev = of_device_alloc(dn, NULL, &ibmebus_bus_device); @@ -298,7 +298,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus, if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path, ibmebus_match_path))) { - of_device_unregister(to_of_device(dev)); + of_device_unregister(to_platform_device(dev)); kfree(path); return count; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 8f96d3198905..d3ce67cf03be 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -53,6 +53,8 @@ #include <linux/bootmem.h> #include <linux/pci.h> #include <linux/debugfs.h> +#include <linux/of.h> +#include <linux/of_irq.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -820,18 +822,6 @@ unsigned int irq_create_of_mapping(struct device_node *controller, } EXPORT_SYMBOL_GPL(irq_create_of_mapping); -unsigned int irq_of_parse_and_map(struct device_node *dev, int index) -{ - struct of_irq oirq; - - if (of_irq_map_one(dev, index, &oirq)) - return NO_IRQ; - - return irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); -} -EXPORT_SYMBOL_GPL(irq_of_parse_and_map); - void irq_dispose_mapping(unsigned int virq) { struct irq_host *host; diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 82a7b228c81a..7f61a3ac787c 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -129,7 +129,7 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs) return 0; if (*(u32 *) (regs->nip) == *(u32 *) (&arch_kgdb_ops.gdb_bpt_instr)) - regs->nip += 4; + regs->nip += BREAK_INSTR_SIZE; return 1; } diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 035ada5443ee..c1fd0f9658fd 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -4,6 +4,7 @@ #include <linux/serial_core.h> #include <linux/console.h> #include <linux/pci.h> +#include <linux/of_address.h> #include <linux/of_device.h> #include <asm/io.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 22e507c8a556..2d29752cbe16 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -127,29 +127,3 @@ _GLOBAL(__setup_cpu_power7) _GLOBAL(__restore_cpu_power7) /* place holder */ blr - -/* - * Get a minimal set of registers for our caller's nth caller. - * r3 = regs pointer, r5 = n. - * - * We only get R1 (stack pointer), NIP (next instruction pointer) - * and LR (link register). These are all we can get in the - * general case without doing complicated stack unwinding, but - * fortunately they are enough to do a stack backtrace, which - * is all we need them for. - */ -_GLOBAL(perf_arch_fetch_caller_regs) - mr r6,r1 - cmpwi r5,0 - mflr r4 - ble 2f - mtctr r5 -1: PPC_LL r6,0(r6) - bdnz 1b - PPC_LL r4,PPC_LR_STKOFF(r6) -2: PPC_LL r7,0(r6) - PPC_LL r7,PPC_LR_STKOFF(r7) - PPC_STL r6,GPR1-STACK_FRAME_OVERHEAD(r3) - PPC_STL r4,_NIP-STACK_FRAME_OVERHEAD(r3) - PPC_STL r7,_LINK-STACK_FRAME_OVERHEAD(r3) - blr diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c deleted file mode 100644 index df78e0236a02..000000000000 --- a/arch/powerpc/kernel/of_device.c +++ /dev/null @@ -1,133 +0,0 @@ -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/mod_devicetable.h> -#include <linux/slab.h> -#include <linux/of_device.h> - -#include <asm/errno.h> -#include <asm/dcr.h> - -static void of_device_make_bus_id(struct of_device *dev) -{ - static atomic_t bus_no_reg_magic; - struct device_node *node = dev->dev.of_node; - const u32 *reg; - u64 addr; - int magic; - - /* - * If it's a DCR based device, use 'd' for native DCRs - * and 'D' for MMIO DCRs. - */ -#ifdef CONFIG_PPC_DCR - reg = of_get_property(node, "dcr-reg", NULL); - if (reg) { -#ifdef CONFIG_PPC_DCR_NATIVE - dev_set_name(&dev->dev, "d%x.%s", *reg, node->name); -#else /* CONFIG_PPC_DCR_NATIVE */ - addr = of_translate_dcr_address(node, *reg, NULL); - if (addr != OF_BAD_ADDR) { - dev_set_name(&dev->dev, "D%llx.%s", - (unsigned long long)addr, node->name); - return; - } -#endif /* !CONFIG_PPC_DCR_NATIVE */ - } -#endif /* CONFIG_PPC_DCR */ - - /* - * For MMIO, get the physical address - */ - reg = of_get_property(node, "reg", NULL); - if (reg) { - addr = of_translate_address(node, reg); - if (addr != OF_BAD_ADDR) { - dev_set_name(&dev->dev, "%llx.%s", - (unsigned long long)addr, node->name); - return; - } - } - - /* - * No BusID, use the node name and add a globally incremented - * counter (and pray...) - */ - magic = atomic_add_return(1, &bus_no_reg_magic); - dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1); -} - -struct of_device *of_device_alloc(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - struct of_device *dev; - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return NULL; - - dev->dev.of_node = of_node_get(np); - dev->dev.dma_mask = &dev->archdata.dma_mask; - dev->dev.parent = parent; - dev->dev.release = of_release_dev; - - if (bus_id) - dev_set_name(&dev->dev, "%s", bus_id); - else - of_device_make_bus_id(dev); - - return dev; -} -EXPORT_SYMBOL(of_device_alloc); - -int of_device_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - struct of_device *ofdev; - const char *compat; - int seen = 0, cplen, sl; - - if (!dev) - return -ENODEV; - - ofdev = to_of_device(dev); - - if (add_uevent_var(env, "OF_NAME=%s", ofdev->dev.of_node->name)) - return -ENOMEM; - - if (add_uevent_var(env, "OF_TYPE=%s", ofdev->dev.of_node->type)) - return -ENOMEM; - - /* Since the compatible field can contain pretty much anything - * it's not really legal to split it out with commas. We split it - * up using a number of environment variables instead. */ - - compat = of_get_property(ofdev->dev.of_node, "compatible", &cplen); - while (compat && *compat && cplen > 0) { - if (add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat)) - return -ENOMEM; - - sl = strlen (compat) + 1; - compat += sl; - cplen -= sl; - seen++; - } - - if (add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen)) - return -ENOMEM; - - /* modalias is trickier, we add it in 2 steps */ - if (add_uevent_var(env, "MODALIAS=")) - return -ENOMEM; - sl = of_device_get_modalias(ofdev, &env->buf[env->buflen-1], - sizeof(env->buf) - env->buflen); - if (sl >= (sizeof(env->buf) - env->buflen)) - return -ENOMEM; - env->buflen += sl; - - return 0; -} -EXPORT_SYMBOL(of_device_uevent); -EXPORT_SYMBOL(of_device_get_modalias); diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index 487a98851ba6..b2c363ef38ad 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -28,207 +28,6 @@ #include <asm/ppc-pci.h> #include <asm/atomic.h> -/* - * The list of OF IDs below is used for matching bus types in the - * system whose devices are to be exposed as of_platform_devices. - * - * This is the default list valid for most platforms. This file provides - * functions who can take an explicit list if necessary though - * - * The search is always performed recursively looking for children of - * the provided device_node and recursively if such a children matches - * a bus type in the list - */ - -static const struct of_device_id of_default_bus_ids[] = { - { .type = "soc", }, - { .compatible = "soc", }, - { .type = "spider", }, - { .type = "axon", }, - { .type = "plb5", }, - { .type = "plb4", }, - { .type = "opb", }, - { .type = "ebc", }, - {}, -}; - -struct bus_type of_platform_bus_type = { - .uevent = of_device_uevent, -}; -EXPORT_SYMBOL(of_platform_bus_type); - -static int __init of_bus_driver_init(void) -{ - return of_bus_type_init(&of_platform_bus_type, "of_platform"); -} - -postcore_initcall(of_bus_driver_init); - -struct of_device* of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - struct of_device *dev; - - dev = of_device_alloc(np, bus_id, parent); - if (!dev) - return NULL; - - dev->archdata.dma_mask = 0xffffffffUL; - dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - - dev->dev.bus = &of_platform_bus_type; - - /* We do not fill the DMA ops for platform devices by default. - * This is currently the responsibility of the platform code - * to do such, possibly using a device notifier - */ - - if (of_device_register(dev) != 0) { - of_device_free(dev); - return NULL; - } - - return dev; -} -EXPORT_SYMBOL(of_platform_device_create); - - - -/** - * of_platform_bus_create - Create an OF device for a bus node and all its - * children. Optionally recursively instanciate matching busses. - * @bus: device node of the bus to instanciate - * @matches: match table, NULL to use the default, OF_NO_DEEP_PROBE to - * disallow recursive creation of child busses - */ -static int of_platform_bus_create(const struct device_node *bus, - const struct of_device_id *matches, - struct device *parent) -{ - struct device_node *child; - struct of_device *dev; - int rc = 0; - - for_each_child_of_node(bus, child) { - pr_debug(" create child: %s\n", child->full_name); - dev = of_platform_device_create(child, NULL, parent); - if (dev == NULL) - rc = -ENOMEM; - else if (!of_match_node(matches, child)) - continue; - if (rc == 0) { - pr_debug(" and sub busses\n"); - rc = of_platform_bus_create(child, matches, &dev->dev); - } if (rc) { - of_node_put(child); - break; - } - } - return rc; -} - -/** - * of_platform_bus_probe - Probe the device-tree for platform busses - * @root: parent of the first level to probe or NULL for the root of the tree - * @matches: match table, NULL to use the default - * @parent: parent to hook devices from, NULL for toplevel - * - * Note that children of the provided root are not instanciated as devices - * unless the specified root itself matches the bus list and is not NULL. - */ - -int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent) -{ - struct device_node *child; - struct of_device *dev; - int rc = 0; - - if (matches == NULL) - matches = of_default_bus_ids; - if (matches == OF_NO_DEEP_PROBE) - return -EINVAL; - if (root == NULL) - root = of_find_node_by_path("/"); - else - of_node_get(root); - - pr_debug("of_platform_bus_probe()\n"); - pr_debug(" starting at: %s\n", root->full_name); - - /* Do a self check of bus type, if there's a match, create - * children - */ - if (of_match_node(matches, root)) { - pr_debug(" root match, create all sub devices\n"); - dev = of_platform_device_create(root, NULL, parent); - if (dev == NULL) { - rc = -ENOMEM; - goto bail; - } - pr_debug(" create all sub busses\n"); - rc = of_platform_bus_create(root, matches, &dev->dev); - goto bail; - } - for_each_child_of_node(root, child) { - if (!of_match_node(matches, child)) - continue; - - pr_debug(" match: %s\n", child->full_name); - dev = of_platform_device_create(child, NULL, parent); - if (dev == NULL) - rc = -ENOMEM; - else - rc = of_platform_bus_create(child, matches, &dev->dev); - if (rc) { - of_node_put(child); - break; - } - } - bail: - of_node_put(root); - return rc; -} -EXPORT_SYMBOL(of_platform_bus_probe); - -static int of_dev_node_match(struct device *dev, void *data) -{ - return to_of_device(dev)->dev.of_node == data; -} - -struct of_device *of_find_device_by_node(struct device_node *np) -{ - struct device *dev; - - dev = bus_find_device(&of_platform_bus_type, - NULL, np, of_dev_node_match); - if (dev) - return to_of_device(dev); - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_node); - -static int of_dev_phandle_match(struct device *dev, void *data) -{ - phandle *ph = data; - return to_of_device(dev)->dev.of_node->phandle == *ph; -} - -struct of_device *of_find_device_by_phandle(phandle ph) -{ - struct device *dev; - - dev = bus_find_device(&of_platform_bus_type, - NULL, &ph, of_dev_phandle_match); - if (dev) - return to_of_device(dev); - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_phandle); - - #ifdef CONFIG_PPC_OF_PLATFORM_PCI /* The probing of PCI controllers from of_platform is currently @@ -237,7 +36,7 @@ EXPORT_SYMBOL(of_find_device_by_phandle); * lacking some bits needed here. */ -static int __devinit of_pci_phb_probe(struct of_device *dev, +static int __devinit of_pci_phb_probe(struct platform_device *dev, const struct of_device_id *match) { struct pci_controller *phb; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 5b38f6ae2b29..9021c4ad4bbd 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/of_address.h> #include <linux/mm.h> #include <linux/list.h> #include <linux/syscalls.h> diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 5c14ffe51258..d301a30445e0 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -410,15 +410,15 @@ static void power_pmu_read(struct perf_event *event) * Therefore we treat them like NMIs. */ do { - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); barrier(); val = read_pmc(event->hw.idx); - } while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev); + } while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev); /* The counters are only 32 bits wide */ delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &event->hw.period_left); + local64_add(delta, &event->count); + local64_sub(delta, &event->hw.period_left); } /* @@ -444,10 +444,10 @@ static void freeze_limited_counters(struct cpu_hw_events *cpuhw, if (!event->hw.idx) continue; val = (event->hw.idx == 5) ? pmc5 : pmc6; - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); event->hw.idx = 0; delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); + local64_add(delta, &event->count); } } @@ -462,7 +462,7 @@ static void thaw_limited_counters(struct cpu_hw_events *cpuhw, event = cpuhw->limited_counter[i]; event->hw.idx = cpuhw->limited_hwidx[i]; val = (event->hw.idx == 5) ? pmc5 : pmc6; - atomic64_set(&event->hw.prev_count, val); + local64_set(&event->hw.prev_count, val); perf_event_update_userpage(event); } } @@ -666,11 +666,11 @@ void hw_perf_enable(void) } val = 0; if (event->hw.sample_period) { - left = atomic64_read(&event->hw.period_left); + left = local64_read(&event->hw.period_left); if (left < 0x80000000L) val = 0x80000000L - left; } - atomic64_set(&event->hw.prev_count, val); + local64_set(&event->hw.prev_count, val); event->hw.idx = idx; write_pmc(idx, val); perf_event_update_userpage(event); @@ -754,7 +754,7 @@ static int power_pmu_enable(struct perf_event *event) * skip the schedulability test here, it will be peformed * at commit time(->commit_txn) as a whole */ - if (cpuhw->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuhw->group_flag & PERF_EVENT_TXN) goto nocheck; if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1)) @@ -845,8 +845,8 @@ static void power_pmu_unthrottle(struct perf_event *event) if (left < 0x80000000L) val = 0x80000000L - left; write_pmc(event->hw.idx, val); - atomic64_set(&event->hw.prev_count, val); - atomic64_set(&event->hw.period_left, left); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); perf_event_update_userpage(event); perf_enable(); local_irq_restore(flags); @@ -861,7 +861,7 @@ void power_pmu_start_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - cpuhw->group_flag |= PERF_EVENT_TXN_STARTED; + cpuhw->group_flag |= PERF_EVENT_TXN; cpuhw->n_txn_start = cpuhw->n_events; } @@ -874,7 +874,7 @@ void power_pmu_cancel_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED; + cpuhw->group_flag &= ~PERF_EVENT_TXN; } /* @@ -900,6 +900,7 @@ int power_pmu_commit_txn(const struct pmu *pmu) for (i = cpuhw->n_txn_start; i < n; ++i) cpuhw->event[i]->hw.config = cpuhw->events[i]; + cpuhw->group_flag &= ~PERF_EVENT_TXN; return 0; } @@ -1111,7 +1112,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) event->hw.config = events[n]; event->hw.event_base = cflags[n]; event->hw.last_period = event->hw.sample_period; - atomic64_set(&event->hw.period_left, event->hw.last_period); + local64_set(&event->hw.period_left, event->hw.last_period); /* * See if we need to reserve the PMU. @@ -1149,16 +1150,16 @@ static void record_and_restart(struct perf_event *event, unsigned long val, int record = 0; /* we don't have to worry about interrupts here */ - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); + local64_add(delta, &event->count); /* * See if the total period for this event has expired, * and update for the next period. */ val = 0; - left = atomic64_read(&event->hw.period_left) - delta; + left = local64_read(&event->hw.period_left) - delta; if (period) { if (left <= 0) { left += period; @@ -1196,8 +1197,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val, } write_pmc(event->hw.idx, val); - atomic64_set(&event->hw.prev_count, val); - atomic64_set(&event->hw.period_left, left); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); perf_event_update_userpage(event); } diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c index babcceecd2ea..1ba45471ae43 100644 --- a/arch/powerpc/kernel/perf_event_fsl_emb.c +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -162,15 +162,15 @@ static void fsl_emb_pmu_read(struct perf_event *event) * Therefore we treat them like NMIs. */ do { - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); barrier(); val = read_pmc(event->hw.idx); - } while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev); + } while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev); /* The counters are only 32 bits wide */ delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &event->hw.period_left); + local64_add(delta, &event->count); + local64_sub(delta, &event->hw.period_left); } /* @@ -296,11 +296,11 @@ static int fsl_emb_pmu_enable(struct perf_event *event) val = 0; if (event->hw.sample_period) { - s64 left = atomic64_read(&event->hw.period_left); + s64 left = local64_read(&event->hw.period_left); if (left < 0x80000000L) val = 0x80000000L - left; } - atomic64_set(&event->hw.prev_count, val); + local64_set(&event->hw.prev_count, val); write_pmc(i, val); perf_event_update_userpage(event); @@ -371,8 +371,8 @@ static void fsl_emb_pmu_unthrottle(struct perf_event *event) if (left < 0x80000000L) val = 0x80000000L - left; write_pmc(event->hw.idx, val); - atomic64_set(&event->hw.prev_count, val); - atomic64_set(&event->hw.period_left, left); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); perf_event_update_userpage(event); perf_enable(); local_irq_restore(flags); @@ -500,7 +500,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) return ERR_PTR(-ENOTSUPP); event->hw.last_period = event->hw.sample_period; - atomic64_set(&event->hw.period_left, event->hw.last_period); + local64_set(&event->hw.period_left, event->hw.last_period); /* * See if we need to reserve the PMU. @@ -541,16 +541,16 @@ static void record_and_restart(struct perf_event *event, unsigned long val, int record = 0; /* we don't have to worry about interrupts here */ - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); + local64_add(delta, &event->count); /* * See if the total period for this event has expired, * and update for the next period. */ val = 0; - left = atomic64_read(&event->hw.period_left) - delta; + left = local64_read(&event->hw.period_left) - delta; if (period) { if (left <= 0) { left += period; @@ -569,6 +569,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, struct perf_sample_data data; perf_sample_data_init(&data, 0); + data.period = event->hw.last_period; if (perf_event_overflow(event, nmi, &data, regs)) { /* @@ -584,8 +585,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val, } write_pmc(event->hw.idx, val); - atomic64_set(&event->hw.prev_count, val); - atomic64_set(&event->hw.period_left, left); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); perf_event_update_userpage(event); } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 551f6713ff42..e78a5add7f15 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1299,3 +1299,14 @@ unsigned long randomize_et_dyn(unsigned long base) return ret; } + +#ifdef CONFIG_SMP +int arch_sd_sibling_asym_packing(void) +{ + if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { + printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); + return SD_ASYM_PACKING; + } + return 0; +} +#endif diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index 8362620c9e6f..88334af038e5 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -6,232 +6,11 @@ #include <linux/module.h> #include <linux/ioport.h> #include <linux/etherdevice.h> +#include <linux/of_address.h> #include <asm/prom.h> #include <asm/pci-bridge.h> -#ifdef DEBUG -#define DBG(fmt...) do { printk(fmt); } while(0) -#else -#define DBG(fmt...) do { } while(0) -#endif - -#ifdef CONFIG_PPC64 -#define PRu64 "%lx" -#else -#define PRu64 "%llx" -#endif - -/* Max address size we deal with */ -#define OF_MAX_ADDR_CELLS 4 -#define OF_CHECK_COUNTS(na, ns) ((na) > 0 && (na) <= OF_MAX_ADDR_CELLS && \ - (ns) > 0) - -static struct of_bus *of_match_bus(struct device_node *np); -static int __of_address_to_resource(struct device_node *dev, - const u32 *addrp, u64 size, unsigned int flags, - struct resource *r); - - -/* Debug utility */ -#ifdef DEBUG -static void of_dump_addr(const char *s, const u32 *addr, int na) -{ - printk("%s", s); - while(na--) - printk(" %08x", *(addr++)); - printk("\n"); -} -#else -static void of_dump_addr(const char *s, const u32 *addr, int na) { } -#endif - - -/* Callbacks for bus specific translators */ -struct of_bus { - const char *name; - const char *addresses; - int (*match)(struct device_node *parent); - void (*count_cells)(struct device_node *child, - int *addrc, int *sizec); - u64 (*map)(u32 *addr, const u32 *range, - int na, int ns, int pna); - int (*translate)(u32 *addr, u64 offset, int na); - unsigned int (*get_flags)(const u32 *addr); -}; - - -/* - * Default translator (generic bus) - */ - -static void of_bus_default_count_cells(struct device_node *dev, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = of_n_addr_cells(dev); - if (sizec) - *sizec = of_n_size_cells(dev); -} - -static u64 of_bus_default_map(u32 *addr, const u32 *range, - int na, int ns, int pna) -{ - u64 cp, s, da; - - cp = of_read_number(range, na); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr, na); - - DBG("OF: default map, cp="PRu64", s="PRu64", da="PRu64"\n", - cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_default_translate(u32 *addr, u64 offset, int na) -{ - u64 a = of_read_number(addr, na); - memset(addr, 0, na * 4); - a += offset; - if (na > 1) - addr[na - 2] = a >> 32; - addr[na - 1] = a & 0xffffffffu; - - return 0; -} - -static unsigned int of_bus_default_get_flags(const u32 *addr) -{ - return IORESOURCE_MEM; -} - - #ifdef CONFIG_PCI -/* - * PCI bus specific translator - */ - -static int of_bus_pci_match(struct device_node *np) -{ - /* "vci" is for the /chaos bridge on 1st-gen PCI powermacs */ - return !strcmp(np->type, "pci") || !strcmp(np->type, "vci"); -} - -static void of_bus_pci_count_cells(struct device_node *np, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = 3; - if (sizec) - *sizec = 2; -} - -static unsigned int of_bus_pci_get_flags(const u32 *addr) -{ - unsigned int flags = 0; - u32 w = addr[0]; - - switch((w >> 24) & 0x03) { - case 0x01: - flags |= IORESOURCE_IO; - break; - case 0x02: /* 32 bits */ - case 0x03: /* 64 bits */ - flags |= IORESOURCE_MEM; - break; - } - if (w & 0x40000000) - flags |= IORESOURCE_PREFETCH; - return flags; -} - -static u64 of_bus_pci_map(u32 *addr, const u32 *range, int na, int ns, int pna) -{ - u64 cp, s, da; - unsigned int af, rf; - - af = of_bus_pci_get_flags(addr); - rf = of_bus_pci_get_flags(range); - - /* Check address type match */ - if ((af ^ rf) & (IORESOURCE_MEM | IORESOURCE_IO)) - return OF_BAD_ADDR; - - /* Read address values, skipping high cell */ - cp = of_read_number(range + 1, na - 1); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr + 1, na - 1); - - DBG("OF: PCI map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_pci_translate(u32 *addr, u64 offset, int na) -{ - return of_bus_default_translate(addr + 1, offset, na - 1); -} - -const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, - unsigned int *flags) -{ - const u32 *prop; - unsigned int psize; - struct device_node *parent; - struct of_bus *bus; - int onesize, i, na, ns; - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - return NULL; - bus = of_match_bus(parent); - if (strcmp(bus->name, "pci")) { - of_node_put(parent); - return NULL; - } - bus->count_cells(dev, &na, &ns); - of_node_put(parent); - if (!OF_CHECK_COUNTS(na, ns)) - return NULL; - - /* Get "reg" or "assigned-addresses" property */ - prop = of_get_property(dev, bus->addresses, &psize); - if (prop == NULL) - return NULL; - psize /= 4; - - onesize = na + ns; - for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) - if ((prop[0] & 0xff) == ((bar_no * 4) + PCI_BASE_ADDRESS_0)) { - if (size) - *size = of_read_number(prop + na, ns); - if (flags) - *flags = bus->get_flags(prop); - return prop; - } - return NULL; -} -EXPORT_SYMBOL(of_get_pci_address); - -int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r) -{ - const u32 *addrp; - u64 size; - unsigned int flags; - - addrp = of_get_pci_address(dev, bar, &size, &flags); - if (addrp == NULL) - return -EINVAL; - return __of_address_to_resource(dev, addrp, size, flags, r); -} -EXPORT_SYMBOL_GPL(of_pci_address_to_resource); - int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) { struct device_node *dn, *ppnode; @@ -313,345 +92,6 @@ int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) EXPORT_SYMBOL_GPL(of_irq_map_pci); #endif /* CONFIG_PCI */ -/* - * ISA bus specific translator - */ - -static int of_bus_isa_match(struct device_node *np) -{ - return !strcmp(np->name, "isa"); -} - -static void of_bus_isa_count_cells(struct device_node *child, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = 2; - if (sizec) - *sizec = 1; -} - -static u64 of_bus_isa_map(u32 *addr, const u32 *range, int na, int ns, int pna) -{ - u64 cp, s, da; - - /* Check address type match */ - if ((addr[0] ^ range[0]) & 0x00000001) - return OF_BAD_ADDR; - - /* Read address values, skipping high cell */ - cp = of_read_number(range + 1, na - 1); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr + 1, na - 1); - - DBG("OF: ISA map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_isa_translate(u32 *addr, u64 offset, int na) -{ - return of_bus_default_translate(addr + 1, offset, na - 1); -} - -static unsigned int of_bus_isa_get_flags(const u32 *addr) -{ - unsigned int flags = 0; - u32 w = addr[0]; - - if (w & 1) - flags |= IORESOURCE_IO; - else - flags |= IORESOURCE_MEM; - return flags; -} - - -/* - * Array of bus specific translators - */ - -static struct of_bus of_busses[] = { -#ifdef CONFIG_PCI - /* PCI */ - { - .name = "pci", - .addresses = "assigned-addresses", - .match = of_bus_pci_match, - .count_cells = of_bus_pci_count_cells, - .map = of_bus_pci_map, - .translate = of_bus_pci_translate, - .get_flags = of_bus_pci_get_flags, - }, -#endif /* CONFIG_PCI */ - /* ISA */ - { - .name = "isa", - .addresses = "reg", - .match = of_bus_isa_match, - .count_cells = of_bus_isa_count_cells, - .map = of_bus_isa_map, - .translate = of_bus_isa_translate, - .get_flags = of_bus_isa_get_flags, - }, - /* Default */ - { - .name = "default", - .addresses = "reg", - .match = NULL, - .count_cells = of_bus_default_count_cells, - .map = of_bus_default_map, - .translate = of_bus_default_translate, - .get_flags = of_bus_default_get_flags, - }, -}; - -static struct of_bus *of_match_bus(struct device_node *np) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(of_busses); i ++) - if (!of_busses[i].match || of_busses[i].match(np)) - return &of_busses[i]; - BUG(); - return NULL; -} - -static int of_translate_one(struct device_node *parent, struct of_bus *bus, - struct of_bus *pbus, u32 *addr, - int na, int ns, int pna, const char *rprop) -{ - const u32 *ranges; - unsigned int rlen; - int rone; - u64 offset = OF_BAD_ADDR; - - /* Normally, an absence of a "ranges" property means we are - * crossing a non-translatable boundary, and thus the addresses - * below the current not cannot be converted to CPU physical ones. - * Unfortunately, while this is very clear in the spec, it's not - * what Apple understood, and they do have things like /uni-n or - * /ht nodes with no "ranges" property and a lot of perfectly - * useable mapped devices below them. Thus we treat the absence of - * "ranges" as equivalent to an empty "ranges" property which means - * a 1:1 translation at that level. It's up to the caller not to try - * to translate addresses that aren't supposed to be translated in - * the first place. --BenH. - */ - ranges = of_get_property(parent, rprop, &rlen); - if (ranges == NULL || rlen == 0) { - offset = of_read_number(addr, na); - memset(addr, 0, pna * 4); - DBG("OF: no ranges, 1:1 translation\n"); - goto finish; - } - - DBG("OF: walking ranges...\n"); - - /* Now walk through the ranges */ - rlen /= 4; - rone = na + pna + ns; - for (; rlen >= rone; rlen -= rone, ranges += rone) { - offset = bus->map(addr, ranges, na, ns, pna); - if (offset != OF_BAD_ADDR) - break; - } - if (offset == OF_BAD_ADDR) { - DBG("OF: not found !\n"); - return 1; - } - memcpy(addr, ranges + na, 4 * pna); - - finish: - of_dump_addr("OF: parent translation for:", addr, pna); - DBG("OF: with offset: "PRu64"\n", offset); - - /* Translate it into parent bus space */ - return pbus->translate(addr, offset, pna); -} - - -/* - * Translate an address from the device-tree into a CPU physical address, - * this walks up the tree and applies the various bus mappings on the - * way. - * - * Note: We consider that crossing any level with #size-cells == 0 to mean - * that translation is impossible (that is we are not dealing with a value - * that can be mapped to a cpu physical address). This is not really specified - * that way, but this is traditionally the way IBM at least do things - */ -u64 __of_translate_address(struct device_node *dev, const u32 *in_addr, - const char *rprop) -{ - struct device_node *parent = NULL; - struct of_bus *bus, *pbus; - u32 addr[OF_MAX_ADDR_CELLS]; - int na, ns, pna, pns; - u64 result = OF_BAD_ADDR; - - DBG("OF: ** translation for device %s **\n", dev->full_name); - - /* Increase refcount at current level */ - of_node_get(dev); - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - goto bail; - bus = of_match_bus(parent); - - /* Cound address cells & copy address locally */ - bus->count_cells(dev, &na, &ns); - if (!OF_CHECK_COUNTS(na, ns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", - dev->full_name); - goto bail; - } - memcpy(addr, in_addr, na * 4); - - DBG("OF: bus is %s (na=%d, ns=%d) on %s\n", - bus->name, na, ns, parent->full_name); - of_dump_addr("OF: translating address:", addr, na); - - /* Translate */ - for (;;) { - /* Switch to parent bus */ - of_node_put(dev); - dev = parent; - parent = of_get_parent(dev); - - /* If root, we have finished */ - if (parent == NULL) { - DBG("OF: reached root node\n"); - result = of_read_number(addr, na); - break; - } - - /* Get new parent bus and counts */ - pbus = of_match_bus(parent); - pbus->count_cells(dev, &pna, &pns); - if (!OF_CHECK_COUNTS(pna, pns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", - dev->full_name); - break; - } - - DBG("OF: parent bus is %s (na=%d, ns=%d) on %s\n", - pbus->name, pna, pns, parent->full_name); - - /* Apply bus translation */ - if (of_translate_one(dev, bus, pbus, addr, na, ns, pna, rprop)) - break; - - /* Complete the move up one level */ - na = pna; - ns = pns; - bus = pbus; - - of_dump_addr("OF: one level translation:", addr, na); - } - bail: - of_node_put(parent); - of_node_put(dev); - - return result; -} - -u64 of_translate_address(struct device_node *dev, const u32 *in_addr) -{ - return __of_translate_address(dev, in_addr, "ranges"); -} -EXPORT_SYMBOL(of_translate_address); - -u64 of_translate_dma_address(struct device_node *dev, const u32 *in_addr) -{ - return __of_translate_address(dev, in_addr, "dma-ranges"); -} -EXPORT_SYMBOL(of_translate_dma_address); - -const u32 *of_get_address(struct device_node *dev, int index, u64 *size, - unsigned int *flags) -{ - const u32 *prop; - unsigned int psize; - struct device_node *parent; - struct of_bus *bus; - int onesize, i, na, ns; - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - return NULL; - bus = of_match_bus(parent); - bus->count_cells(dev, &na, &ns); - of_node_put(parent); - if (!OF_CHECK_COUNTS(na, ns)) - return NULL; - - /* Get "reg" or "assigned-addresses" property */ - prop = of_get_property(dev, bus->addresses, &psize); - if (prop == NULL) - return NULL; - psize /= 4; - - onesize = na + ns; - for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) - if (i == index) { - if (size) - *size = of_read_number(prop + na, ns); - if (flags) - *flags = bus->get_flags(prop); - return prop; - } - return NULL; -} -EXPORT_SYMBOL(of_get_address); - -static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, - u64 size, unsigned int flags, - struct resource *r) -{ - u64 taddr; - - if ((flags & (IORESOURCE_IO | IORESOURCE_MEM)) == 0) - return -EINVAL; - taddr = of_translate_address(dev, addrp); - if (taddr == OF_BAD_ADDR) - return -EINVAL; - memset(r, 0, sizeof(struct resource)); - if (flags & IORESOURCE_IO) { - unsigned long port; - port = pci_address_to_pio(taddr); - if (port == (unsigned long)-1) - return -EINVAL; - r->start = port; - r->end = port + size - 1; - } else { - r->start = taddr; - r->end = taddr + size - 1; - } - r->flags = flags; - r->name = dev->name; - return 0; -} - -int of_address_to_resource(struct device_node *dev, int index, - struct resource *r) -{ - const u32 *addrp; - u64 size; - unsigned int flags; - - addrp = of_get_address(dev, index, &size, &flags); - if (addrp == NULL) - return -EINVAL; - return __of_address_to_resource(dev, addrp, size, flags, r); -} -EXPORT_SYMBOL_GPL(of_address_to_resource); - void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, unsigned long *busno, unsigned long *phys, unsigned long *size) { @@ -678,342 +118,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, *size = of_read_number(dma_window, cells); } -/* - * Interrupt remapper - */ - -static unsigned int of_irq_workarounds; -static struct device_node *of_irq_dflt_pic; - -static struct device_node *of_irq_find_parent(struct device_node *child) -{ - struct device_node *p; - const phandle *parp; - - if (!of_node_get(child)) - return NULL; - - do { - parp = of_get_property(child, "interrupt-parent", NULL); - if (parp == NULL) - p = of_get_parent(child); - else { - if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) - p = of_node_get(of_irq_dflt_pic); - else - p = of_find_node_by_phandle(*parp); - } - of_node_put(child); - child = p; - } while (p && of_get_property(p, "#interrupt-cells", NULL) == NULL); - - return p; -} - -/* This doesn't need to be called if you don't have any special workaround - * flags to pass - */ -void of_irq_map_init(unsigned int flags) -{ - of_irq_workarounds = flags; - - /* OldWorld, don't bother looking at other things */ - if (flags & OF_IMAP_OLDWORLD_MAC) - return; - - /* If we don't have phandles, let's try to locate a default interrupt - * controller (happens when booting with BootX). We do a first match - * here, hopefully, that only ever happens on machines with one - * controller. - */ - if (flags & OF_IMAP_NO_PHANDLE) { - struct device_node *np; - - for_each_node_with_property(np, "interrupt-controller") { - /* Skip /chosen/interrupt-controller */ - if (strcmp(np->name, "chosen") == 0) - continue; - /* It seems like at least one person on this planet wants - * to use BootX on a machine with an AppleKiwi controller - * which happens to pretend to be an interrupt - * controller too. - */ - if (strcmp(np->name, "AppleKiwi") == 0) - continue; - /* I think we found one ! */ - of_irq_dflt_pic = np; - break; - } - } - -} - -int of_irq_map_raw(struct device_node *parent, const u32 *intspec, u32 ointsize, - const u32 *addr, struct of_irq *out_irq) -{ - struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL; - const u32 *tmp, *imap, *imask; - u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0; - int imaplen, match, i; - - DBG("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n", - parent->full_name, intspec[0], intspec[1], ointsize); - - ipar = of_node_get(parent); - - /* First get the #interrupt-cells property of the current cursor - * that tells us how to interpret the passed-in intspec. If there - * is none, we are nice and just walk up the tree - */ - do { - tmp = of_get_property(ipar, "#interrupt-cells", NULL); - if (tmp != NULL) { - intsize = *tmp; - break; - } - tnode = ipar; - ipar = of_irq_find_parent(ipar); - of_node_put(tnode); - } while (ipar); - if (ipar == NULL) { - DBG(" -> no parent found !\n"); - goto fail; - } - - DBG("of_irq_map_raw: ipar=%s, size=%d\n", ipar->full_name, intsize); - - if (ointsize != intsize) - return -EINVAL; - - /* Look for this #address-cells. We have to implement the old linux - * trick of looking for the parent here as some device-trees rely on it - */ - old = of_node_get(ipar); - do { - tmp = of_get_property(old, "#address-cells", NULL); - tnode = of_get_parent(old); - of_node_put(old); - old = tnode; - } while(old && tmp == NULL); - of_node_put(old); - old = NULL; - addrsize = (tmp == NULL) ? 2 : *tmp; - - DBG(" -> addrsize=%d\n", addrsize); - - /* Now start the actual "proper" walk of the interrupt tree */ - while (ipar != NULL) { - /* Now check if cursor is an interrupt-controller and if it is - * then we are done - */ - if (of_get_property(ipar, "interrupt-controller", NULL) != - NULL) { - DBG(" -> got it !\n"); - memcpy(out_irq->specifier, intspec, - intsize * sizeof(u32)); - out_irq->size = intsize; - out_irq->controller = ipar; - of_node_put(old); - return 0; - } - - /* Now look for an interrupt-map */ - imap = of_get_property(ipar, "interrupt-map", &imaplen); - /* No interrupt map, check for an interrupt parent */ - if (imap == NULL) { - DBG(" -> no map, getting parent\n"); - newpar = of_irq_find_parent(ipar); - goto skiplevel; - } - imaplen /= sizeof(u32); - - /* Look for a mask */ - imask = of_get_property(ipar, "interrupt-map-mask", NULL); - - /* If we were passed no "reg" property and we attempt to parse - * an interrupt-map, then #address-cells must be 0. - * Fail if it's not. - */ - if (addr == NULL && addrsize != 0) { - DBG(" -> no reg passed in when needed !\n"); - goto fail; - } - - /* Parse interrupt-map */ - match = 0; - while (imaplen > (addrsize + intsize + 1) && !match) { - /* Compare specifiers */ - match = 1; - for (i = 0; i < addrsize && match; ++i) { - u32 mask = imask ? imask[i] : 0xffffffffu; - match = ((addr[i] ^ imap[i]) & mask) == 0; - } - for (; i < (addrsize + intsize) && match; ++i) { - u32 mask = imask ? imask[i] : 0xffffffffu; - match = - ((intspec[i-addrsize] ^ imap[i]) & mask) == 0; - } - imap += addrsize + intsize; - imaplen -= addrsize + intsize; - - DBG(" -> match=%d (imaplen=%d)\n", match, imaplen); - - /* Get the interrupt parent */ - if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) - newpar = of_node_get(of_irq_dflt_pic); - else - newpar = of_find_node_by_phandle((phandle)*imap); - imap++; - --imaplen; - - /* Check if not found */ - if (newpar == NULL) { - DBG(" -> imap parent not found !\n"); - goto fail; - } - - /* Get #interrupt-cells and #address-cells of new - * parent - */ - tmp = of_get_property(newpar, "#interrupt-cells", NULL); - if (tmp == NULL) { - DBG(" -> parent lacks #interrupt-cells !\n"); - goto fail; - } - newintsize = *tmp; - tmp = of_get_property(newpar, "#address-cells", NULL); - newaddrsize = (tmp == NULL) ? 0 : *tmp; - - DBG(" -> newintsize=%d, newaddrsize=%d\n", - newintsize, newaddrsize); - - /* Check for malformed properties */ - if (imaplen < (newaddrsize + newintsize)) - goto fail; - - imap += newaddrsize + newintsize; - imaplen -= newaddrsize + newintsize; - - DBG(" -> imaplen=%d\n", imaplen); - } - if (!match) - goto fail; - - of_node_put(old); - old = of_node_get(newpar); - addrsize = newaddrsize; - intsize = newintsize; - intspec = imap - intsize; - addr = intspec - addrsize; - - skiplevel: - /* Iterate again with new parent */ - DBG(" -> new parent: %s\n", newpar ? newpar->full_name : "<>"); - of_node_put(ipar); - ipar = newpar; - newpar = NULL; - } - fail: - of_node_put(ipar); - of_node_put(old); - of_node_put(newpar); - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(of_irq_map_raw); - -#if defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32) -static int of_irq_map_oldworld(struct device_node *device, int index, - struct of_irq *out_irq) -{ - const u32 *ints = NULL; - int intlen; - - /* - * Old machines just have a list of interrupt numbers - * and no interrupt-controller nodes. We also have dodgy - * cases where the APPL,interrupts property is completely - * missing behind pci-pci bridges and we have to get it - * from the parent (the bridge itself, as apple just wired - * everything together on these) - */ - while (device) { - ints = of_get_property(device, "AAPL,interrupts", &intlen); - if (ints != NULL) - break; - device = device->parent; - if (device && strcmp(device->type, "pci") != 0) - break; - } - if (ints == NULL) - return -EINVAL; - intlen /= sizeof(u32); - - if (index >= intlen) - return -EINVAL; - - out_irq->controller = NULL; - out_irq->specifier[0] = ints[index]; - out_irq->size = 1; - - return 0; -} -#else /* defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32) */ -static int of_irq_map_oldworld(struct device_node *device, int index, - struct of_irq *out_irq) -{ - return -EINVAL; -} -#endif /* !(defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32)) */ - -int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq) -{ - struct device_node *p; - const u32 *intspec, *tmp, *addr; - u32 intsize, intlen; - int res = -EINVAL; - - DBG("of_irq_map_one: dev=%s, index=%d\n", device->full_name, index); - - /* OldWorld mac stuff is "special", handle out of line */ - if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) - return of_irq_map_oldworld(device, index, out_irq); - - /* Get the interrupts property */ - intspec = of_get_property(device, "interrupts", &intlen); - if (intspec == NULL) - return -EINVAL; - intlen /= sizeof(u32); - - /* Get the reg property (if any) */ - addr = of_get_property(device, "reg", NULL); - - /* Look for the interrupt parent. */ - p = of_irq_find_parent(device); - if (p == NULL) - return -EINVAL; - - /* Get size of interrupt specifier */ - tmp = of_get_property(p, "#interrupt-cells", NULL); - if (tmp == NULL) - goto out; - intsize = *tmp; - - DBG(" intsize=%d intlen=%d\n", intsize, intlen); - - /* Check index */ - if ((index + 1) * intsize > intlen) - goto out; - - /* Get new specifier and map it */ - res = of_irq_map_raw(p, intspec + index * intsize, intsize, - addr, out_irq); -out: - of_node_put(p); - return res; -} -EXPORT_SYMBOL_GPL(of_irq_map_one); - /** * Search the device tree for the best MAC address to use. 'mac-address' is * checked first, because that is supposed to contain to "most recent" MAC @@ -1051,29 +155,3 @@ const void *of_get_mac_address(struct device_node *np) return NULL; } EXPORT_SYMBOL(of_get_mac_address); - -int of_irq_to_resource(struct device_node *dev, int index, struct resource *r) -{ - int irq = irq_of_parse_and_map(dev, index); - - /* Only dereference the resource if both the - * resource and the irq are valid. */ - if (r && irq != NO_IRQ) { - r->start = r->end = irq; - r->flags = IORESOURCE_IRQ; - } - - return irq; -} -EXPORT_SYMBOL_GPL(of_irq_to_resource); - -void __iomem *of_iomap(struct device_node *np, int index) -{ - struct resource res; - - if (of_address_to_resource(np, index, &res)) - return NULL; - - return ioremap(res.start, 1 + res.end - res.start); -} -EXPORT_SYMBOL(of_iomap); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 70decd8068ca..15ade0d7bbb2 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -714,16 +714,9 @@ static struct notifier_block ppc_dflt_plat_bus_notifier = { .priority = INT_MAX, }; -static struct notifier_block ppc_dflt_of_bus_notifier = { - .notifier_call = ppc_dflt_bus_notify, - .priority = INT_MAX, -}; - static int __init setup_bus_notifier(void) { bus_register_notifier(&platform_bus_type, &ppc_dflt_plat_bus_notifier); - bus_register_notifier(&of_platform_bus_type, &ppc_dflt_of_bus_notifier); - return 0; } diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c index e1c5cd6650b1..5b243bd3eb3b 100644 --- a/arch/powerpc/platforms/512x/clock.c +++ b/arch/powerpc/platforms/512x/clock.c @@ -678,7 +678,7 @@ static void psc_clks_init(void) { struct device_node *np; const u32 *cell_index; - struct of_device *ofdev; + struct platform_device *ofdev; for_each_compatible_node(np, NULL, "fsl,mpc5121-psc") { cell_index = of_get_property(np, "cell-index", NULL); diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c index 6d584f4e3c9a..de55bc0584b5 100644 --- a/arch/powerpc/platforms/52xx/lite5200.c +++ b/arch/powerpc/platforms/52xx/lite5200.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/root_dev.h> #include <linux/initrd.h> #include <asm/time.h> diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c b/arch/powerpc/platforms/52xx/mpc52xx_gpio.c index ca5305a5bd61..0dad9a935eb5 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpio.c @@ -147,26 +147,25 @@ mpc52xx_wkup_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) return 0; } -static int __devinit mpc52xx_wkup_gpiochip_probe(struct of_device *ofdev, +static int __devinit mpc52xx_wkup_gpiochip_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct mpc52xx_gpiochip *chip; struct mpc52xx_gpio_wkup __iomem *regs; - struct of_gpio_chip *ofchip; + struct gpio_chip *gc; int ret; chip = kzalloc(sizeof(*chip), GFP_KERNEL); if (!chip) return -ENOMEM; - ofchip = &chip->mmchip.of_gc; + gc = &chip->mmchip.gc; - ofchip->gpio_cells = 2; - ofchip->gc.ngpio = 8; - ofchip->gc.direction_input = mpc52xx_wkup_gpio_dir_in; - ofchip->gc.direction_output = mpc52xx_wkup_gpio_dir_out; - ofchip->gc.get = mpc52xx_wkup_gpio_get; - ofchip->gc.set = mpc52xx_wkup_gpio_set; + gc->ngpio = 8; + gc->direction_input = mpc52xx_wkup_gpio_dir_in; + gc->direction_output = mpc52xx_wkup_gpio_dir_out; + gc->get = mpc52xx_wkup_gpio_get; + gc->set = mpc52xx_wkup_gpio_set; ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); if (ret) @@ -180,7 +179,7 @@ static int __devinit mpc52xx_wkup_gpiochip_probe(struct of_device *ofdev, return 0; } -static int mpc52xx_gpiochip_remove(struct of_device *ofdev) +static int mpc52xx_gpiochip_remove(struct platform_device *ofdev) { return -EBUSY; } @@ -311,11 +310,11 @@ mpc52xx_simple_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) return 0; } -static int __devinit mpc52xx_simple_gpiochip_probe(struct of_device *ofdev, +static int __devinit mpc52xx_simple_gpiochip_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct mpc52xx_gpiochip *chip; - struct of_gpio_chip *ofchip; + struct gpio_chip *gc; struct mpc52xx_gpio __iomem *regs; int ret; @@ -323,14 +322,13 @@ static int __devinit mpc52xx_simple_gpiochip_probe(struct of_device *ofdev, if (!chip) return -ENOMEM; - ofchip = &chip->mmchip.of_gc; + gc = &chip->mmchip.gc; - ofchip->gpio_cells = 2; - ofchip->gc.ngpio = 32; - ofchip->gc.direction_input = mpc52xx_simple_gpio_dir_in; - ofchip->gc.direction_output = mpc52xx_simple_gpio_dir_out; - ofchip->gc.get = mpc52xx_simple_gpio_get; - ofchip->gc.set = mpc52xx_simple_gpio_set; + gc->ngpio = 32; + gc->direction_input = mpc52xx_simple_gpio_dir_in; + gc->direction_output = mpc52xx_simple_gpio_dir_out; + gc->get = mpc52xx_simple_gpio_get; + gc->set = mpc52xx_simple_gpio_set; ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); if (ret) diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index 46c93578cbf0..fea833e18ad5 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -78,7 +78,7 @@ MODULE_LICENSE("GPL"); * @dev: pointer to device structure * @regs: virtual address of GPT registers * @lock: spinlock to coordinate between different functions. - * @of_gc: of_gpio_chip instance structure; used when GPIO is enabled + * @gc: gpio_chip instance structure; used when GPIO is enabled * @irqhost: Pointer to irq_host instance; used when IRQ mode is supported * @wdt_mode: only relevant for gpt0: bit 0 (MPC52xx_GPT_CAN_WDT) indicates * if the gpt may be used as wdt, bit 1 (MPC52xx_GPT_IS_WDT) indicates @@ -94,7 +94,7 @@ struct mpc52xx_gpt_priv { u8 wdt_mode; #if defined(CONFIG_GPIOLIB) - struct of_gpio_chip of_gc; + struct gpio_chip gc; #endif }; @@ -280,7 +280,7 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) #if defined(CONFIG_GPIOLIB) static inline struct mpc52xx_gpt_priv *gc_to_mpc52xx_gpt(struct gpio_chip *gc) { - return container_of(to_of_gpio_chip(gc), struct mpc52xx_gpt_priv,of_gc); + return container_of(gc, struct mpc52xx_gpt_priv, gc); } static int mpc52xx_gpt_gpio_get(struct gpio_chip *gc, unsigned int gpio) @@ -336,28 +336,25 @@ mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) if (!of_find_property(node, "gpio-controller", NULL)) return; - gpt->of_gc.gc.label = kstrdup(node->full_name, GFP_KERNEL); - if (!gpt->of_gc.gc.label) { + gpt->gc.label = kstrdup(node->full_name, GFP_KERNEL); + if (!gpt->gc.label) { dev_err(gpt->dev, "out of memory\n"); return; } - gpt->of_gc.gpio_cells = 2; - gpt->of_gc.gc.ngpio = 1; - gpt->of_gc.gc.direction_input = mpc52xx_gpt_gpio_dir_in; - gpt->of_gc.gc.direction_output = mpc52xx_gpt_gpio_dir_out; - gpt->of_gc.gc.get = mpc52xx_gpt_gpio_get; - gpt->of_gc.gc.set = mpc52xx_gpt_gpio_set; - gpt->of_gc.gc.base = -1; - gpt->of_gc.xlate = of_gpio_simple_xlate; - node->data = &gpt->of_gc; - of_node_get(node); + gpt->gc.ngpio = 1; + gpt->gc.direction_input = mpc52xx_gpt_gpio_dir_in; + gpt->gc.direction_output = mpc52xx_gpt_gpio_dir_out; + gpt->gc.get = mpc52xx_gpt_gpio_get; + gpt->gc.set = mpc52xx_gpt_gpio_set; + gpt->gc.base = -1; + gpt->gc.of_node = node; /* Setup external pin in GPIO mode */ clrsetbits_be32(&gpt->regs->mode, MPC52xx_GPT_MODE_MS_MASK, MPC52xx_GPT_MODE_MS_GPIO); - rc = gpiochip_add(&gpt->of_gc.gc); + rc = gpiochip_add(&gpt->gc); if (rc) dev_err(gpt->dev, "gpiochip_add() failed; rc=%i\n", rc); @@ -723,7 +720,7 @@ static inline int mpc52xx_gpt_wdt_setup(struct mpc52xx_gpt_priv *gpt, /* --------------------------------------------------------------------- * of_platform bus binding code */ -static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev, +static int __devinit mpc52xx_gpt_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct mpc52xx_gpt_priv *gpt; @@ -769,7 +766,7 @@ static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev, return 0; } -static int mpc52xx_gpt_remove(struct of_device *ofdev) +static int mpc52xx_gpt_remove(struct platform_device *ofdev) { return -EBUSY; } diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c index e86aec644501..f4ac213c89c0 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c @@ -436,8 +436,8 @@ void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req) } EXPORT_SYMBOL(mpc52xx_lpbfifo_abort); -static int __devinit -mpc52xx_lpbfifo_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit mpc52xx_lpbfifo_probe(struct platform_device *op, + const struct of_device_id *match) { struct resource res; int rc = -ENOMEM; @@ -507,7 +507,7 @@ mpc52xx_lpbfifo_probe(struct of_device *op, const struct of_device_id *match) } -static int __devexit mpc52xx_lpbfifo_remove(struct of_device *op) +static int __devexit mpc52xx_lpbfifo_remove(struct platform_device *op) { if (lpbfifo.dev != &op->dev) return 0; diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c index 9f2e52b36f91..1565e0446dc8 100644 --- a/arch/powerpc/platforms/82xx/ep8248e.c +++ b/arch/powerpc/platforms/82xx/ep8248e.c @@ -111,7 +111,7 @@ static struct mdiobb_ctrl ep8248e_mdio_ctrl = { .ops = &ep8248e_mdio_ops, }; -static int __devinit ep8248e_mdio_probe(struct of_device *ofdev, +static int __devinit ep8248e_mdio_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct mii_bus *bus; @@ -154,7 +154,7 @@ err_free_bus: return ret; } -static int ep8248e_mdio_remove(struct of_device *ofdev) +static int ep8248e_mdio_remove(struct platform_device *ofdev) { BUG(); return 0; diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index d119a7c1c17a..70798ac911ef 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -35,9 +35,8 @@ struct mcu { struct mutex lock; - struct device_node *np; struct i2c_client *client; - struct of_gpio_chip of_gc; + struct gpio_chip gc; u8 reg_ctrl; }; @@ -56,8 +55,7 @@ static void mcu_power_off(void) static void mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) { - struct of_gpio_chip *of_gc = to_of_gpio_chip(gc); - struct mcu *mcu = container_of(of_gc, struct mcu, of_gc); + struct mcu *mcu = container_of(gc, struct mcu, gc); u8 bit = 1 << (4 + gpio); mutex_lock(&mcu->lock); @@ -79,9 +77,7 @@ static int mcu_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) static int mcu_gpiochip_add(struct mcu *mcu) { struct device_node *np; - struct of_gpio_chip *of_gc = &mcu->of_gc; - struct gpio_chip *gc = &of_gc->gc; - int ret; + struct gpio_chip *gc = &mcu->gc; np = of_find_compatible_node(NULL, NULL, "fsl,mcu-mpc8349emitx"); if (!np) @@ -94,32 +90,14 @@ static int mcu_gpiochip_add(struct mcu *mcu) gc->base = -1; gc->set = mcu_gpio_set; gc->direction_output = mcu_gpio_dir_out; - of_gc->gpio_cells = 2; - of_gc->xlate = of_gpio_simple_xlate; + gc->of_node = np; - np->data = of_gc; - mcu->np = np; - - /* - * We don't want to lose the node, its ->data and ->full_name... - * So, if succeeded, we don't put the node here. - */ - ret = gpiochip_add(gc); - if (ret) - of_node_put(np); - return ret; + return gpiochip_add(gc); } static int mcu_gpiochip_remove(struct mcu *mcu) { - int ret; - - ret = gpiochip_remove(&mcu->of_gc.gc); - if (ret) - return ret; - of_node_put(mcu->np); - - return 0; + return gpiochip_remove(&mcu->gc); } static int __devinit mcu_probe(struct i2c_client *client, @@ -182,10 +160,16 @@ static const struct i2c_device_id mcu_ids[] = { }; MODULE_DEVICE_TABLE(i2c, mcu_ids); +static struct of_device_id mcu_of_match_table[] __devinitdata = { + { .compatible = "fsl,mcu-mpc8349emitx", }, + { }, +}; + static struct i2c_driver mcu_driver = { .driver = { .name = "mcu-mpc8349emitx", .owner = THIS_MODULE, + .of_match_table = mcu_of_match_table, }, .probe = mcu_probe, .remove = __devexit_p(mcu_remove), diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index ebe6c3537209..75ae77f1af6a 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -99,7 +99,7 @@ struct pmc_type { int has_deep_sleep; }; -static struct of_device *pmc_dev; +static struct platform_device *pmc_dev; static int has_deep_sleep, deep_sleeping; static int pmc_irq; static struct mpc83xx_pmc __iomem *pmc_regs; @@ -318,7 +318,7 @@ static struct platform_suspend_ops mpc83xx_suspend_ops = { .end = mpc83xx_suspend_end, }; -static int pmc_probe(struct of_device *ofdev, +static int pmc_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct device_node *np = ofdev->dev.of_node; @@ -396,7 +396,7 @@ out: return ret; } -static int pmc_remove(struct of_device *ofdev) +static int pmc_remove(struct platform_device *ofdev) { return -EPERM; }; diff --git a/arch/powerpc/platforms/86xx/gef_gpio.c b/arch/powerpc/platforms/86xx/gef_gpio.c index b8cb08dbd89c..4ff7b1e7bbad 100644 --- a/arch/powerpc/platforms/86xx/gef_gpio.c +++ b/arch/powerpc/platforms/86xx/gef_gpio.c @@ -118,12 +118,12 @@ static int __init gef_gpio_init(void) } /* Setup pointers to chip functions */ - gef_gpio_chip->of_gc.gpio_cells = 2; - gef_gpio_chip->of_gc.gc.ngpio = 19; - gef_gpio_chip->of_gc.gc.direction_input = gef_gpio_dir_in; - gef_gpio_chip->of_gc.gc.direction_output = gef_gpio_dir_out; - gef_gpio_chip->of_gc.gc.get = gef_gpio_get; - gef_gpio_chip->of_gc.gc.set = gef_gpio_set; + gef_gpio_chip->gc.of_gpio_n_cells = 2; + gef_gpio_chip->gc.ngpio = 19; + gef_gpio_chip->gc.direction_input = gef_gpio_dir_in; + gef_gpio_chip->gc.direction_output = gef_gpio_dir_out; + gef_gpio_chip->gc.get = gef_gpio_get; + gef_gpio_chip->gc.set = gef_gpio_set; /* This function adds a memory mapped GPIO chip */ retval = of_mm_gpiochip_add(np, gef_gpio_chip); @@ -146,12 +146,12 @@ static int __init gef_gpio_init(void) } /* Setup pointers to chip functions */ - gef_gpio_chip->of_gc.gpio_cells = 2; - gef_gpio_chip->of_gc.gc.ngpio = 6; - gef_gpio_chip->of_gc.gc.direction_input = gef_gpio_dir_in; - gef_gpio_chip->of_gc.gc.direction_output = gef_gpio_dir_out; - gef_gpio_chip->of_gc.gc.get = gef_gpio_get; - gef_gpio_chip->of_gc.gc.set = gef_gpio_set; + gef_gpio_chip->gc.of_gpio_n_cells = 2; + gef_gpio_chip->gc.ngpio = 6; + gef_gpio_chip->gc.direction_input = gef_gpio_dir_in; + gef_gpio_chip->gc.direction_output = gef_gpio_dir_out; + gef_gpio_chip->gc.get = gef_gpio_get; + gef_gpio_chip->gc.set = gef_gpio_set; /* This function adds a memory mapped GPIO chip */ retval = of_mm_gpiochip_add(np, gef_gpio_chip); diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c index fb4eb0df054c..03aabc0e16ac 100644 --- a/arch/powerpc/platforms/amigaone/setup.c +++ b/arch/powerpc/platforms/amigaone/setup.c @@ -13,12 +13,13 @@ */ #include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/seq_file.h> #include <generated/utsrelease.h> #include <asm/machdep.h> #include <asm/cputable.h> -#include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/i8259.h> #include <asm/time.h> diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 6257e5378615..97085530aa63 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -328,7 +328,7 @@ static struct irq_host_ops msic_host_ops = { .map = msic_host_map, }; -static int axon_msi_shutdown(struct of_device *device) +static int axon_msi_shutdown(struct platform_device *device) { struct axon_msic *msic = dev_get_drvdata(&device->dev); u32 tmp; @@ -342,7 +342,7 @@ static int axon_msi_shutdown(struct of_device *device) return 0; } -static int axon_msi_probe(struct of_device *device, +static int axon_msi_probe(struct platform_device *device, const struct of_device_id *device_id) { struct device_node *dn = device->dev.of_node; diff --git a/arch/powerpc/platforms/cell/beat_iommu.c b/arch/powerpc/platforms/cell/beat_iommu.c index 39d361c5c6d2..beec405eb6f8 100644 --- a/arch/powerpc/platforms/cell/beat_iommu.c +++ b/arch/powerpc/platforms/cell/beat_iommu.c @@ -108,7 +108,7 @@ static int __init celleb_init_iommu(void) celleb_init_direct_mapping(); set_pci_dma_ops(&dma_direct_ops); ppc_md.pci_dma_dev_setup = celleb_pci_dma_dev_setup; - bus_register_notifier(&of_platform_bus_type, &celleb_of_bus_notifier); + bus_register_notifier(&platform_bus_type, &celleb_of_bus_notifier); return 0; } diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 3712900471ba..58b13ce3847e 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -1204,7 +1204,7 @@ static int __init cell_iommu_init(void) /* Register callbacks on OF platform device addition/removal * to handle linking them to the right DMA operations */ - bus_register_notifier(&of_platform_bus_type, &cell_of_bus_notifier); + bus_register_notifier(&platform_bus_type, &cell_of_bus_notifier); return 0; } diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c index c5ce02e84c8e..1b5749042756 100644 --- a/arch/powerpc/platforms/cell/qpace_setup.c +++ b/arch/powerpc/platforms/cell/qpace_setup.c @@ -61,12 +61,24 @@ static void qpace_progress(char *s, unsigned short hex) printk("*** %04x : %s\n", hex, s ? s : ""); } +static const struct of_device_id qpace_bus_ids[] __initdata = { + { .type = "soc", }, + { .compatible = "soc", }, + { .type = "spider", }, + { .type = "axon", }, + { .type = "plb5", }, + { .type = "plb4", }, + { .type = "opb", }, + { .type = "ebc", }, + {}, +}; + static int __init qpace_publish_devices(void) { int node; /* Publish OF platform devices for southbridge IOs */ - of_platform_bus_probe(NULL, NULL, NULL); + of_platform_bus_probe(NULL, qpace_bus_ids, NULL); /* There is no device for the MIC memory controller, thus we create * a platform device for it to attach the EDAC driver to. diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index 50385db586bd..691995761b3d 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -141,6 +141,18 @@ static int __devinit cell_setup_phb(struct pci_controller *phb) return 0; } +static const struct of_device_id cell_bus_ids[] __initdata = { + { .type = "soc", }, + { .compatible = "soc", }, + { .type = "spider", }, + { .type = "axon", }, + { .type = "plb5", }, + { .type = "plb4", }, + { .type = "opb", }, + { .type = "ebc", }, + {}, +}; + static int __init cell_publish_devices(void) { struct device_node *root = of_find_node_by_path("/"); @@ -148,7 +160,7 @@ static int __init cell_publish_devices(void) int node; /* Publish OF platform devices for southbridge IOs */ - of_platform_bus_probe(NULL, NULL, NULL); + of_platform_bus_probe(NULL, cell_bus_ids, NULL); /* On spider based blades, we need to manually create the OF * platform devices for the PCI host bridges diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c index d2c1d497846e..33e5fc7334fc 100644 --- a/arch/powerpc/platforms/iseries/mf.c +++ b/arch/powerpc/platforms/iseries/mf.c @@ -30,6 +30,7 @@ #include <linux/init.h> #include <linux/completion.h> #include <linux/delay.h> +#include <linux/proc_fs.h> #include <linux/dma-mapping.h> #include <linux/bcd.h> #include <linux/rtc.h> diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c index 627ee089e75d..a5d907b5a4c2 100644 --- a/arch/powerpc/platforms/pasemi/gpio_mdio.c +++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c @@ -216,7 +216,7 @@ static int gpio_mdio_reset(struct mii_bus *bus) } -static int __devinit gpio_mdio_probe(struct of_device *ofdev, +static int __devinit gpio_mdio_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct device *dev = &ofdev->dev; @@ -275,7 +275,7 @@ out: } -static int gpio_mdio_remove(struct of_device *dev) +static int gpio_mdio_remove(struct platform_device *dev) { struct mii_bus *bus = dev_get_drvdata(&dev->dev); diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index 79bd3e89dbaf..39df6ab1735a 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -21,6 +21,8 @@ #include <linux/delay.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/spinlock.h> #include <linux/adb.h> #include <linux/pmu.h> diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 630a533d0e59..890d5f72b198 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -46,6 +46,10 @@ struct pmac_irq_hw { unsigned int level; }; +/* Workaround flags for 32bit powermac machines */ +unsigned int of_irq_workarounds; +struct device_node *of_irq_dflt_pic; + /* Default addresses */ static volatile struct pmac_irq_hw __iomem *pmac_irq_hw[4]; @@ -428,6 +432,42 @@ static void __init pmac_pic_probe_oldstyle(void) setup_irq(irq_create_mapping(NULL, 20), &xmon_action); #endif } + +int of_irq_map_oldworld(struct device_node *device, int index, + struct of_irq *out_irq) +{ + const u32 *ints = NULL; + int intlen; + + /* + * Old machines just have a list of interrupt numbers + * and no interrupt-controller nodes. We also have dodgy + * cases where the APPL,interrupts property is completely + * missing behind pci-pci bridges and we have to get it + * from the parent (the bridge itself, as apple just wired + * everything together on these) + */ + while (device) { + ints = of_get_property(device, "AAPL,interrupts", &intlen); + if (ints != NULL) + break; + device = device->parent; + if (device && strcmp(device->type, "pci") != 0) + break; + } + if (ints == NULL) + return -EINVAL; + intlen /= sizeof(u32); + + if (index >= intlen) + return -EINVAL; + + out_irq->controller = NULL; + out_irq->specifier[0] = ints[index]; + out_irq->size = 1; + + return 0; +} #endif /* CONFIG_PPC32 */ static void pmac_u3_cascade(unsigned int irq, struct irq_desc *desc) @@ -559,19 +599,39 @@ static int __init pmac_pic_probe_mpic(void) void __init pmac_pic_init(void) { - unsigned int flags = 0; - /* We configure the OF parsing based on our oldworld vs. newworld * platform type and wether we were booted by BootX. */ #ifdef CONFIG_PPC32 if (!pmac_newworld) - flags |= OF_IMAP_OLDWORLD_MAC; + of_irq_workarounds |= OF_IMAP_OLDWORLD_MAC; if (of_get_property(of_chosen, "linux,bootx", NULL) != NULL) - flags |= OF_IMAP_NO_PHANDLE; -#endif /* CONFIG_PPC_32 */ + of_irq_workarounds |= OF_IMAP_NO_PHANDLE; - of_irq_map_init(flags); + /* If we don't have phandles on a newworld, then try to locate a + * default interrupt controller (happens when booting with BootX). + * We do a first match here, hopefully, that only ever happens on + * machines with one controller. + */ + if (pmac_newworld && (of_irq_workarounds & OF_IMAP_NO_PHANDLE)) { + struct device_node *np; + + for_each_node_with_property(np, "interrupt-controller") { + /* Skip /chosen/interrupt-controller */ + if (strcmp(np->name, "chosen") == 0) + continue; + /* It seems like at least one person wants + * to use BootX on a machine with an AppleKiwi + * controller which happens to pretend to be an + * interrupt controller too. */ + if (strcmp(np->name, "AppleKiwi") == 0) + continue; + /* I think we found one ! */ + of_irq_dflt_pic = np; + break; + } + } +#endif /* CONFIG_PPC32 */ /* We first try to detect Apple's new Core99 chipset, since mac-io * is quite different on those machines and contains an IBM MPIC2. diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 402d2212162f..2659a60bd7b8 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -60,7 +60,7 @@ static int azfs_major, azfs_minor; struct axon_ram_bank { - struct of_device *device; + struct platform_device *device; struct gendisk *disk; unsigned int irq_id; unsigned long ph_addr; @@ -72,7 +72,7 @@ struct axon_ram_bank { static ssize_t axon_ram_sysfs_ecc(struct device *dev, struct device_attribute *attr, char *buf) { - struct of_device *device = to_of_device(dev); + struct platform_device *device = to_platform_device(dev); struct axon_ram_bank *bank = device->dev.platform_data; BUG_ON(!bank); @@ -90,7 +90,7 @@ static DEVICE_ATTR(ecc, S_IRUGO, axon_ram_sysfs_ecc, NULL); static irqreturn_t axon_ram_irq_handler(int irq, void *dev) { - struct of_device *device = dev; + struct platform_device *device = dev; struct axon_ram_bank *bank = device->dev.platform_data; BUG_ON(!bank); @@ -174,8 +174,8 @@ static const struct block_device_operations axon_ram_devops = { * axon_ram_probe - probe() method for platform driver * @device, @device_id: see of_platform_driver method */ -static int -axon_ram_probe(struct of_device *device, const struct of_device_id *device_id) +static int axon_ram_probe(struct platform_device *device, + const struct of_device_id *device_id) { static int axon_ram_bank_id = -1; struct axon_ram_bank *bank; @@ -304,7 +304,7 @@ failed: * @device: see of_platform_driver method */ static int -axon_ram_remove(struct of_device *device) +axon_ram_remove(struct platform_device *device) { struct axon_ram_bank *bank = device->dev.platform_data; diff --git a/arch/powerpc/sysdev/bestcomm/bestcomm.c b/arch/powerpc/sysdev/bestcomm/bestcomm.c index a7c5c470af14..650256115064 100644 --- a/arch/powerpc/sysdev/bestcomm/bestcomm.c +++ b/arch/powerpc/sysdev/bestcomm/bestcomm.c @@ -365,8 +365,8 @@ bcom_engine_cleanup(void) /* OF platform driver */ /* ======================================================================== */ -static int __devinit -mpc52xx_bcom_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit mpc52xx_bcom_probe(struct platform_device *op, + const struct of_device_id *match) { struct device_node *ofn_sram; struct resource res_bcom; @@ -461,8 +461,7 @@ error_ofput: } -static int -mpc52xx_bcom_remove(struct of_device *op) +static int mpc52xx_bcom_remove(struct platform_device *op) { /* Clean up the engine */ bcom_engine_cleanup(); diff --git a/arch/powerpc/sysdev/bestcomm/sram.c b/arch/powerpc/sysdev/bestcomm/sram.c index 5d74ef7a651f..1225012a681a 100644 --- a/arch/powerpc/sysdev/bestcomm/sram.c +++ b/arch/powerpc/sysdev/bestcomm/sram.c @@ -11,6 +11,7 @@ * kind, whether express or implied. */ +#include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c index 8d103ca6d6ab..00852124ff4a 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/sysdev/cpm1.c @@ -621,7 +621,6 @@ int cpm1_gpiochip_add16(struct device_node *np) { struct cpm1_gpio16_chip *cpm1_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL); @@ -631,11 +630,9 @@ int cpm1_gpiochip_add16(struct device_node *np) spin_lock_init(&cpm1_gc->lock); mm_gc = &cpm1_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = cpm1_gpio16_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = 16; gc->direction_input = cpm1_gpio16_dir_in; gc->direction_output = cpm1_gpio16_dir_out; @@ -745,7 +742,6 @@ int cpm1_gpiochip_add32(struct device_node *np) { struct cpm1_gpio32_chip *cpm1_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL); @@ -755,11 +751,9 @@ int cpm1_gpiochip_add32(struct device_node *np) spin_lock_init(&cpm1_gc->lock); mm_gc = &cpm1_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = cpm1_gpio32_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = 32; gc->direction_input = cpm1_gpio32_dir_in; gc->direction_output = cpm1_gpio32_dir_out; diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c index 88b9812c854f..2b69aa0315b3 100644 --- a/arch/powerpc/sysdev/cpm_common.c +++ b/arch/powerpc/sysdev/cpm_common.c @@ -325,7 +325,6 @@ int cpm2_gpiochip_add32(struct device_node *np) { struct cpm2_gpio32_chip *cpm2_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; cpm2_gc = kzalloc(sizeof(*cpm2_gc), GFP_KERNEL); @@ -335,11 +334,9 @@ int cpm2_gpiochip_add32(struct device_node *np) spin_lock_init(&cpm2_gc->lock); mm_gc = &cpm2_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = cpm2_gpio32_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = 32; gc->direction_input = cpm2_gpio32_dir_in; gc->direction_output = cpm2_gpio32_dir_out; diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c index eca4545dd52e..7dd2885321ad 100644 --- a/arch/powerpc/sysdev/fsl_gtm.c +++ b/arch/powerpc/sysdev/fsl_gtm.c @@ -14,6 +14,7 @@ */ #include <linux/kernel.h> +#include <linux/err.h> #include <linux/errno.h> #include <linux/list.h> #include <linux/io.h> diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 962c2d8dd8d9..87991d3abbab 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -250,7 +250,7 @@ unlock: raw_spin_unlock(&desc->lock); } -static int fsl_of_msi_remove(struct of_device *ofdev) +static int fsl_of_msi_remove(struct platform_device *ofdev) { struct fsl_msi *msi = ofdev->dev.platform_data; int virq, i; @@ -274,7 +274,7 @@ static int fsl_of_msi_remove(struct of_device *ofdev) return 0; } -static int __devinit fsl_of_msi_probe(struct of_device *dev, +static int __devinit fsl_of_msi_probe(struct platform_device *dev, const struct of_device_id *match) { struct fsl_msi *msi; diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c index 9082eb921ad9..44de8559c975 100644 --- a/arch/powerpc/sysdev/fsl_pmc.c +++ b/arch/powerpc/sysdev/fsl_pmc.c @@ -58,7 +58,8 @@ static struct platform_suspend_ops pmc_suspend_ops = { .enter = pmc_suspend_enter, }; -static int pmc_probe(struct of_device *ofdev, const struct of_device_id *id) +static int pmc_probe(struct platform_device *ofdev, + const struct of_device_id *id) { pmc_regs = of_iomap(ofdev->dev.of_node, 0); if (!pmc_regs) diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 30e1626b2e85..8bd86530ee25 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -1338,7 +1338,7 @@ static inline void fsl_rio_info(struct device *dev, u32 ccsr) * master port with system-specific info, and registers the * master port with the RapidIO subsystem. */ -int fsl_rio_setup(struct of_device *dev) +int fsl_rio_setup(struct platform_device *dev) { struct rio_ops *ops; struct rio_mport *port; @@ -1536,7 +1536,7 @@ err_ops: /* The probe function for RapidIO peer-to-peer network. */ -static int __devinit fsl_of_rio_rpn_probe(struct of_device *dev, +static int __devinit fsl_of_rio_rpn_probe(struct platform_device *dev, const struct of_device_id *match) { int rc; diff --git a/arch/powerpc/sysdev/mpc8xxx_gpio.c b/arch/powerpc/sysdev/mpc8xxx_gpio.c index 83f519655fac..2b69084d0f0c 100644 --- a/arch/powerpc/sysdev/mpc8xxx_gpio.c +++ b/arch/powerpc/sysdev/mpc8xxx_gpio.c @@ -257,7 +257,6 @@ static void __init mpc8xxx_add_controller(struct device_node *np) { struct mpc8xxx_gpio_chip *mpc8xxx_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; unsigned hwirq; int ret; @@ -271,11 +270,9 @@ static void __init mpc8xxx_add_controller(struct device_node *np) spin_lock_init(&mpc8xxx_gc->lock); mm_gc = &mpc8xxx_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = mpc8xxx_gpio_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = MPC8XXX_GPIO_PINS; gc->direction_input = mpc8xxx_gpio_dir_in; gc->direction_output = mpc8xxx_gpio_dir_out; diff --git a/arch/powerpc/sysdev/mv64x60_dev.c b/arch/powerpc/sysdev/mv64x60_dev.c index 31acd3b1718b..1398bc454999 100644 --- a/arch/powerpc/sysdev/mv64x60_dev.c +++ b/arch/powerpc/sysdev/mv64x60_dev.c @@ -20,12 +20,7 @@ #include <asm/prom.h> -/* - * These functions provide the necessary setup for the mv64x60 drivers. - * These drivers are unusual in that they work on both the MIPS and PowerPC - * architectures. Because of that, the drivers do not support the normal - * PowerPC of_platform_bus_type. They support platform_bus_type instead. - */ +/* These functions provide the necessary setup for the mv64x60 drivers. */ static struct of_device_id __initdata of_mv64x60_devices[] = { { .compatible = "marvell,mv64306-devctrl", }, diff --git a/arch/powerpc/sysdev/mv64x60_pci.c b/arch/powerpc/sysdev/mv64x60_pci.c index 198f288570cc..77bb3f4d530a 100644 --- a/arch/powerpc/sysdev/mv64x60_pci.c +++ b/arch/powerpc/sysdev/mv64x60_pci.c @@ -73,7 +73,6 @@ static struct bin_attribute mv64x60_hs_reg_attr = { /* Hotswap register */ .attr = { .name = "hs_reg", .mode = S_IRUGO | S_IWUSR, - .owner = THIS_MODULE, }, .size = MV64X60_VAL_LEN_MAX, .read = mv64x60_hs_reg_read, diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c index d07137a07d75..24a0bb955b18 100644 --- a/arch/powerpc/sysdev/pmi.c +++ b/arch/powerpc/sysdev/pmi.c @@ -43,7 +43,7 @@ struct pmi_data { struct mutex msg_mutex; pmi_message_t msg; struct completion *completion; - struct of_device *dev; + struct platform_device *dev; int irq; u8 __iomem *pmi_reg; struct work_struct work; @@ -121,7 +121,7 @@ static void pmi_notify_handlers(struct work_struct *work) spin_unlock(&data->handler_spinlock); } -static int pmi_of_probe(struct of_device *dev, +static int pmi_of_probe(struct platform_device *dev, const struct of_device_id *match) { struct device_node *np = dev->dev.of_node; @@ -185,7 +185,7 @@ out: return rc; } -static int pmi_of_remove(struct of_device *dev) +static int pmi_of_remove(struct platform_device *dev) { struct pmi_handler *handler, *tmp; diff --git a/arch/powerpc/sysdev/ppc4xx_gpio.c b/arch/powerpc/sysdev/ppc4xx_gpio.c index 3812fc366bec..fc65ad1b3293 100644 --- a/arch/powerpc/sysdev/ppc4xx_gpio.c +++ b/arch/powerpc/sysdev/ppc4xx_gpio.c @@ -181,7 +181,6 @@ static int __init ppc4xx_add_gpiochips(void) int ret; struct ppc4xx_gpio_chip *ppc4xx_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; ppc4xx_gc = kzalloc(sizeof(*ppc4xx_gc), GFP_KERNEL); @@ -193,10 +192,8 @@ static int __init ppc4xx_add_gpiochips(void) spin_lock_init(&ppc4xx_gc->lock); mm_gc = &ppc4xx_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; - of_gc->gpio_cells = 2; gc->ngpio = 32; gc->direction_input = ppc4xx_gpio_dir_in; gc->direction_output = ppc4xx_gpio_dir_out; diff --git a/arch/powerpc/sysdev/qe_lib/gpio.c b/arch/powerpc/sysdev/qe_lib/gpio.c index dc8f8d618074..36bf845df127 100644 --- a/arch/powerpc/sysdev/qe_lib/gpio.c +++ b/arch/powerpc/sysdev/qe_lib/gpio.c @@ -138,8 +138,8 @@ struct qe_pin { struct qe_pin *qe_pin_request(struct device_node *np, int index) { struct qe_pin *qe_pin; - struct device_node *gc; - struct of_gpio_chip *of_gc = NULL; + struct device_node *gpio_np; + struct gpio_chip *gc; struct of_mm_gpio_chip *mm_gc; struct qe_gpio_chip *qe_gc; int err; @@ -155,40 +155,40 @@ struct qe_pin *qe_pin_request(struct device_node *np, int index) } err = of_parse_phandles_with_args(np, "gpios", "#gpio-cells", index, - &gc, &gpio_spec); + &gpio_np, &gpio_spec); if (err) { pr_debug("%s: can't parse gpios property\n", __func__); goto err0; } - if (!of_device_is_compatible(gc, "fsl,mpc8323-qe-pario-bank")) { + if (!of_device_is_compatible(gpio_np, "fsl,mpc8323-qe-pario-bank")) { pr_debug("%s: tried to get a non-qe pin\n", __func__); err = -EINVAL; goto err1; } - of_gc = gc->data; - if (!of_gc) { + gc = of_node_to_gpiochip(gpio_np); + if (!gc) { pr_debug("%s: gpio controller %s isn't registered\n", - np->full_name, gc->full_name); + np->full_name, gpio_np->full_name); err = -ENODEV; goto err1; } - gpio_cells = of_get_property(gc, "#gpio-cells", &size); + gpio_cells = of_get_property(gpio_np, "#gpio-cells", &size); if (!gpio_cells || size != sizeof(*gpio_cells) || - *gpio_cells != of_gc->gpio_cells) { + *gpio_cells != gc->of_gpio_n_cells) { pr_debug("%s: wrong #gpio-cells for %s\n", - np->full_name, gc->full_name); + np->full_name, gpio_np->full_name); err = -EINVAL; goto err1; } - err = of_gc->xlate(of_gc, np, gpio_spec, NULL); + err = gc->of_xlate(gc, np, gpio_spec, NULL); if (err < 0) goto err1; - mm_gc = to_of_mm_gpio_chip(&of_gc->gc); + mm_gc = to_of_mm_gpio_chip(gc); qe_gc = to_qe_gpio_chip(mm_gc); spin_lock_irqsave(&qe_gc->lock, flags); @@ -206,7 +206,7 @@ struct qe_pin *qe_pin_request(struct device_node *np, int index) if (!err) return qe_pin; err1: - of_node_put(gc); + of_node_put(gpio_np); err0: kfree(qe_pin); pr_debug("%s failed with status %d\n", __func__, err); @@ -307,7 +307,6 @@ static int __init qe_add_gpiochips(void) int ret; struct qe_gpio_chip *qe_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; qe_gc = kzalloc(sizeof(*qe_gc), GFP_KERNEL); @@ -319,11 +318,9 @@ static int __init qe_add_gpiochips(void) spin_lock_init(&qe_gc->lock); mm_gc = &qe_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = qe_gpio_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = QE_PIO_PINS; gc->direction_input = qe_gpio_dir_in; gc->direction_output = qe_gpio_dir_out; diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c index 093e0ae1a941..3da8014931c9 100644 --- a/arch/powerpc/sysdev/qe_lib/qe.c +++ b/arch/powerpc/sysdev/qe_lib/qe.c @@ -651,14 +651,15 @@ unsigned int qe_get_num_of_snums(void) EXPORT_SYMBOL(qe_get_num_of_snums); #if defined(CONFIG_SUSPEND) && defined(CONFIG_PPC_85xx) -static int qe_resume(struct of_device *ofdev) +static int qe_resume(struct platform_device *ofdev) { if (!qe_alive_during_sleep()) qe_reset(); return 0; } -static int qe_probe(struct of_device *ofdev, const struct of_device_id *id) +static int qe_probe(struct platform_device *ofdev, + const struct of_device_id *id) { return 0; } diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c index d5fb173e588c..b6defda5ccc9 100644 --- a/arch/powerpc/sysdev/simple_gpio.c +++ b/arch/powerpc/sysdev/simple_gpio.c @@ -91,7 +91,6 @@ static int __init u8_simple_gpiochip_add(struct device_node *np) int ret; struct u8_gpio_chip *u8_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; u8_gc = kzalloc(sizeof(*u8_gc), GFP_KERNEL); @@ -101,11 +100,9 @@ static int __init u8_simple_gpiochip_add(struct device_node *np) spin_lock_init(&u8_gc->lock); mm_gc = &u8_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = u8_gpio_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = 8; gc->direction_input = u8_gpio_dir_in; gc->direction_output = u8_gpio_dir_out; diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 30c5f01f93b0..0c9e6c6d2a64 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -24,7 +24,8 @@ CHECKFLAGS += -D__s390__ -msize-long else LD_BFD := elf64-s390 LDFLAGS := -m elf64_s390 -MODFLAGS += -fpic -D__PIC__ +KBUILD_AFLAGS_MODULE += -fpic -D__PIC__ +KBUILD_CFLAGS_MODULE += -fpic -D__PIC__ KBUILD_CFLAGS += -m64 KBUILD_AFLAGS += -m64 UTS_MACHINE := s390x diff --git a/arch/s390/include/asm/local64.h b/arch/s390/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/s390/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/score/Makefile b/arch/score/Makefile index 68e0cd06d5c9..d77dc639d8e3 100644 --- a/arch/score/Makefile +++ b/arch/score/Makefile @@ -20,7 +20,8 @@ cflags-y += -G0 -pipe -mel -mnhwloop -D__SCOREEL__ \ # KBUILD_AFLAGS += $(cflags-y) KBUILD_CFLAGS += $(cflags-y) -MODFLAGS += -mlong-calls +KBUILD_AFLAGS_MODULE += -mlong-calls +KBUILD_CFLAGS_MODULE += -mlong-calls LDFLAGS += --oformat elf32-littlescore LDFLAGS_vmlinux += -G0 -static -nostdlib diff --git a/arch/score/include/asm/local64.h b/arch/score/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/score/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/sh/include/asm/local64.h b/arch/sh/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/sh/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 81b6de41ae5d..7a3dc3567258 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -185,10 +185,10 @@ static void sh_perf_event_update(struct perf_event *event, * this is the simplest approach for maintaining consistency. */ again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); new_raw_count = sh_pmu->read(idx); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; @@ -203,7 +203,7 @@ again: delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - atomic64_add(delta, &event->count); + local64_add(delta, &event->count); } static void sh_pmu_disable(struct perf_event *event) diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c0015db247ba..ba068c833e5d 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -18,6 +18,7 @@ config 64BIT config SPARC bool default y + select OF select HAVE_IDE select HAVE_OPROFILE select HAVE_ARCH_KGDB if !SMP || SPARC64 @@ -148,9 +149,6 @@ config GENERIC_GPIO config ARCH_NO_VIRT_TO_BUS def_bool y -config OF - def_bool y - config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y if SPARC64 diff --git a/arch/sparc/include/asm/device.h b/arch/sparc/include/asm/device.h index d4c452147412..daa6a8a5e9cd 100644 --- a/arch/sparc/include/asm/device.h +++ b/arch/sparc/include/asm/device.h @@ -6,18 +6,25 @@ #ifndef _ASM_SPARC_DEVICE_H #define _ASM_SPARC_DEVICE_H +#include <asm/openprom.h> + struct device_node; -struct of_device; +struct platform_device; struct dev_archdata { void *iommu; void *stc; void *host_controller; - struct of_device *op; + struct platform_device *op; int numa_node; }; +extern void of_propagate_archdata(struct platform_device *bus); + struct pdev_archdata { + struct resource resource[PROMREG_MAX]; + unsigned int irqs[PROMINTR_MAX]; + int num_irqs; }; #endif /* _ASM_SPARC_DEVICE_H */ diff --git a/arch/sparc/include/asm/floppy_64.h b/arch/sparc/include/asm/floppy_64.h index 8fac3ab22f36..6597ce874d78 100644 --- a/arch/sparc/include/asm/floppy_64.h +++ b/arch/sparc/include/asm/floppy_64.h @@ -43,7 +43,7 @@ struct sun_flpy_controller { /* You'll only ever find one controller on an Ultra anyways. */ static struct sun_flpy_controller *sun_fdc = (struct sun_flpy_controller *)-1; unsigned long fdc_status; -static struct of_device *floppy_op = NULL; +static struct platform_device *floppy_op = NULL; struct sun_floppy_ops { unsigned char (*fd_inb) (unsigned long port); @@ -548,7 +548,7 @@ static unsigned long __init sun_floppy_init(void) { static int initialized = 0; struct device_node *dp; - struct of_device *op; + struct platform_device *op; const char *prop; char state[128]; @@ -567,7 +567,7 @@ static unsigned long __init sun_floppy_init(void) } if (op) { floppy_op = op; - FLOPPY_IRQ = op->irqs[0]; + FLOPPY_IRQ = op->archdata.irqs[0]; } else { struct device_node *ebus_dp; void __iomem *auxio_reg; @@ -593,7 +593,7 @@ static unsigned long __init sun_floppy_init(void) if (state_prop && !strncmp(state_prop, "disabled", 8)) return 0; - FLOPPY_IRQ = op->irqs[0]; + FLOPPY_IRQ = op->archdata.irqs[0]; /* Make sure the high density bit is set, some systems * (most notably Ultra5/Ultra10) come up with it clear. @@ -661,7 +661,7 @@ static unsigned long __init sun_floppy_init(void) config = 0; for (dp = ebus_dp->child; dp; dp = dp->sibling) { if (!strcmp(dp->name, "ecpp")) { - struct of_device *ecpp_op; + struct platform_device *ecpp_op; ecpp_op = of_find_device_by_node(dp); if (ecpp_op) diff --git a/arch/sparc/include/asm/local64.h b/arch/sparc/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/sparc/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/sparc/include/asm/of_device.h b/arch/sparc/include/asm/of_device.h deleted file mode 100644 index f320246a0586..000000000000 --- a/arch/sparc/include/asm/of_device.h +++ /dev/null @@ -1,38 +0,0 @@ -#ifndef _ASM_SPARC_OF_DEVICE_H -#define _ASM_SPARC_OF_DEVICE_H -#ifdef __KERNEL__ - -#include <linux/device.h> -#include <linux/of.h> -#include <linux/mod_devicetable.h> -#include <asm/openprom.h> - -/* - * The of_device is a kind of "base class" that is a superset of - * struct device for use by devices attached to an OF node and - * probed using OF properties. - */ -struct of_device -{ - struct device dev; - struct resource resource[PROMREG_MAX]; - unsigned int irqs[PROMINTR_MAX]; - int num_irqs; - - void *sysdata; - - int slot; - int portid; - int clock_freq; -}; - -extern void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name); -extern void of_iounmap(struct resource *res, void __iomem *base, unsigned long size); - -extern void of_propagate_archdata(struct of_device *bus); - -/* This is just here during the transition */ -#include <linux/of_platform.h> - -#endif /* __KERNEL__ */ -#endif /* _ASM_SPARC_OF_DEVICE_H */ diff --git a/arch/sparc/include/asm/of_platform.h b/arch/sparc/include/asm/of_platform.h deleted file mode 100644 index 90da99059f83..000000000000 --- a/arch/sparc/include/asm/of_platform.h +++ /dev/null @@ -1,18 +0,0 @@ -#ifndef ___ASM_SPARC_OF_PLATFORM_H -#define ___ASM_SPARC_OF_PLATFORM_H -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * Modified for Sparc by merging parts of asm/of_device.h - * by Stephen Rothwell - * - * 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 of_bus_type of_platform_bus_type /* for compatibility */ - -#endif diff --git a/arch/sparc/include/asm/parport.h b/arch/sparc/include/asm/parport.h index c333b8d0949b..4f7afa01b2ae 100644 --- a/arch/sparc/include/asm/parport.h +++ b/arch/sparc/include/asm/parport.h @@ -103,7 +103,7 @@ static inline unsigned int get_dma_residue(unsigned int dmanr) return ebus_dma_residue(&sparc_ebus_dmas[dmanr].info); } -static int __devinit ecpp_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit ecpp_probe(struct platform_device *op, const struct of_device_id *match) { unsigned long base = op->resource[0].start; unsigned long config = op->resource[1].start; @@ -116,7 +116,7 @@ static int __devinit ecpp_probe(struct of_device *op, const struct of_device_id parent = op->dev.of_node->parent; if (!strcmp(parent->name, "dma")) { p = parport_pc_probe_port(base, base + 0x400, - op->irqs[0], PARPORT_DMA_NOFIFO, + op->archdata.irqs[0], PARPORT_DMA_NOFIFO, op->dev.parent->parent, 0); if (!p) return -ENOMEM; @@ -166,7 +166,7 @@ static int __devinit ecpp_probe(struct of_device *op, const struct of_device_id 0, PTR_LPT_REG_DIR); p = parport_pc_probe_port(base, base + 0x400, - op->irqs[0], + op->archdata.irqs[0], slot, op->dev.parent, 0); @@ -192,7 +192,7 @@ out_err: return err; } -static int __devexit ecpp_remove(struct of_device *op) +static int __devexit ecpp_remove(struct platform_device *op) { struct parport *p = dev_get_drvdata(&op->dev); int slot = p->dma; @@ -243,9 +243,7 @@ static struct of_platform_driver ecpp_driver = { static int parport_pc_find_nonpci_ports(int autoirq, int autodma) { - of_register_driver(&ecpp_driver, &of_bus_type); - - return 0; + return of_register_platform_driver(&ecpp_driver); } #endif /* !(_ASM_SPARC64_PARPORT_H */ diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h index 7e2669894ce8..74c4e0cd889c 100644 --- a/arch/sparc/include/asm/perf_event.h +++ b/arch/sparc/include/asm/perf_event.h @@ -6,7 +6,15 @@ extern void set_perf_event_pending(void); #define PERF_EVENT_INDEX_OFFSET 0 #ifdef CONFIG_PERF_EVENTS +#include <asm/ptrace.h> + extern void init_hw_perf_events(void); + +extern void +__perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); + +#define perf_arch_fetch_caller_regs(pt_regs, ip) \ + __perf_arch_fetch_caller_regs(pt_regs, ip, 1); #else static inline void init_hw_perf_events(void) { } #endif diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h index f845828ca4c6..291f12575edd 100644 --- a/arch/sparc/include/asm/prom.h +++ b/arch/sparc/include/asm/prom.h @@ -43,20 +43,22 @@ extern int of_getintprop_default(struct device_node *np, extern int of_find_in_proplist(const char *list, const char *match, int len); #ifdef CONFIG_NUMA extern int of_node_to_nid(struct device_node *dp); -#else -#define of_node_to_nid(dp) (-1) +#define of_node_to_nid of_node_to_nid #endif extern void prom_build_devicetree(void); extern void of_populate_present_mask(void); extern void of_fill_in_cpu_data(void); +struct resource; +extern void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name); +extern void of_iounmap(struct resource *res, void __iomem *base, unsigned long size); + /* These routines are here to provide compatibility with how powerpc * handles IRQ mapping for OF device nodes. We precompute and permanently - * register them in the of_device objects, whereas powerpc computes them + * register them in the platform_device objects, whereas powerpc computes them * on request. */ -extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); static inline void irq_dispose_mapping(unsigned int virq) { } diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c index b27476caa133..2c0046ecc715 100644 --- a/arch/sparc/kernel/apc.c +++ b/arch/sparc/kernel/apc.c @@ -68,7 +68,7 @@ static void apc_swift_idle(void) #endif } -static inline void apc_free(struct of_device *op) +static inline void apc_free(struct platform_device *op) { of_iounmap(&op->resource[0], regs, resource_size(&op->resource[0])); } @@ -136,7 +136,7 @@ static const struct file_operations apc_fops = { static struct miscdevice apc_miscdev = { APC_MINOR, APC_DEVNAME, &apc_fops }; -static int __devinit apc_probe(struct of_device *op, +static int __devinit apc_probe(struct platform_device *op, const struct of_device_id *match) { int err; @@ -184,7 +184,7 @@ static struct of_platform_driver apc_driver = { static int __init apc_init(void) { - return of_register_driver(&apc_driver, &of_bus_type); + return of_register_platform_driver(&apc_driver); } /* This driver is not critical to the boot process diff --git a/arch/sparc/kernel/auxio_64.c b/arch/sparc/kernel/auxio_64.c index ddc84128b3c2..3efd3c5af6a9 100644 --- a/arch/sparc/kernel/auxio_64.c +++ b/arch/sparc/kernel/auxio_64.c @@ -102,7 +102,8 @@ static struct of_device_id __initdata auxio_match[] = { MODULE_DEVICE_TABLE(of, auxio_match); -static int __devinit auxio_probe(struct of_device *dev, const struct of_device_id *match) +static int __devinit auxio_probe(struct platform_device *dev, + const struct of_device_id *match) { struct device_node *dp = dev->dev.of_node; unsigned long size; @@ -142,7 +143,7 @@ static struct of_platform_driver auxio_driver = { static int __init auxio_init(void) { - return of_register_driver(&auxio_driver, &of_platform_bus_type); + return of_register_platform_driver(&auxio_driver); } /* Must be after subsys_initcall() so that busses are probed. Must diff --git a/arch/sparc/kernel/central.c b/arch/sparc/kernel/central.c index 434335f65823..cfa2624c5332 100644 --- a/arch/sparc/kernel/central.c +++ b/arch/sparc/kernel/central.c @@ -59,7 +59,7 @@ static int __devinit clock_board_calc_nslots(struct clock_board *p) } } -static int __devinit clock_board_probe(struct of_device *op, +static int __devinit clock_board_probe(struct platform_device *op, const struct of_device_id *match) { struct clock_board *p = kzalloc(sizeof(*p), GFP_KERNEL); @@ -157,7 +157,7 @@ static struct of_platform_driver clock_board_driver = { }, }; -static int __devinit fhc_probe(struct of_device *op, +static int __devinit fhc_probe(struct platform_device *op, const struct of_device_id *match) { struct fhc *p = kzalloc(sizeof(*p), GFP_KERNEL); @@ -265,8 +265,8 @@ static struct of_platform_driver fhc_driver = { static int __init sunfire_init(void) { - (void) of_register_driver(&fhc_driver, &of_platform_bus_type); - (void) of_register_driver(&clock_board_driver, &of_platform_bus_type); + (void) of_register_platform_driver(&fhc_driver); + (void) of_register_platform_driver(&clock_board_driver); return 0; } diff --git a/arch/sparc/kernel/chmc.c b/arch/sparc/kernel/chmc.c index 870cb65b3f21..08c466ebb32b 100644 --- a/arch/sparc/kernel/chmc.c +++ b/arch/sparc/kernel/chmc.c @@ -392,7 +392,7 @@ static void __devinit jbusmc_construct_dimm_groups(struct jbusmc *p, } } -static int __devinit jbusmc_probe(struct of_device *op, +static int __devinit jbusmc_probe(struct platform_device *op, const struct of_device_id *match) { const struct linux_prom64_registers *mem_regs; @@ -690,7 +690,7 @@ static void chmc_fetch_decode_regs(struct chmc *p) chmc_read_mcreg(p, CHMCTRL_DECODE4)); } -static int __devinit chmc_probe(struct of_device *op, +static int __devinit chmc_probe(struct platform_device *op, const struct of_device_id *match) { struct device_node *dp = op->dev.of_node; @@ -765,7 +765,7 @@ out_free: goto out; } -static int __devinit us3mc_probe(struct of_device *op, +static int __devinit us3mc_probe(struct platform_device *op, const struct of_device_id *match) { if (mc_type == MC_TYPE_SAFARI) @@ -775,21 +775,21 @@ static int __devinit us3mc_probe(struct of_device *op, return -ENODEV; } -static void __devexit chmc_destroy(struct of_device *op, struct chmc *p) +static void __devexit chmc_destroy(struct platform_device *op, struct chmc *p) { list_del(&p->list); of_iounmap(&op->resource[0], p->regs, 0x48); kfree(p); } -static void __devexit jbusmc_destroy(struct of_device *op, struct jbusmc *p) +static void __devexit jbusmc_destroy(struct platform_device *op, struct jbusmc *p) { mc_list_del(&p->list); of_iounmap(&op->resource[0], p->regs, JBUSMC_REGS_SIZE); kfree(p); } -static int __devexit us3mc_remove(struct of_device *op) +static int __devexit us3mc_remove(struct platform_device *op) { void *p = dev_get_drvdata(&op->dev); @@ -848,7 +848,7 @@ static int __init us3mc_init(void) ret = register_dimm_printer(us3mc_dimm_printer); if (!ret) { - ret = of_register_driver(&us3mc_driver, &of_bus_type); + ret = of_register_platform_driver(&us3mc_driver); if (ret) unregister_dimm_printer(us3mc_dimm_printer); } @@ -859,7 +859,7 @@ static void __exit us3mc_cleanup(void) { if (us3mc_platform()) { unregister_dimm_printer(us3mc_dimm_printer); - of_unregister_driver(&us3mc_driver); + of_unregister_platform_driver(&us3mc_driver); } } diff --git a/arch/sparc/kernel/helpers.S b/arch/sparc/kernel/helpers.S index 92090cc9e829..682fee06a16b 100644 --- a/arch/sparc/kernel/helpers.S +++ b/arch/sparc/kernel/helpers.S @@ -47,9 +47,9 @@ stack_trace_flush: .size stack_trace_flush,.-stack_trace_flush #ifdef CONFIG_PERF_EVENTS - .globl perf_arch_fetch_caller_regs - .type perf_arch_fetch_caller_regs,#function -perf_arch_fetch_caller_regs: + .globl __perf_arch_fetch_caller_regs + .type __perf_arch_fetch_caller_regs,#function +__perf_arch_fetch_caller_regs: /* We always read the %pstate into %o5 since we will use * that to construct a fake %tstate to store into the regs. */ diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 703e4aa9bc38..41f7e4e0f72a 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -253,7 +253,7 @@ EXPORT_SYMBOL(sbus_set_sbus64); static void *sbus_alloc_coherent(struct device *dev, size_t len, dma_addr_t *dma_addrp, gfp_t gfp) { - struct of_device *op = to_of_device(dev); + struct platform_device *op = to_platform_device(dev); unsigned long len_total = (len + PAGE_SIZE-1) & PAGE_MASK; unsigned long va; struct resource *res; diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c index 47e63f1e719c..2d055a1e9cc2 100644 --- a/arch/sparc/kernel/of_device_32.c +++ b/arch/sparc/kernel/of_device_32.c @@ -241,10 +241,10 @@ static int __init use_1to1_mapping(struct device_node *pp) static int of_resource_verbose; -static void __init build_device_resources(struct of_device *op, +static void __init build_device_resources(struct platform_device *op, struct device *parent) { - struct of_device *p_op; + struct platform_device *p_op; struct of_bus *bus; int na, ns; int index, num_reg; @@ -253,7 +253,7 @@ static void __init build_device_resources(struct of_device *op, if (!parent) return; - p_op = to_of_device(parent); + p_op = to_platform_device(parent); bus = of_match_bus(p_op->dev.of_node); bus->count_cells(op->dev.of_node, &na, &ns); @@ -267,6 +267,8 @@ static void __init build_device_resources(struct of_device *op, /* Conver to num-entries. */ num_reg /= na + ns; + op->resource = op->archdata.resource; + op->num_resources = num_reg; for (index = 0; index < num_reg; index++) { struct resource *r = &op->resource[index]; u32 addr[OF_MAX_ADDR_CELLS]; @@ -333,10 +335,10 @@ static void __init build_device_resources(struct of_device *op, } } -static struct of_device * __init scan_one_device(struct device_node *dp, +static struct platform_device * __init scan_one_device(struct device_node *dp, struct device *parent) { - struct of_device *op = kzalloc(sizeof(*op), GFP_KERNEL); + struct platform_device *op = kzalloc(sizeof(*op), GFP_KERNEL); const struct linux_prom_irqs *intr; struct dev_archdata *sd; int len, i; @@ -349,27 +351,21 @@ static struct of_device * __init scan_one_device(struct device_node *dp, op->dev.of_node = dp; - op->clock_freq = of_getintprop_default(dp, "clock-frequency", - (25*1000*1000)); - op->portid = of_getintprop_default(dp, "upa-portid", -1); - if (op->portid == -1) - op->portid = of_getintprop_default(dp, "portid", -1); - intr = of_get_property(dp, "intr", &len); if (intr) { - op->num_irqs = len / sizeof(struct linux_prom_irqs); - for (i = 0; i < op->num_irqs; i++) - op->irqs[i] = intr[i].pri; + op->archdata.num_irqs = len / sizeof(struct linux_prom_irqs); + for (i = 0; i < op->archdata.num_irqs; i++) + op->archdata.irqs[i] = intr[i].pri; } else { const unsigned int *irq = of_get_property(dp, "interrupts", &len); if (irq) { - op->num_irqs = len / sizeof(unsigned int); - for (i = 0; i < op->num_irqs; i++) - op->irqs[i] = irq[i]; + op->archdata.num_irqs = len / sizeof(unsigned int); + for (i = 0; i < op->archdata.num_irqs; i++) + op->archdata.irqs[i] = irq[i]; } else { - op->num_irqs = 0; + op->archdata.num_irqs = 0; } } if (sparc_cpu_model == sun4d) { @@ -411,8 +407,8 @@ static struct of_device * __init scan_one_device(struct device_node *dp, goto build_resources; } - for (i = 0; i < op->num_irqs; i++) { - int this_irq = op->irqs[i]; + for (i = 0; i < op->archdata.num_irqs; i++) { + int this_irq = op->archdata.irqs[i]; int sbusl = pil_to_sbus[this_irq]; if (sbusl) @@ -420,7 +416,7 @@ static struct of_device * __init scan_one_device(struct device_node *dp, (sbusl << 2) + slot); - op->irqs[i] = this_irq; + op->archdata.irqs[i] = this_irq; } } @@ -428,7 +424,7 @@ build_resources: build_device_resources(op, parent); op->dev.parent = parent; - op->dev.bus = &of_platform_bus_type; + op->dev.bus = &platform_bus_type; if (!parent) dev_set_name(&op->dev, "root"); else @@ -447,7 +443,7 @@ build_resources: static void __init scan_tree(struct device_node *dp, struct device *parent) { while (dp) { - struct of_device *op = scan_one_device(dp, parent); + struct platform_device *op = scan_one_device(dp, parent); if (op) scan_tree(dp->child, &op->dev); @@ -456,30 +452,19 @@ static void __init scan_tree(struct device_node *dp, struct device *parent) } } -static void __init scan_of_devices(void) +static int __init scan_of_devices(void) { struct device_node *root = of_find_node_by_path("/"); - struct of_device *parent; + struct platform_device *parent; parent = scan_one_device(root, NULL); if (!parent) - return; + return 0; scan_tree(root->child, &parent->dev); + return 0; } - -static int __init of_bus_driver_init(void) -{ - int err; - - err = of_bus_type_init(&of_platform_bus_type, "of"); - if (!err) - scan_of_devices(); - - return err; -} - -postcore_initcall(of_bus_driver_init); +postcore_initcall(scan_of_devices); static int __init of_debug(char *str) { diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c index 1dae8079f728..63cd4e5d47c2 100644 --- a/arch/sparc/kernel/of_device_64.c +++ b/arch/sparc/kernel/of_device_64.c @@ -310,10 +310,10 @@ static int __init use_1to1_mapping(struct device_node *pp) static int of_resource_verbose; -static void __init build_device_resources(struct of_device *op, +static void __init build_device_resources(struct platform_device *op, struct device *parent) { - struct of_device *p_op; + struct platform_device *p_op; struct of_bus *bus; int na, ns; int index, num_reg; @@ -322,7 +322,7 @@ static void __init build_device_resources(struct of_device *op, if (!parent) return; - p_op = to_of_device(parent); + p_op = to_platform_device(parent); bus = of_match_bus(p_op->dev.of_node); bus->count_cells(op->dev.of_node, &na, &ns); @@ -344,6 +344,8 @@ static void __init build_device_resources(struct of_device *op, num_reg = PROMREG_MAX; } + op->resource = op->archdata.resource; + op->num_resources = num_reg; for (index = 0; index < num_reg; index++) { struct resource *r = &op->resource[index]; u32 addr[OF_MAX_ADDR_CELLS]; @@ -526,7 +528,7 @@ static unsigned int __init pci_irq_swizzle(struct device_node *dp, static int of_irq_verbose; -static unsigned int __init build_one_device_irq(struct of_device *op, +static unsigned int __init build_one_device_irq(struct platform_device *op, struct device *parent, unsigned int irq) { @@ -628,10 +630,10 @@ out: return irq; } -static struct of_device * __init scan_one_device(struct device_node *dp, +static struct platform_device * __init scan_one_device(struct device_node *dp, struct device *parent) { - struct of_device *op = kzalloc(sizeof(*op), GFP_KERNEL); + struct platform_device *op = kzalloc(sizeof(*op), GFP_KERNEL); const unsigned int *irq; struct dev_archdata *sd; int len, i; @@ -644,34 +646,28 @@ static struct of_device * __init scan_one_device(struct device_node *dp, op->dev.of_node = dp; - op->clock_freq = of_getintprop_default(dp, "clock-frequency", - (25*1000*1000)); - op->portid = of_getintprop_default(dp, "upa-portid", -1); - if (op->portid == -1) - op->portid = of_getintprop_default(dp, "portid", -1); - irq = of_get_property(dp, "interrupts", &len); if (irq) { - op->num_irqs = len / 4; + op->archdata.num_irqs = len / 4; /* Prevent overrunning the op->irqs[] array. */ - if (op->num_irqs > PROMINTR_MAX) { + if (op->archdata.num_irqs > PROMINTR_MAX) { printk(KERN_WARNING "%s: Too many irqs (%d), " "limiting to %d.\n", - dp->full_name, op->num_irqs, PROMINTR_MAX); - op->num_irqs = PROMINTR_MAX; + dp->full_name, op->archdata.num_irqs, PROMINTR_MAX); + op->archdata.num_irqs = PROMINTR_MAX; } - memcpy(op->irqs, irq, op->num_irqs * 4); + memcpy(op->archdata.irqs, irq, op->archdata.num_irqs * 4); } else { - op->num_irqs = 0; + op->archdata.num_irqs = 0; } build_device_resources(op, parent); - for (i = 0; i < op->num_irqs; i++) - op->irqs[i] = build_one_device_irq(op, parent, op->irqs[i]); + for (i = 0; i < op->archdata.num_irqs; i++) + op->archdata.irqs[i] = build_one_device_irq(op, parent, op->archdata.irqs[i]); op->dev.parent = parent; - op->dev.bus = &of_platform_bus_type; + op->dev.bus = &platform_bus_type; if (!parent) dev_set_name(&op->dev, "root"); else @@ -690,7 +686,7 @@ static struct of_device * __init scan_one_device(struct device_node *dp, static void __init scan_tree(struct device_node *dp, struct device *parent) { while (dp) { - struct of_device *op = scan_one_device(dp, parent); + struct platform_device *op = scan_one_device(dp, parent); if (op) scan_tree(dp->child, &op->dev); @@ -699,30 +695,19 @@ static void __init scan_tree(struct device_node *dp, struct device *parent) } } -static void __init scan_of_devices(void) +static int __init scan_of_devices(void) { struct device_node *root = of_find_node_by_path("/"); - struct of_device *parent; + struct platform_device *parent; parent = scan_one_device(root, NULL); if (!parent) - return; + return 0; scan_tree(root->child, &parent->dev); + return 0; } - -static int __init of_bus_driver_init(void) -{ - int err; - - err = of_bus_type_init(&of_platform_bus_type, "of"); - if (!err) - scan_of_devices(); - - return err; -} - -postcore_initcall(of_bus_driver_init); +postcore_initcall(scan_of_devices); static int __init of_debug(char *str) { diff --git a/arch/sparc/kernel/of_device_common.c b/arch/sparc/kernel/of_device_common.c index 10c6c36a6e75..49ddff56cb04 100644 --- a/arch/sparc/kernel/of_device_common.c +++ b/arch/sparc/kernel/of_device_common.c @@ -11,48 +11,28 @@ #include "of_device_common.h" -static int node_match(struct device *dev, void *data) -{ - struct of_device *op = to_of_device(dev); - struct device_node *dp = data; - - return (op->dev.of_node == dp); -} - -struct of_device *of_find_device_by_node(struct device_node *dp) -{ - struct device *dev = bus_find_device(&of_platform_bus_type, NULL, - dp, node_match); - - if (dev) - return to_of_device(dev); - - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_node); - unsigned int irq_of_parse_and_map(struct device_node *node, int index) { - struct of_device *op = of_find_device_by_node(node); + struct platform_device *op = of_find_device_by_node(node); - if (!op || index >= op->num_irqs) + if (!op || index >= op->archdata.num_irqs) return 0; - return op->irqs[index]; + return op->archdata.irqs[index]; } EXPORT_SYMBOL(irq_of_parse_and_map); /* Take the archdata values for IOMMU, STC, and HOSTDATA found in - * BUS and propagate to all child of_device objects. + * BUS and propagate to all child platform_device objects. */ -void of_propagate_archdata(struct of_device *bus) +void of_propagate_archdata(struct platform_device *bus) { struct dev_archdata *bus_sd = &bus->dev.archdata; struct device_node *bus_dp = bus->dev.of_node; struct device_node *dp; for (dp = bus_dp->child; dp; dp = dp->sibling) { - struct of_device *op = of_find_device_by_node(dp); + struct platform_device *op = of_find_device_by_node(dp); op->dev.archdata.iommu = bus_sd->iommu; op->dev.archdata.stc = bus_sd->stc; @@ -64,9 +44,6 @@ void of_propagate_archdata(struct of_device *bus) } } -struct bus_type of_platform_bus_type; -EXPORT_SYMBOL(of_platform_bus_type); - static void get_cells(struct device_node *dp, int *addrc, int *sizec) { if (addrc) diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 8a8363adb8bd..4137579d9adc 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -198,7 +198,7 @@ static unsigned long pci_parse_of_flags(u32 addr0) * into physical address resources, we only have to figure out the register * mapping. */ -static void pci_parse_of_addrs(struct of_device *op, +static void pci_parse_of_addrs(struct platform_device *op, struct device_node *node, struct pci_dev *dev) { @@ -248,7 +248,7 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, { struct dev_archdata *sd; struct pci_slot *slot; - struct of_device *op; + struct platform_device *op; struct pci_dev *dev; const char *type; u32 class; @@ -340,7 +340,7 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, dev->hdr_type = PCI_HEADER_TYPE_NORMAL; dev->rom_base_reg = PCI_ROM_ADDRESS; - dev->irq = sd->op->irqs[0]; + dev->irq = sd->op->archdata.irqs[0]; if (dev->irq == 0xffffffff) dev->irq = PCI_IRQ_NONE; } diff --git a/arch/sparc/kernel/pci_fire.c b/arch/sparc/kernel/pci_fire.c index 51cfa09e392a..efb896d68754 100644 --- a/arch/sparc/kernel/pci_fire.c +++ b/arch/sparc/kernel/pci_fire.c @@ -410,7 +410,7 @@ static void pci_fire_hw_init(struct pci_pbm_info *pbm) } static int __devinit pci_fire_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op, u32 portid) + struct platform_device *op, u32 portid) { const struct linux_prom64_registers *regs; struct device_node *dp = op->dev.of_node; @@ -455,7 +455,7 @@ static int __devinit pci_fire_pbm_init(struct pci_pbm_info *pbm, return 0; } -static int __devinit fire_probe(struct of_device *op, +static int __devinit fire_probe(struct platform_device *op, const struct of_device_id *match) { struct device_node *dp = op->dev.of_node; @@ -518,7 +518,7 @@ static struct of_platform_driver fire_driver = { static int __init fire_init(void) { - return of_register_driver(&fire_driver, &of_bus_type); + return of_register_platform_driver(&fire_driver); } subsys_initcall(fire_init); diff --git a/arch/sparc/kernel/pci_impl.h b/arch/sparc/kernel/pci_impl.h index 03186824327e..e20ed5f06e9c 100644 --- a/arch/sparc/kernel/pci_impl.h +++ b/arch/sparc/kernel/pci_impl.h @@ -91,7 +91,7 @@ struct pci_pbm_info { char *name; /* OBP specific information. */ - struct of_device *op; + struct platform_device *op; u64 ino_bitmap; /* PBM I/O and Memory space resources. */ diff --git a/arch/sparc/kernel/pci_psycho.c b/arch/sparc/kernel/pci_psycho.c index 558a70512824..22eab7cf3b11 100644 --- a/arch/sparc/kernel/pci_psycho.c +++ b/arch/sparc/kernel/pci_psycho.c @@ -285,7 +285,7 @@ static irqreturn_t psycho_ce_intr(int irq, void *dev_id) #define PSYCHO_ECCCTRL_CE 0x2000000000000000UL /* Enable CE INterrupts */ static void psycho_register_error_handlers(struct pci_pbm_info *pbm) { - struct of_device *op = of_find_device_by_node(pbm->op->dev.of_node); + struct platform_device *op = of_find_device_by_node(pbm->op->dev.of_node); unsigned long base = pbm->controller_regs; u64 tmp; int err; @@ -302,23 +302,23 @@ static void psycho_register_error_handlers(struct pci_pbm_info *pbm) * 5: POWER MANAGEMENT */ - if (op->num_irqs < 6) + if (op->archdata.num_irqs < 6) return; /* We really mean to ignore the return result here. Two * PCI controller share the same interrupt numbers and * drive the same front-end hardware. */ - err = request_irq(op->irqs[1], psycho_ue_intr, IRQF_SHARED, + err = request_irq(op->archdata.irqs[1], psycho_ue_intr, IRQF_SHARED, "PSYCHO_UE", pbm); - err = request_irq(op->irqs[2], psycho_ce_intr, IRQF_SHARED, + err = request_irq(op->archdata.irqs[2], psycho_ce_intr, IRQF_SHARED, "PSYCHO_CE", pbm); /* This one, however, ought not to fail. We can just warn * about it since the system can still operate properly even * if this fails. */ - err = request_irq(op->irqs[0], psycho_pcierr_intr, IRQF_SHARED, + err = request_irq(op->archdata.irqs[0], psycho_pcierr_intr, IRQF_SHARED, "PSYCHO_PCIERR", pbm); if (err) printk(KERN_WARNING "%s: Could not register PCIERR, " @@ -483,7 +483,7 @@ static void psycho_pbm_strbuf_init(struct pci_pbm_info *pbm, #define PSYCHO_MEMSPACE_SIZE 0x07fffffffUL static void __devinit psycho_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op, int is_pbm_a) + struct platform_device *op, int is_pbm_a) { psycho_pbm_init_common(pbm, op, "PSYCHO", PBM_CHIP_TYPE_PSYCHO); psycho_pbm_strbuf_init(pbm, is_pbm_a); @@ -503,7 +503,7 @@ static struct pci_pbm_info * __devinit psycho_find_sibling(u32 upa_portid) #define PSYCHO_CONFIGSPACE 0x001000000UL -static int __devinit psycho_probe(struct of_device *op, +static int __devinit psycho_probe(struct platform_device *op, const struct of_device_id *match) { const struct linux_prom64_registers *pr_regs; @@ -612,7 +612,7 @@ static struct of_platform_driver psycho_driver = { static int __init psycho_init(void) { - return of_register_driver(&psycho_driver, &of_bus_type); + return of_register_platform_driver(&psycho_driver); } subsys_initcall(psycho_init); diff --git a/arch/sparc/kernel/pci_sabre.c b/arch/sparc/kernel/pci_sabre.c index 6dad8e3b7506..5c3f5ec4cabc 100644 --- a/arch/sparc/kernel/pci_sabre.c +++ b/arch/sparc/kernel/pci_sabre.c @@ -311,7 +311,7 @@ static irqreturn_t sabre_ce_intr(int irq, void *dev_id) static void sabre_register_error_handlers(struct pci_pbm_info *pbm) { struct device_node *dp = pbm->op->dev.of_node; - struct of_device *op; + struct platform_device *op; unsigned long base = pbm->controller_regs; u64 tmp; int err; @@ -329,7 +329,7 @@ static void sabre_register_error_handlers(struct pci_pbm_info *pbm) * 2: CE ERR * 3: POWER FAIL */ - if (op->num_irqs < 4) + if (op->archdata.num_irqs < 4) return; /* We clear the error bits in the appropriate AFSR before @@ -341,7 +341,7 @@ static void sabre_register_error_handlers(struct pci_pbm_info *pbm) SABRE_UEAFSR_SDTE | SABRE_UEAFSR_PDTE), base + SABRE_UE_AFSR); - err = request_irq(op->irqs[1], sabre_ue_intr, 0, "SABRE_UE", pbm); + err = request_irq(op->archdata.irqs[1], sabre_ue_intr, 0, "SABRE_UE", pbm); if (err) printk(KERN_WARNING "%s: Couldn't register UE, err=%d.\n", pbm->name, err); @@ -351,11 +351,11 @@ static void sabre_register_error_handlers(struct pci_pbm_info *pbm) base + SABRE_CE_AFSR); - err = request_irq(op->irqs[2], sabre_ce_intr, 0, "SABRE_CE", pbm); + err = request_irq(op->archdata.irqs[2], sabre_ce_intr, 0, "SABRE_CE", pbm); if (err) printk(KERN_WARNING "%s: Couldn't register CE, err=%d.\n", pbm->name, err); - err = request_irq(op->irqs[0], psycho_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], psycho_pcierr_intr, 0, "SABRE_PCIERR", pbm); if (err) printk(KERN_WARNING "%s: Couldn't register PCIERR, err=%d.\n", @@ -443,7 +443,7 @@ static void __devinit sabre_scan_bus(struct pci_pbm_info *pbm, } static void __devinit sabre_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op) + struct platform_device *op) { psycho_pbm_init_common(pbm, op, "SABRE", PBM_CHIP_TYPE_SABRE); pbm->pci_afsr = pbm->controller_regs + SABRE_PIOAFSR; @@ -452,7 +452,7 @@ static void __devinit sabre_pbm_init(struct pci_pbm_info *pbm, sabre_scan_bus(pbm, &op->dev); } -static int __devinit sabre_probe(struct of_device *op, +static int __devinit sabre_probe(struct platform_device *op, const struct of_device_id *match) { const struct linux_prom64_registers *pr_regs; @@ -606,7 +606,7 @@ static struct of_platform_driver sabre_driver = { static int __init sabre_init(void) { - return of_register_driver(&sabre_driver, &of_bus_type); + return of_register_platform_driver(&sabre_driver); } subsys_initcall(sabre_init); diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index 97a1ae2e1c02..445a47a2fb3d 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -844,7 +844,7 @@ static int pbm_routes_this_ino(struct pci_pbm_info *pbm, u32 ino) */ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) { - struct of_device *op = of_find_device_by_node(pbm->op->dev.of_node); + struct platform_device *op = of_find_device_by_node(pbm->op->dev.of_node); u64 tmp, err_mask, err_no_mask; int err; @@ -857,14 +857,14 @@ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) */ if (pbm_routes_this_ino(pbm, SCHIZO_UE_INO)) { - err = request_irq(op->irqs[1], schizo_ue_intr, 0, + err = request_irq(op->archdata.irqs[1], schizo_ue_intr, 0, "TOMATILLO_UE", pbm); if (err) printk(KERN_WARNING "%s: Could not register UE, " "err=%d\n", pbm->name, err); } if (pbm_routes_this_ino(pbm, SCHIZO_CE_INO)) { - err = request_irq(op->irqs[2], schizo_ce_intr, 0, + err = request_irq(op->archdata.irqs[2], schizo_ce_intr, 0, "TOMATILLO_CE", pbm); if (err) printk(KERN_WARNING "%s: Could not register CE, " @@ -872,10 +872,10 @@ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) } err = 0; if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_A_INO)) { - err = request_irq(op->irqs[0], schizo_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0, "TOMATILLO_PCIERR", pbm); } else if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_B_INO)) { - err = request_irq(op->irqs[0], schizo_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0, "TOMATILLO_PCIERR", pbm); } if (err) @@ -883,7 +883,7 @@ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) "err=%d\n", pbm->name, err); if (pbm_routes_this_ino(pbm, SCHIZO_SERR_INO)) { - err = request_irq(op->irqs[3], schizo_safarierr_intr, 0, + err = request_irq(op->archdata.irqs[3], schizo_safarierr_intr, 0, "TOMATILLO_SERR", pbm); if (err) printk(KERN_WARNING "%s: Could not register SERR, " @@ -939,7 +939,7 @@ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) static void schizo_register_error_handlers(struct pci_pbm_info *pbm) { - struct of_device *op = of_find_device_by_node(pbm->op->dev.of_node); + struct platform_device *op = of_find_device_by_node(pbm->op->dev.of_node); u64 tmp, err_mask, err_no_mask; int err; @@ -952,14 +952,14 @@ static void schizo_register_error_handlers(struct pci_pbm_info *pbm) */ if (pbm_routes_this_ino(pbm, SCHIZO_UE_INO)) { - err = request_irq(op->irqs[1], schizo_ue_intr, 0, + err = request_irq(op->archdata.irqs[1], schizo_ue_intr, 0, "SCHIZO_UE", pbm); if (err) printk(KERN_WARNING "%s: Could not register UE, " "err=%d\n", pbm->name, err); } if (pbm_routes_this_ino(pbm, SCHIZO_CE_INO)) { - err = request_irq(op->irqs[2], schizo_ce_intr, 0, + err = request_irq(op->archdata.irqs[2], schizo_ce_intr, 0, "SCHIZO_CE", pbm); if (err) printk(KERN_WARNING "%s: Could not register CE, " @@ -967,10 +967,10 @@ static void schizo_register_error_handlers(struct pci_pbm_info *pbm) } err = 0; if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_A_INO)) { - err = request_irq(op->irqs[0], schizo_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0, "SCHIZO_PCIERR", pbm); } else if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_B_INO)) { - err = request_irq(op->irqs[0], schizo_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0, "SCHIZO_PCIERR", pbm); } if (err) @@ -978,7 +978,7 @@ static void schizo_register_error_handlers(struct pci_pbm_info *pbm) "err=%d\n", pbm->name, err); if (pbm_routes_this_ino(pbm, SCHIZO_SERR_INO)) { - err = request_irq(op->irqs[3], schizo_safarierr_intr, 0, + err = request_irq(op->archdata.irqs[3], schizo_safarierr_intr, 0, "SCHIZO_SERR", pbm); if (err) printk(KERN_WARNING "%s: Could not register SERR, " @@ -1307,7 +1307,7 @@ static void schizo_pbm_hw_init(struct pci_pbm_info *pbm) } static int __devinit schizo_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op, u32 portid, + struct platform_device *op, u32 portid, int chip_type) { const struct linux_prom64_registers *regs; @@ -1413,7 +1413,7 @@ static struct pci_pbm_info * __devinit schizo_find_sibling(u32 portid, return NULL; } -static int __devinit __schizo_init(struct of_device *op, unsigned long chip_type) +static int __devinit __schizo_init(struct platform_device *op, unsigned long chip_type) { struct device_node *dp = op->dev.of_node; struct pci_pbm_info *pbm; @@ -1460,7 +1460,7 @@ out_err: return err; } -static int __devinit schizo_probe(struct of_device *op, +static int __devinit schizo_probe(struct platform_device *op, const struct of_device_id *match) { return __schizo_init(op, (unsigned long) match->data); @@ -1501,7 +1501,7 @@ static struct of_platform_driver schizo_driver = { static int __init schizo_init(void) { - return of_register_driver(&schizo_driver, &of_bus_type); + return of_register_platform_driver(&schizo_driver); } subsys_initcall(schizo_init); diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index a24af6f7e17f..743344aa6d8a 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -879,7 +879,7 @@ static void pci_sun4v_msi_init(struct pci_pbm_info *pbm) #endif /* !(CONFIG_PCI_MSI) */ static int __devinit pci_sun4v_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op, u32 devhandle) + struct platform_device *op, u32 devhandle) { struct device_node *dp = op->dev.of_node; int err; @@ -918,7 +918,7 @@ static int __devinit pci_sun4v_pbm_init(struct pci_pbm_info *pbm, return 0; } -static int __devinit pci_sun4v_probe(struct of_device *op, +static int __devinit pci_sun4v_probe(struct platform_device *op, const struct of_device_id *match) { const struct linux_prom64_registers *regs; @@ -1019,7 +1019,7 @@ static struct of_platform_driver pci_sun4v_driver = { static int __init pci_sun4v_init(void) { - return of_register_driver(&pci_sun4v_driver, &of_bus_type); + return of_register_platform_driver(&pci_sun4v_driver); } subsys_initcall(pci_sun4v_init); diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 44faabc3c02c..357ced3c33ff 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -572,18 +572,18 @@ static u64 sparc_perf_event_update(struct perf_event *event, s64 delta; again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); new_raw_count = read_pmc(idx); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &hwc->period_left); + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); return new_raw_count; } @@ -591,27 +591,27 @@ again: static int sparc_perf_event_set_period(struct perf_event *event, struct hw_perf_event *hwc, int idx) { - s64 left = atomic64_read(&hwc->period_left); + s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0; if (unlikely(left <= -period)) { left = period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (left > MAX_PERIOD) left = MAX_PERIOD; - atomic64_set(&hwc->prev_count, (u64)-left); + local64_set(&hwc->prev_count, (u64)-left); write_pmc(idx, (u64)(-left) & 0xffffffff); @@ -1006,7 +1006,7 @@ static int sparc_pmu_enable(struct perf_event *event) * skip the schedulability test here, it will be peformed * at commit time(->commit_txn) as a whole */ - if (cpuc->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuc->group_flag & PERF_EVENT_TXN) goto nocheck; if (check_excludes(cpuc->event, n0, 1)) @@ -1088,7 +1088,7 @@ static int __hw_perf_event_init(struct perf_event *event) if (!hwc->sample_period) { hwc->sample_period = MAX_PERIOD; hwc->last_period = hwc->sample_period; - atomic64_set(&hwc->period_left, hwc->sample_period); + local64_set(&hwc->period_left, hwc->sample_period); } return 0; @@ -1103,7 +1103,7 @@ static void sparc_pmu_start_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - cpuhw->group_flag |= PERF_EVENT_TXN_STARTED; + cpuhw->group_flag |= PERF_EVENT_TXN; } /* @@ -1115,7 +1115,7 @@ static void sparc_pmu_cancel_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED; + cpuhw->group_flag &= ~PERF_EVENT_TXN; } /* @@ -1138,6 +1138,7 @@ static int sparc_pmu_commit_txn(const struct pmu *pmu) if (sparc_check_constraints(cpuc->event, cpuc->events, n)) return -EAGAIN; + cpuc->group_flag &= ~PERF_EVENT_TXN; return 0; } diff --git a/arch/sparc/kernel/pmc.c b/arch/sparc/kernel/pmc.c index 9589d8b9b0c1..94536a85f161 100644 --- a/arch/sparc/kernel/pmc.c +++ b/arch/sparc/kernel/pmc.c @@ -51,7 +51,7 @@ static void pmc_swift_idle(void) #endif } -static int __devinit pmc_probe(struct of_device *op, +static int __devinit pmc_probe(struct platform_device *op, const struct of_device_id *match) { regs = of_ioremap(&op->resource[0], 0, @@ -89,7 +89,7 @@ static struct of_platform_driver pmc_driver = { static int __init pmc_init(void) { - return of_register_driver(&pmc_driver, &of_bus_type); + return of_register_platform_driver(&pmc_driver); } /* This driver is not critical to the boot process diff --git a/arch/sparc/kernel/power.c b/arch/sparc/kernel/power.c index 168d4cb63f5b..2c59f4d387dd 100644 --- a/arch/sparc/kernel/power.c +++ b/arch/sparc/kernel/power.c @@ -33,10 +33,10 @@ static int __devinit has_button_interrupt(unsigned int irq, struct device_node * return 1; } -static int __devinit power_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit power_probe(struct platform_device *op, const struct of_device_id *match) { struct resource *res = &op->resource[0]; - unsigned int irq= op->irqs[0]; + unsigned int irq = op->archdata.irqs[0]; power_reg = of_ioremap(res, 0, 0x4, "power"); @@ -70,7 +70,7 @@ static struct of_platform_driver power_driver = { static int __init power_init(void) { - return of_register_driver(&power_driver, &of_platform_bus_type); + return of_register_platform_driver(&power_driver); } device_initcall(power_init); diff --git a/arch/sparc/kernel/prom.h b/arch/sparc/kernel/prom.h index a8591ef2636d..eeb04a782ec8 100644 --- a/arch/sparc/kernel/prom.h +++ b/arch/sparc/kernel/prom.h @@ -9,14 +9,6 @@ extern void irq_trans_init(struct device_node *dp); extern unsigned int prom_unique_id; -static inline int is_root_node(const struct device_node *dp) -{ - if (!dp) - return 0; - - return (dp->parent == NULL); -} - extern char *build_path_component(struct device_node *dp); extern void of_console_init(void); diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index 466a32763ea8..86597d9867fd 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -21,7 +21,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/memblock.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <asm/prom.h> #include <asm/oplib.h> @@ -81,7 +81,7 @@ static void __init sun4v_path_component(struct device_node *dp, char *tmp_buf) return; regs = rprop->value; - if (!is_root_node(dp->parent)) { + if (!of_node_is_root(dp->parent)) { sprintf(tmp_buf, "%s@%x,%x", dp->name, (unsigned int) (regs->phys_addr >> 32UL), @@ -121,7 +121,7 @@ static void __init sun4u_path_component(struct device_node *dp, char *tmp_buf) return; regs = prop->value; - if (!is_root_node(dp->parent)) { + if (!of_node_is_root(dp->parent)) { sprintf(tmp_buf, "%s@%x,%x", dp->name, (unsigned int) (regs->phys_addr >> 32UL), diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c index 57ac9e28be0c..1f830da2ddf2 100644 --- a/arch/sparc/kernel/prom_common.c +++ b/arch/sparc/kernel/prom_common.c @@ -244,7 +244,7 @@ char * __init build_full_name(struct device_node *dp) n = prom_early_alloc(len); strcpy(n, dp->parent->full_name); - if (!is_root_node(dp->parent)) { + if (!of_node_is_root(dp->parent)) { strcpy(n + plen, "/"); plen++; } diff --git a/arch/sparc/kernel/prom_irqtrans.c b/arch/sparc/kernel/prom_irqtrans.c index 5702ad4710cb..ce651147fabc 100644 --- a/arch/sparc/kernel/prom_irqtrans.c +++ b/arch/sparc/kernel/prom_irqtrans.c @@ -719,7 +719,7 @@ static unsigned int central_build_irq(struct device_node *dp, void *_data) { struct device_node *central_dp = _data; - struct of_device *central_op = of_find_device_by_node(central_dp); + struct platform_device *central_op = of_find_device_by_node(central_dp); struct resource *res; unsigned long imap, iclr; u32 tmp; diff --git a/arch/sparc/kernel/psycho_common.c b/arch/sparc/kernel/psycho_common.c index 3f34ac853931..fe2af66bb198 100644 --- a/arch/sparc/kernel/psycho_common.c +++ b/arch/sparc/kernel/psycho_common.c @@ -447,7 +447,7 @@ int psycho_iommu_init(struct pci_pbm_info *pbm, int tsbsize, } -void psycho_pbm_init_common(struct pci_pbm_info *pbm, struct of_device *op, +void psycho_pbm_init_common(struct pci_pbm_info *pbm, struct platform_device *op, const char *chip_name, int chip_type) { struct device_node *dp = op->dev.of_node; diff --git a/arch/sparc/kernel/psycho_common.h b/arch/sparc/kernel/psycho_common.h index 092c278ef28d..590b4ed8ab5e 100644 --- a/arch/sparc/kernel/psycho_common.h +++ b/arch/sparc/kernel/psycho_common.h @@ -42,7 +42,7 @@ extern int psycho_iommu_init(struct pci_pbm_info *pbm, int tsbsize, unsigned long write_complete_offset); extern void psycho_pbm_init_common(struct pci_pbm_info *pbm, - struct of_device *op, + struct platform_device *op, const char *chip_name, int chip_type); #endif /* _PSYCHO_COMMON_H */ diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c index cfeaf04b9cdf..2ca32d13abcf 100644 --- a/arch/sparc/kernel/sbus.c +++ b/arch/sparc/kernel/sbus.c @@ -57,7 +57,7 @@ void sbus_set_sbus64(struct device *dev, int bursts) { struct iommu *iommu = dev->archdata.iommu; - struct of_device *op = to_of_device(dev); + struct platform_device *op = to_platform_device(dev); const struct linux_prom_registers *regs; unsigned long cfg_reg; int slot; @@ -204,7 +204,7 @@ static unsigned long sysio_imap_to_iclr(unsigned long imap) return imap + diff; } -static unsigned int sbus_build_irq(struct of_device *op, unsigned int ino) +static unsigned int sbus_build_irq(struct platform_device *op, unsigned int ino) { struct iommu *iommu = op->dev.archdata.iommu; unsigned long reg_base = iommu->write_complete_reg - 0x2000UL; @@ -267,7 +267,7 @@ static unsigned int sbus_build_irq(struct of_device *op, unsigned int ino) #define SYSIO_UEAFSR_RESV2 0x0000001fffffffffUL /* Reserved */ static irqreturn_t sysio_ue_handler(int irq, void *dev_id) { - struct of_device *op = dev_id; + struct platform_device *op = dev_id; struct iommu *iommu = op->dev.archdata.iommu; unsigned long reg_base = iommu->write_complete_reg - 0x2000UL; unsigned long afsr_reg, afar_reg; @@ -341,7 +341,7 @@ static irqreturn_t sysio_ue_handler(int irq, void *dev_id) #define SYSIO_CEAFSR_RESV2 0x0000001fffffffffUL /* Reserved */ static irqreturn_t sysio_ce_handler(int irq, void *dev_id) { - struct of_device *op = dev_id; + struct platform_device *op = dev_id; struct iommu *iommu = op->dev.archdata.iommu; unsigned long reg_base = iommu->write_complete_reg - 0x2000UL; unsigned long afsr_reg, afar_reg; @@ -420,7 +420,7 @@ static irqreturn_t sysio_ce_handler(int irq, void *dev_id) #define SYSIO_SBAFSR_RESV3 0x0000001fffffffffUL /* Reserved */ static irqreturn_t sysio_sbus_error_handler(int irq, void *dev_id) { - struct of_device *op = dev_id; + struct platform_device *op = dev_id; struct iommu *iommu = op->dev.archdata.iommu; unsigned long afsr_reg, afar_reg, reg_base; unsigned long afsr, afar, error_bits; @@ -488,7 +488,7 @@ static irqreturn_t sysio_sbus_error_handler(int irq, void *dev_id) #define SYSIO_CE_INO 0x35 #define SYSIO_SBUSERR_INO 0x36 -static void __init sysio_register_error_handlers(struct of_device *op) +static void __init sysio_register_error_handlers(struct platform_device *op) { struct iommu *iommu = op->dev.archdata.iommu; unsigned long reg_base = iommu->write_complete_reg - 0x2000UL; @@ -534,7 +534,7 @@ static void __init sysio_register_error_handlers(struct of_device *op) } /* Boot time initialization. */ -static void __init sbus_iommu_init(struct of_device *op) +static void __init sbus_iommu_init(struct platform_device *op) { const struct linux_prom64_registers *pr; struct device_node *dp = op->dev.of_node; @@ -663,7 +663,7 @@ static int __init sbus_init(void) struct device_node *dp; for_each_node_by_name(dp, "sbus") { - struct of_device *op = of_find_device_by_node(dp); + struct platform_device *op = of_find_device_by_node(dp); sbus_iommu_init(op); of_propagate_archdata(op); diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c index e404b063be2c..9c743b1886ff 100644 --- a/arch/sparc/kernel/time_32.c +++ b/arch/sparc/kernel/time_32.c @@ -142,7 +142,7 @@ static struct platform_device m48t59_rtc = { }, }; -static int __devinit clock_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit clock_probe(struct platform_device *op, const struct of_device_id *match) { struct device_node *dp = op->dev.of_node; const char *model = of_get_property(dp, "model", NULL); @@ -189,7 +189,7 @@ static struct of_platform_driver clock_driver = { /* Probe for the mostek real time clock chip. */ static int __init clock_init(void) { - return of_register_driver(&clock_driver, &of_platform_bus_type); + return of_register_platform_driver(&clock_driver); } /* Must be after subsys_initcall() so that busses are probed. Must * be before device_initcall() because things like the RTC driver diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 21e9fcae0668..3bc9c9979b92 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -419,7 +419,7 @@ static struct platform_device rtc_cmos_device = { .num_resources = 1, }; -static int __devinit rtc_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit rtc_probe(struct platform_device *op, const struct of_device_id *match) { struct resource *r; @@ -477,7 +477,7 @@ static struct platform_device rtc_bq4802_device = { .num_resources = 1, }; -static int __devinit bq4802_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit bq4802_probe(struct platform_device *op, const struct of_device_id *match) { printk(KERN_INFO "%s: BQ4802 regs at 0x%llx\n", @@ -534,7 +534,7 @@ static struct platform_device m48t59_rtc = { }, }; -static int __devinit mostek_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit mostek_probe(struct platform_device *op, const struct of_device_id *match) { struct device_node *dp = op->dev.of_node; @@ -586,9 +586,9 @@ static int __init clock_init(void) if (tlb_type == hypervisor) return platform_device_register(&rtc_sun4v_device); - (void) of_register_driver(&rtc_driver, &of_platform_bus_type); - (void) of_register_driver(&mostek_driver, &of_platform_bus_type); - (void) of_register_driver(&bq4802_driver, &of_platform_bus_type); + (void) of_register_platform_driver(&rtc_driver); + (void) of_register_platform_driver(&mostek_driver); + (void) of_register_platform_driver(&bq4802_driver); return 0; } diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c index 005e758a4db7..fc58c3e917df 100644 --- a/arch/sparc/mm/io-unit.c +++ b/arch/sparc/mm/io-unit.c @@ -35,7 +35,7 @@ #define IOPERM (IOUPTE_CACHE | IOUPTE_WRITE | IOUPTE_VALID) #define MKIOPTE(phys) __iopte((((phys)>>4) & IOUPTE_PAGE) | IOPERM) -static void __init iounit_iommu_init(struct of_device *op) +static void __init iounit_iommu_init(struct platform_device *op) { struct iounit_struct *iounit; iopte_t *xpt, *xptend; @@ -74,7 +74,7 @@ static int __init iounit_init(void) struct device_node *dp; for_each_node_by_name(dp, "sbi") { - struct of_device *op = of_find_device_by_node(dp); + struct platform_device *op = of_find_device_by_node(dp); iounit_iommu_init(op); of_propagate_archdata(op); diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 0e8ae298b3c3..07fc6a65d9b6 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -56,7 +56,7 @@ static pgprot_t dvma_prot; /* Consistent mapping pte flags */ #define IOPERM (IOPTE_CACHE | IOPTE_WRITE | IOPTE_VALID) #define MKIOPTE(pfn, perm) (((((pfn)<<8) & IOPTE_PAGE) | (perm)) & ~IOPTE_WAZ) -static void __init sbus_iommu_init(struct of_device *op) +static void __init sbus_iommu_init(struct platform_device *op) { struct iommu_struct *iommu; unsigned int impl, vers; @@ -132,7 +132,7 @@ static int __init iommu_init(void) struct device_node *dp; for_each_node_by_name(dp, "iommu") { - struct of_device *op = of_find_device_by_node(dp); + struct platform_device *op = of_find_device_by_node(dp); sbus_iommu_init(op); of_propagate_archdata(op); diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h index 084de4a9fc70..0032f9212e74 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-3level.h @@ -60,7 +60,7 @@ set_pud(pud, __pud(_PAGE_TABLE + __pa(pmd))) #ifdef CONFIG_64BIT -#define set_pud(pudptr, pudval) set_64bit((phys_t *) (pudptr), pud_val(pudval)) +#define set_pud(pudptr, pudval) set_64bit((u64 *) (pudptr), pud_val(pudval)) #else #define set_pud(pudptr, pudval) (*(pudptr) = (pudval)) #endif @@ -73,7 +73,7 @@ static inline int pgd_newpage(pgd_t pgd) static inline void pgd_mkuptodate(pgd_t pgd) { pgd_val(pgd) &= ~_PAGE_NEWPAGE; } #ifdef CONFIG_64BIT -#define set_pmd(pmdptr, pmdval) set_64bit((phys_t *) (pmdptr), pmd_val(pmdval)) +#define set_pmd(pmdptr, pmdval) set_64bit((u64 *) (pmdptr), pmd_val(pmdval)) #else #define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) #endif diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dcb0593b4a66..6f77afa6bca9 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -55,6 +55,7 @@ config X86 select HAVE_HW_BREAKPOINT select HAVE_MIXED_BREAKPOINTS_REGS select PERF_EVENTS + select HAVE_PERF_EVENTS_NMI select ANON_INODES select HAVE_ARCH_KMEMCHECK select HAVE_USER_RETURN_NOTIFIER diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index ec749c2bfdd7..f7cb086b4add 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -26,10 +26,10 @@ targets := vmlinux.bin setup.bin setup.elf bzImage targets += fdimage fdimage144 fdimage288 image.iso mtools.conf subdir- := compressed -setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o edd.o -setup-y += header.o main.o mca.o memory.o pm.o pmjump.o -setup-y += printf.o regs.o string.o tty.o video.o video-mode.o -setup-y += version.o +setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o +setup-y += early_serial_console.o edd.o header.o main.o mca.o memory.o +setup-y += pm.o pmjump.o printf.o regs.o string.o tty.o video.o +setup-y += video-mode.o version.o setup-$(CONFIG_X86_APM_BOOT) += apm.o # The link order of the video-*.o modules can matter. In particular, diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 98239d2658f2..c7093bd9f2d3 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -28,6 +28,7 @@ #include "bitops.h" #include <asm/cpufeature.h> #include <asm/processor-flags.h> +#include "ctype.h" /* Useful macros */ #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) @@ -37,6 +38,8 @@ extern struct setup_header hdr; extern struct boot_params boot_params; +#define cpu_relax() asm volatile("rep; nop") + /* Basic port I/O */ static inline void outb(u8 v, u16 port) { @@ -198,11 +201,6 @@ static inline int memcmp_gs(const void *s1, addr_t s2, size_t len) return diff; } -static inline int isdigit(int ch) -{ - return (ch >= '0') && (ch <= '9'); -} - /* Heap -- available for dynamic lists. */ extern char _end[]; extern char *HEAP; @@ -287,8 +285,18 @@ struct biosregs { void intcall(u8 int_no, const struct biosregs *ireg, struct biosregs *oreg); /* cmdline.c */ -int cmdline_find_option(const char *option, char *buffer, int bufsize); -int cmdline_find_option_bool(const char *option); +int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int bufsize); +int __cmdline_find_option_bool(u32 cmdline_ptr, const char *option); +static inline int cmdline_find_option(const char *option, char *buffer, int bufsize) +{ + return __cmdline_find_option(boot_params.hdr.cmd_line_ptr, option, buffer, bufsize); +} + +static inline int cmdline_find_option_bool(const char *option) +{ + return __cmdline_find_option_bool(boot_params.hdr.cmd_line_ptr, option); +} + /* cpu.c, cpucheck.c */ struct cpu_features { @@ -300,6 +308,10 @@ extern struct cpu_features cpu; int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr); int validate_cpu(void); +/* early_serial_console.c */ +extern int early_serial_base; +void console_init(void); + /* edd.c */ void query_edd(void); @@ -329,8 +341,10 @@ void initregs(struct biosregs *regs); /* string.c */ int strcmp(const char *str1, const char *str2); +int strncmp(const char *cs, const char *ct, size_t count); size_t strnlen(const char *s, size_t maxlen); unsigned int atou(const char *s); +unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base); /* tty.c */ void puts(const char *); diff --git a/arch/x86/boot/cmdline.c b/arch/x86/boot/cmdline.c index a1d35634bce0..6b3b6f708c04 100644 --- a/arch/x86/boot/cmdline.c +++ b/arch/x86/boot/cmdline.c @@ -27,9 +27,8 @@ static inline int myisspace(u8 c) * Returns the length of the argument (regardless of if it was * truncated to fit in the buffer), or -1 on not found. */ -int cmdline_find_option(const char *option, char *buffer, int bufsize) +int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int bufsize) { - u32 cmdline_ptr = boot_params.hdr.cmd_line_ptr; addr_t cptr; char c; int len = -1; @@ -100,9 +99,8 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize) * Returns the position of that option (starts counting with 1) * or 0 on not found */ -int cmdline_find_option_bool(const char *option) +int __cmdline_find_option_bool(u32 cmdline_ptr, const char *option) { - u32 cmdline_ptr = boot_params.hdr.cmd_line_ptr; addr_t cptr; char c; int pos = 0, wstart = 0; diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index fbb47daf2459..0c229551eead 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,7 +4,7 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(BITS).o misc.o piggy.o +targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC @@ -23,7 +23,7 @@ LDFLAGS_vmlinux := -T hostprogs-y := mkpiggy -$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE +$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o $(obj)/piggy.o FORCE $(call if_changed,ld) @: diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c new file mode 100644 index 000000000000..cb62f786990d --- /dev/null +++ b/arch/x86/boot/compressed/cmdline.c @@ -0,0 +1,21 @@ +#include "misc.h" + +static unsigned long fs; +static inline void set_fs(unsigned long seg) +{ + fs = seg << 4; /* shift it back */ +} +typedef unsigned long addr_t; +static inline char rdfs8(addr_t addr) +{ + return *((char *)(fs + addr)); +} +#include "../cmdline.c" +int cmdline_find_option(const char *option, char *buffer, int bufsize) +{ + return __cmdline_find_option(real_mode->hdr.cmd_line_ptr, option, buffer, bufsize); +} +int cmdline_find_option_bool(const char *option) +{ + return __cmdline_find_option_bool(real_mode->hdr.cmd_line_ptr, option); +} diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c new file mode 100644 index 000000000000..261e81fb9582 --- /dev/null +++ b/arch/x86/boot/compressed/early_serial_console.c @@ -0,0 +1,5 @@ +#include "misc.h" + +int early_serial_base; + +#include "../early_serial_console.c" diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index f543b70ffae2..67a655a39ce4 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -124,6 +124,19 @@ relocated: rep stosl /* + * Adjust our own GOT + */ + leal _got(%ebx), %edx + leal _egot(%ebx), %ecx +1: + cmpl %ecx, %edx + jae 2f + addl %ebx, (%edx) + addl $4, %edx + jmp 1b +2: + +/* * Do the decompression, and jump to the new kernel.. */ leal z_extract_offset_negative(%ebx), %ebp diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index faff0dc9c06a..52f85a196fa0 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -280,6 +280,19 @@ relocated: rep stosq /* + * Adjust our own GOT + */ + leaq _got(%rip), %rdx + leaq _egot(%rip), %rcx +1: + cmpq %rcx, %rdx + jae 2f + addq %rbx, (%rdx) + addq $8, %rdx + jmp 1b +2: + +/* * Do the decompression, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 51e240779a44..8f7bef8e9fff 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -9,23 +9,7 @@ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996 */ -/* - * we have to be careful, because no indirections are allowed here, and - * paravirt_ops is a kind of one. As it will only run in baremetal anyway, - * we just keep it from happening - */ -#undef CONFIG_PARAVIRT -#ifdef CONFIG_X86_32 -#define _ASM_X86_DESC_H 1 -#endif - -#include <linux/linkage.h> -#include <linux/screen_info.h> -#include <linux/elf.h> -#include <linux/io.h> -#include <asm/page.h> -#include <asm/boot.h> -#include <asm/bootparam.h> +#include "misc.h" /* WARNING!! * This code is compiled with -fPIC and it is relocated dynamically @@ -123,15 +107,13 @@ static void error(char *m); /* * This is set up by the setup-routine at boot-time */ -static struct boot_params *real_mode; /* Pointer to real-mode data */ +struct boot_params *real_mode; /* Pointer to real-mode data */ static int quiet; +static int debug; void *memset(void *s, int c, size_t n); void *memcpy(void *dest, const void *src, size_t n); -static void __putstr(int, const char *); -#define putstr(__x) __putstr(0, __x) - #ifdef CONFIG_X86_64 #define memptr long #else @@ -170,7 +152,21 @@ static void scroll(void) vidmem[i] = ' '; } -static void __putstr(int error, const char *s) +#define XMTRDY 0x20 + +#define TXR 0 /* Transmit register (WRITE) */ +#define LSR 5 /* Line Status */ +static void serial_putchar(int ch) +{ + unsigned timeout = 0xffff; + + while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout) + cpu_relax(); + + outb(ch, early_serial_base + TXR); +} + +void __putstr(int error, const char *s) { int x, y, pos; char c; @@ -179,6 +175,14 @@ static void __putstr(int error, const char *s) if (!error) return; #endif + if (early_serial_base) { + const char *str = s; + while (*str) { + if (*str == '\n') + serial_putchar('\r'); + serial_putchar(*str++); + } + } if (real_mode->screen_info.orig_video_mode == 0 && lines == 0 && cols == 0) @@ -305,8 +309,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, { real_mode = rmode; - if (real_mode->hdr.loadflags & QUIET_FLAG) + if (cmdline_find_option_bool("quiet")) quiet = 1; + if (cmdline_find_option_bool("debug")) + debug = 1; if (real_mode->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; @@ -319,6 +325,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, lines = real_mode->screen_info.orig_video_lines; cols = real_mode->screen_info.orig_video_cols; + console_init(); + if (debug) + putstr("early console in decompress_kernel\n"); + free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h new file mode 100644 index 000000000000..3f19c81a6203 --- /dev/null +++ b/arch/x86/boot/compressed/misc.h @@ -0,0 +1,39 @@ +#ifndef BOOT_COMPRESSED_MISC_H +#define BOOT_COMPRESSED_MISC_H + +/* + * we have to be careful, because no indirections are allowed here, and + * paravirt_ops is a kind of one. As it will only run in baremetal anyway, + * we just keep it from happening + */ +#undef CONFIG_PARAVIRT +#ifdef CONFIG_X86_32 +#define _ASM_X86_DESC_H 1 +#endif + +#include <linux/linkage.h> +#include <linux/screen_info.h> +#include <linux/elf.h> +#include <linux/io.h> +#include <asm/page.h> +#include <asm/boot.h> +#include <asm/bootparam.h> + +#define BOOT_BOOT_H +#include "../ctype.h" + +/* misc.c */ +extern struct boot_params *real_mode; /* Pointer to real-mode data */ +void __putstr(int error, const char *s); +#define putstr(__x) __putstr(0, __x) +#define puts(__x) __putstr(0, __x) + +/* cmdline.c */ +int cmdline_find_option(const char *option, char *buffer, int bufsize); +int cmdline_find_option_bool(const char *option); + +/* early_serial_console.c */ +extern int early_serial_base; +void console_init(void); + +#endif diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c new file mode 100644 index 000000000000..19b3e693cd72 --- /dev/null +++ b/arch/x86/boot/compressed/string.c @@ -0,0 +1,2 @@ +#include "misc.h" +#include "../string.c" diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 5ddabceee124..34d047c98284 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -41,6 +41,12 @@ SECTIONS *(.rodata.*) _erodata = . ; } + .got : { + _got = .; + KEEP(*(.got.plt)) + KEEP(*(.got)) + _egot = .; + } .data : { _data = . ; *(.data) diff --git a/arch/x86/boot/ctype.h b/arch/x86/boot/ctype.h new file mode 100644 index 000000000000..25e13403193c --- /dev/null +++ b/arch/x86/boot/ctype.h @@ -0,0 +1,21 @@ +#ifndef BOOT_ISDIGIT_H + +#define BOOT_ISDIGIT_H + +static inline int isdigit(int ch) +{ + return (ch >= '0') && (ch <= '9'); +} + +static inline int isxdigit(int ch) +{ + if (isdigit(ch)) + return true; + + if ((ch >= 'a') && (ch <= 'f')) + return true; + + return (ch >= 'A') && (ch <= 'F'); +} + +#endif diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c new file mode 100644 index 000000000000..030f4b93e255 --- /dev/null +++ b/arch/x86/boot/early_serial_console.c @@ -0,0 +1,139 @@ +#include "boot.h" + +#define DEFAULT_SERIAL_PORT 0x3f8 /* ttyS0 */ + +#define XMTRDY 0x20 + +#define DLAB 0x80 + +#define TXR 0 /* Transmit register (WRITE) */ +#define RXR 0 /* Receive register (READ) */ +#define IER 1 /* Interrupt Enable */ +#define IIR 2 /* Interrupt ID */ +#define FCR 2 /* FIFO control */ +#define LCR 3 /* Line control */ +#define MCR 4 /* Modem control */ +#define LSR 5 /* Line Status */ +#define MSR 6 /* Modem Status */ +#define DLL 0 /* Divisor Latch Low */ +#define DLH 1 /* Divisor latch High */ + +#define DEFAULT_BAUD 9600 + +static void early_serial_init(int port, int baud) +{ + unsigned char c; + unsigned divisor; + + outb(0x3, port + LCR); /* 8n1 */ + outb(0, port + IER); /* no interrupt */ + outb(0, port + FCR); /* no fifo */ + outb(0x3, port + MCR); /* DTR + RTS */ + + divisor = 115200 / baud; + c = inb(port + LCR); + outb(c | DLAB, port + LCR); + outb(divisor & 0xff, port + DLL); + outb((divisor >> 8) & 0xff, port + DLH); + outb(c & ~DLAB, port + LCR); + + early_serial_base = port; +} + +static void parse_earlyprintk(void) +{ + int baud = DEFAULT_BAUD; + char arg[32]; + int pos = 0; + int port = 0; + + if (cmdline_find_option("earlyprintk", arg, sizeof arg) > 0) { + char *e; + + if (!strncmp(arg, "serial", 6)) { + port = DEFAULT_SERIAL_PORT; + pos += 6; + } + + if (arg[pos] == ',') + pos++; + + if (!strncmp(arg, "ttyS", 4)) { + static const int bases[] = { 0x3f8, 0x2f8 }; + int idx = 0; + + if (!strncmp(arg + pos, "ttyS", 4)) + pos += 4; + + if (arg[pos++] == '1') + idx = 1; + + port = bases[idx]; + } + + if (arg[pos] == ',') + pos++; + + baud = simple_strtoull(arg + pos, &e, 0); + if (baud == 0 || arg + pos == e) + baud = DEFAULT_BAUD; + } + + if (port) + early_serial_init(port, baud); +} + +#define BASE_BAUD (1843200/16) +static unsigned int probe_baud(int port) +{ + unsigned char lcr, dll, dlh; + unsigned int quot; + + lcr = inb(port + LCR); + outb(lcr | DLAB, port + LCR); + dll = inb(port + DLL); + dlh = inb(port + DLH); + outb(lcr, port + LCR); + quot = (dlh << 8) | dll; + + return BASE_BAUD / quot; +} + +static void parse_console_uart8250(void) +{ + char optstr[64], *options; + int baud = DEFAULT_BAUD; + int port = 0; + + /* + * console=uart8250,io,0x3f8,115200n8 + * need to make sure it is last one console ! + */ + if (cmdline_find_option("console", optstr, sizeof optstr) <= 0) + return; + + options = optstr; + + if (!strncmp(options, "uart8250,io,", 12)) + port = simple_strtoull(options + 12, &options, 0); + else if (!strncmp(options, "uart,io,", 8)) + port = simple_strtoull(options + 8, &options, 0); + else + return; + + if (options && (options[0] == ',')) + baud = simple_strtoull(options + 1, &options, 0); + else + baud = probe_baud(port); + + if (port) + early_serial_init(port, baud); +} + +void console_init(void) +{ + parse_earlyprintk(); + + if (!early_serial_base) + parse_console_uart8250(); +} diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index 140172b895bd..40358c8905be 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -130,6 +130,11 @@ void main(void) /* First, copy the boot header into the "zeropage" */ copy_boot_params(); + /* Initialize the early-boot console */ + console_init(); + if (cmdline_find_option_bool("debug")) + puts("early console in setup code\n"); + /* End of heap check */ init_heap(); @@ -168,10 +173,6 @@ void main(void) /* Set the video mode */ set_video(); - /* Parse command line for 'quiet' and pass it to decompressor. */ - if (cmdline_find_option_bool("quiet")) - boot_params.hdr.loadflags |= QUIET_FLAG; - /* Do the last things and invoke protected mode */ go_to_protected_mode(); } diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c index 50e47cdbdddd..cdac91ca55d3 100644 --- a/arch/x86/boot/printf.c +++ b/arch/x86/boot/printf.c @@ -34,7 +34,7 @@ static int skip_atoi(const char **s) #define SMALL 32 /* Must be 32 == 0x20 */ #define SPECIAL 64 /* 0x */ -#define do_div(n,base) ({ \ +#define __do_div(n, base) ({ \ int __res; \ __res = ((unsigned long) n) % (unsigned) base; \ n = ((unsigned long) n) / (unsigned) base; \ @@ -83,7 +83,7 @@ static char *number(char *str, long num, int base, int size, int precision, tmp[i++] = '0'; else while (num != 0) - tmp[i++] = (digits[do_div(num, base)] | locase); + tmp[i++] = (digits[__do_div(num, base)] | locase); if (i > precision) precision = i; size -= precision; diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index f94b7a0c2abf..3cbc4058dd26 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -30,6 +30,22 @@ int strcmp(const char *str1, const char *str2) return 0; } +int strncmp(const char *cs, const char *ct, size_t count) +{ + unsigned char c1, c2; + + while (count) { + c1 = *cs++; + c2 = *ct++; + if (c1 != c2) + return c1 < c2 ? -1 : 1; + if (!c1) + break; + count--; + } + return 0; +} + size_t strnlen(const char *s, size_t maxlen) { const char *es = s; @@ -48,3 +64,50 @@ unsigned int atou(const char *s) i = i * 10 + (*s++ - '0'); return i; } + +/* Works only for digits and letters, but small and fast */ +#define TOLOWER(x) ((x) | 0x20) + +static unsigned int simple_guess_base(const char *cp) +{ + if (cp[0] == '0') { + if (TOLOWER(cp[1]) == 'x' && isxdigit(cp[2])) + return 16; + else + return 8; + } else { + return 10; + } +} + +/** + * simple_strtoull - convert a string to an unsigned long long + * @cp: The start of the string + * @endp: A pointer to the end of the parsed string will be placed here + * @base: The number base to use + */ + +unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) +{ + unsigned long long result = 0; + + if (!base) + base = simple_guess_base(cp); + + if (base == 16 && cp[0] == '0' && TOLOWER(cp[1]) == 'x') + cp += 2; + + while (isxdigit(*cp)) { + unsigned int value; + + value = isdigit(*cp) ? *cp - '0' : TOLOWER(*cp) - 'a' + 10; + if (value >= base) + break; + result = result * base + value; + cp++; + } + if (endp) + *endp = (char *)cp; + + return result; +} diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c index 01ec69c901c7..def2451f46ae 100644 --- a/arch/x86/boot/tty.c +++ b/arch/x86/boot/tty.c @@ -10,23 +10,36 @@ * ----------------------------------------------------------------------- */ /* - * Very simple screen I/O - * XXX: Probably should add very simple serial I/O? + * Very simple screen and serial I/O */ #include "boot.h" +int early_serial_base; + +#define XMTRDY 0x20 + +#define TXR 0 /* Transmit register (WRITE) */ +#define LSR 5 /* Line Status */ + /* * These functions are in .inittext so they can be used to signal * error during initialization. */ -void __attribute__((section(".inittext"))) putchar(int ch) +static void __attribute__((section(".inittext"))) serial_putchar(int ch) { - struct biosregs ireg; + unsigned timeout = 0xffff; - if (ch == '\n') - putchar('\r'); /* \n -> \r\n */ + while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout) + cpu_relax(); + + outb(ch, early_serial_base + TXR); +} + +static void __attribute__((section(".inittext"))) bios_putchar(int ch) +{ + struct biosregs ireg; initregs(&ireg); ireg.bx = 0x0007; @@ -36,6 +49,17 @@ void __attribute__((section(".inittext"))) putchar(int ch) intcall(0x10, &ireg, NULL); } +void __attribute__((section(".inittext"))) putchar(int ch) +{ + if (ch == '\n') + putchar('\r'); /* \n -> \r\n */ + + bios_putchar(ch); + + if (early_serial_base != 0) + serial_putchar(ch); +} + void __attribute__((section(".inittext"))) puts(const char *str) { while (*str) @@ -112,3 +136,4 @@ int getchar_timeout(void) return 0; /* Timeout! */ } + diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index d28fad19654a..e3a32431ca1e 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1471,6 +1471,7 @@ CONFIG_HWMON=y # CONFIG_SENSORS_GL518SM is not set # CONFIG_SENSORS_GL520SM is not set # CONFIG_SENSORS_CORETEMP is not set +# CONFIG_SENSORS_PKGTEMP is not set # CONFIG_SENSORS_IT87 is not set # CONFIG_SENSORS_LM63 is not set # CONFIG_SENSORS_LM75 is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 6c86acd847a4..4251f8372050 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1456,6 +1456,7 @@ CONFIG_HWMON=y # CONFIG_SENSORS_GL518SM is not set # CONFIG_SENSORS_GL520SM is not set # CONFIG_SENSORS_CORETEMP is not set +# CONFIG_SENSORS_PKGTEMP is not set # CONFIG_SENSORS_IT87 is not set # CONFIG_SENSORS_LM63 is not set # CONFIG_SENSORS_LM75 is not set diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index aa2c39d968fc..92091de11113 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -134,7 +134,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) boot_cpu_data.x86_model <= 0x05 && boot_cpu_data.x86_mask < 0x0A) return 1; - else if (boot_cpu_has(X86_FEATURE_AMDC1E)) + else if (c1e_detected) return 1; else return max_cstate; diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h index c74a2eebe570..a69b1ac9eaf8 100644 --- a/arch/x86/include/asm/apb_timer.h +++ b/arch/x86/include/asm/apb_timer.h @@ -55,7 +55,6 @@ extern unsigned long apbt_quick_calibrate(void); extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu); extern void apbt_setup_secondary_clock(void); extern unsigned int boot_cpu_id; -extern int disable_apbt_percpu; extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint); extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr); diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 8859e12dd3cf..284a6e8f7ce1 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -11,38 +11,42 @@ extern void __xchg_wrong_size(void); /* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. */ - -struct __xchg_dummy { - unsigned long a[100]; -}; -#define __xg(x) ((struct __xchg_dummy *)(x)) - #define __xchg(x, ptr, size) \ ({ \ __typeof(*(ptr)) __x = (x); \ switch (size) { \ case 1: \ - asm volatile("xchgb %b0,%1" \ - : "=q" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile("xchgb %0,%1" \ + : "=q" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile("xchgw %w0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile("xchgw %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 4: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ asm volatile("xchgl %0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ default: \ __xchg_wrong_size(); \ } \ @@ -53,60 +57,33 @@ struct __xchg_dummy { __xchg((v), (ptr), sizeof(*ptr)) /* - * The semantics of XCHGCMP8B are a bit strange, this is why - * there is a loop and the loading of %%eax and %%edx has to - * be inside. This inlines well in most cases, the cached - * cost is around ~38 cycles. (in the future we might want - * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that - * might have an implicit FPU-save as a cost, so it's not - * clear which path to go.) + * CMPXCHG8B only writes to the target if we had the previous + * value in registers, otherwise it acts as a read and gives us the + * "new previous" value. That is why there is a loop. Preloading + * EDX:EAX is a performance optimization: in the common case it means + * we need only one locked operation. * - * cmpxchg8b must be used with the lock prefix here to allow - * the instruction to be executed atomically, see page 3-102 - * of the instruction set reference 24319102.pdf. We need - * the reader side to see the coherent 64bit value. + * A SIMD/3DNOW!/MMX/FPU 64-bit store here would require at the very + * least an FPU save and/or %cr0.ts manipulation. + * + * cmpxchg8b must be used with the lock prefix here to allow the + * instruction to be executed atomically. We need to have the reader + * side to see the coherent 64bit value. */ -static inline void __set_64bit(unsigned long long *ptr, - unsigned int low, unsigned int high) +static inline void set_64bit(volatile u64 *ptr, u64 value) { + u32 low = value; + u32 high = value >> 32; + u64 prev = *ptr; + asm volatile("\n1:\t" - "movl (%0), %%eax\n\t" - "movl 4(%0), %%edx\n\t" - LOCK_PREFIX "cmpxchg8b (%0)\n\t" + LOCK_PREFIX "cmpxchg8b %0\n\t" "jnz 1b" - : /* no outputs */ - : "D"(ptr), - "b"(low), - "c"(high) - : "ax", "dx", "memory"); -} - -static inline void __set_64bit_constant(unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr, (unsigned int)value, (unsigned int)(value >> 32)); -} - -#define ll_low(x) *(((unsigned int *)&(x)) + 0) -#define ll_high(x) *(((unsigned int *)&(x)) + 1) - -static inline void __set_64bit_var(unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr, ll_low(value), ll_high(value)); + : "=m" (*ptr), "+A" (prev) + : "b" (low), "c" (high) + : "memory"); } -#define set_64bit(ptr, value) \ - (__builtin_constant_p((value)) \ - ? __set_64bit_constant((ptr), (value)) \ - : __set_64bit_var((ptr), (value))) - -#define _set_64bit(ptr, value) \ - (__builtin_constant_p(value) \ - ? __set_64bit(ptr, (unsigned int)(value), \ - (unsigned int)((value) >> 32)) \ - : __set_64bit(ptr, ll_low((value)), ll_high((value)))) - extern void __cmpxchg_wrong_size(void); /* @@ -121,23 +98,32 @@ extern void __cmpxchg_wrong_size(void); __typeof__(*(ptr)) __new = (new); \ switch (size) { \ case 1: \ - asm volatile(lock "cmpxchgb %b1,%2" \ - : "=a"(__ret) \ - : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile(lock "cmpxchgw %w1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile(lock "cmpxchgl %1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ default: \ __cmpxchg_wrong_size(); \ } \ @@ -175,32 +161,28 @@ extern void __cmpxchg_wrong_size(void); (unsigned long long)(n))) #endif -static inline unsigned long long __cmpxchg64(volatile void *ptr, - unsigned long long old, - unsigned long long new) +static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new) { - unsigned long long prev; - asm volatile(LOCK_PREFIX "cmpxchg8b %3" - : "=A"(prev) - : "b"((unsigned long)new), - "c"((unsigned long)(new >> 32)), - "m"(*__xg(ptr)), - "0"(old) + u64 prev; + asm volatile(LOCK_PREFIX "cmpxchg8b %1" + : "=A" (prev), + "+m" (*ptr) + : "b" ((u32)new), + "c" ((u32)(new >> 32)), + "0" (old) : "memory"); return prev; } -static inline unsigned long long __cmpxchg64_local(volatile void *ptr, - unsigned long long old, - unsigned long long new) +static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) { - unsigned long long prev; - asm volatile("cmpxchg8b %3" - : "=A"(prev) - : "b"((unsigned long)new), - "c"((unsigned long)(new >> 32)), - "m"(*__xg(ptr)), - "0"(old) + u64 prev; + asm volatile("cmpxchg8b %1" + : "=A" (prev), + "+m" (*ptr) + : "b" ((u32)new), + "c" ((u32)(new >> 32)), + "0" (old) : "memory"); return prev; } @@ -264,8 +246,6 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old, * to simulate the cmpxchg8b on the 80386 and 80486 CPU. */ -extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64); - #define cmpxchg64(ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ @@ -283,20 +263,20 @@ extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64); __ret; }) - -#define cmpxchg64_local(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - if (likely(boot_cpu_data.x86 > 4)) \ - __ret = (__typeof__(*(ptr)))__cmpxchg64_local((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - else \ - __ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - __ret; \ -}) +#define cmpxchg64_local(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (o); \ + __typeof__(*(ptr)) __new = (n); \ + alternative_io("call cmpxchg8b_emu", \ + "cmpxchg8b (%%esi)" , \ + X86_FEATURE_CX8, \ + "=A" (__ret), \ + "S" ((ptr)), "0" (__old), \ + "b" ((unsigned int)__new), \ + "c" ((unsigned int)(__new>>32)) \ + : "memory"); \ + __ret; }) #endif diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 485ae415faec..423ae58aa020 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -3,51 +3,60 @@ #include <asm/alternative.h> /* Provides LOCK_PREFIX */ -#define __xg(x) ((volatile long *)(x)) - -static inline void set_64bit(volatile unsigned long *ptr, unsigned long val) +static inline void set_64bit(volatile u64 *ptr, u64 val) { *ptr = val; } -#define _set_64bit set_64bit - extern void __xchg_wrong_size(void); extern void __cmpxchg_wrong_size(void); /* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. */ #define __xchg(x, ptr, size) \ ({ \ __typeof(*(ptr)) __x = (x); \ switch (size) { \ case 1: \ - asm volatile("xchgb %b0,%1" \ - : "=q" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile("xchgb %0,%1" \ + : "=q" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile("xchgw %w0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile("xchgw %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile("xchgl %k0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile("xchgl %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 8: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ asm volatile("xchgq %0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ default: \ __xchg_wrong_size(); \ } \ @@ -71,29 +80,41 @@ extern void __cmpxchg_wrong_size(void); __typeof__(*(ptr)) __new = (new); \ switch (size) { \ case 1: \ - asm volatile(lock "cmpxchgb %b1,%2" \ - : "=a"(__ret) \ - : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile(lock "cmpxchgw %w1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile(lock "cmpxchgl %k1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 8: \ - asm volatile(lock "cmpxchgq %1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + asm volatile(lock "cmpxchgq %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ default: \ __cmpxchg_wrong_size(); \ } \ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 468145914389..0b205b8a4308 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -6,7 +6,7 @@ #include <asm/required-features.h> -#define NCAPINTS 9 /* N 32-bit words worth of info */ +#define NCAPINTS 10 /* N 32-bit words worth of info */ /* * Note: If the comment begins with a quoted string, that string is used @@ -89,7 +89,7 @@ #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */ #define X86_FEATURE_11AP (3*32+19) /* "" Bad local APIC aka 11AP */ #define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_AMDC1E (3*32+21) /* AMD C1E detected */ + /* 21 available, was AMD_C1E */ #define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */ @@ -124,6 +124,8 @@ #define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ #define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */ #define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */ +#define X86_FEATURE_F16C (4*32+29) /* 16-bit fp conversions */ +#define X86_FEATURE_RDRND (4*32+30) /* The RDRAND instruction */ #define X86_FEATURE_HYPERVISOR (4*32+31) /* Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ @@ -157,22 +159,29 @@ /* * Auxiliary flags: Linux defined - For features scattered in various - * CPUID levels like 0x6, 0xA etc + * CPUID levels like 0x6, 0xA etc, word 7 */ #define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */ #define X86_FEATURE_ARAT (7*32+ 1) /* Always Running APIC Timer */ #define X86_FEATURE_CPB (7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB (7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ +#define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ -/* Virtualization flags: Linux defined */ +/* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ #define X86_FEATURE_VNMI (8*32+ 1) /* Intel Virtual NMI */ #define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */ #define X86_FEATURE_EPT (8*32+ 3) /* Intel Extended Page Table */ #define X86_FEATURE_VPID (8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_NPT (8*32+5) /* AMD Nested Page Table support */ -#define X86_FEATURE_LBRV (8*32+6) /* AMD LBR Virtualization support */ -#define X86_FEATURE_SVML (8*32+7) /* "svm_lock" AMD SVM locking MSR */ -#define X86_FEATURE_NRIPS (8*32+8) /* "nrip_save" AMD SVM next_rip save */ +#define X86_FEATURE_NPT (8*32+ 5) /* AMD Nested Page Table support */ +#define X86_FEATURE_LBRV (8*32+ 6) /* AMD LBR Virtualization support */ +#define X86_FEATURE_SVML (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ +#define X86_FEATURE_NRIPS (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ +#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) @@ -194,7 +203,9 @@ extern const char * const x86_power_flags[32]; (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) || \ (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) || \ (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) || \ - (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ) \ + (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) || \ + (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \ + (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) ) \ ? 1 : \ test_cpu_cap(c, bit)) diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 942255310e6a..528a11e8d3e3 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -20,10 +20,10 @@ struct arch_hw_breakpoint { #include <linux/list.h> /* Available HW breakpoint length encodings */ +#define X86_BREAKPOINT_LEN_X 0x00 #define X86_BREAKPOINT_LEN_1 0x40 #define X86_BREAKPOINT_LEN_2 0x44 #define X86_BREAKPOINT_LEN_4 0x4c -#define X86_BREAKPOINT_LEN_EXECUTE 0x40 #ifdef CONFIG_X86_64 #define X86_BREAKPOINT_LEN_8 0x48 diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 70abda7058c8..ff2546ce7178 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -45,5 +45,6 @@ extern const struct hypervisor_x86 *x86_hyper; /* Recognized hypervisors */ extern const struct hypervisor_x86 x86_hyper_vmware; extern const struct hypervisor_x86 x86_hyper_ms_hyperv; +extern const struct hypervisor_x86 x86_hyper_xen_hvm; #endif diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 8767d99c4f64..e2ca30092557 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -125,6 +125,9 @@ */ #define MCE_SELF_VECTOR 0xeb +/* Xen vector callback to receive events in a HVM domain */ +#define XEN_HVM_EVTCHN_CALLBACK 0xe9 + #define NR_VECTORS 256 #define FPU_IRQ 13 diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 006da3687cdc..396f5b5fc4d7 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -39,9 +39,11 @@ enum regnames { GDB_FS, /* 14 */ GDB_GS, /* 15 */ }; +#define GDB_ORIG_AX 41 +#define DBG_MAX_REG_NUM 16 #define NUMREGBYTES ((GDB_GS+1)*4) #else /* ! CONFIG_X86_32 */ -enum regnames64 { +enum regnames { GDB_AX, /* 0 */ GDB_BX, /* 1 */ GDB_CX, /* 2 */ @@ -59,15 +61,15 @@ enum regnames64 { GDB_R14, /* 14 */ GDB_R15, /* 15 */ GDB_PC, /* 16 */ + GDB_PS, /* 17 */ + GDB_CS, /* 18 */ + GDB_SS, /* 19 */ }; - -enum regnames32 { - GDB_PS = 34, - GDB_CS, - GDB_SS, -}; -#define NUMREGBYTES ((GDB_SS+1)*4) -#endif /* CONFIG_X86_32 */ +#define GDB_ORIG_AX 57 +#define DBG_MAX_REG_NUM 20 +/* 17 64 bit regs and 3 32 bit regs */ +#define NUMREGBYTES ((17 * 8) + (3 * 4)) +#endif /* ! CONFIG_X86_32 */ static inline void arch_kgdb_breakpoint(void) { diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/x86/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 451d30e7f62d..16350740edf6 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -13,6 +13,32 @@ extern int pci_mrst_init(void); int __init sfi_parse_mrtc(struct sfi_table_header *table); +/* + * Medfield is the follow-up of Moorestown, it combines two chip solution into + * one. Other than that it also added always-on and constant tsc and lapic + * timers. Medfield is the platform name, and the chip name is called Penwell + * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be + * identified via MSRs. + */ +enum mrst_cpu_type { + MRST_CPU_CHIP_LINCROFT = 1, + MRST_CPU_CHIP_PENWELL, +}; + +extern enum mrst_cpu_type __mrst_cpu_chip; +static enum mrst_cpu_type mrst_identify_cpu(void) +{ + return __mrst_cpu_chip; +} + +enum mrst_timer_options { + MRST_TIMER_DEFAULT, + MRST_TIMER_APBT_ONLY, + MRST_TIMER_LAPIC_APBT, +}; + +extern enum mrst_timer_options mrst_timer_options; + #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 509a42187dc2..65bbec2093aa 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -161,8 +161,6 @@ #define MSR_K7_FID_VID_STATUS 0xc0010042 /* K6 MSRs */ -#define MSR_K6_EFER 0xc0000080 -#define MSR_K6_STAR 0xc0000081 #define MSR_K6_WHCR 0xc0000082 #define MSR_K6_UWCCR 0xc0000085 #define MSR_K6_EPMR 0xc0000086 @@ -226,12 +224,14 @@ #define MSR_IA32_THERM_CONTROL 0x0000019a #define MSR_IA32_THERM_INTERRUPT 0x0000019b -#define THERM_INT_LOW_ENABLE (1 << 0) -#define THERM_INT_HIGH_ENABLE (1 << 1) +#define THERM_INT_HIGH_ENABLE (1 << 0) +#define THERM_INT_LOW_ENABLE (1 << 1) +#define THERM_INT_PLN_ENABLE (1 << 24) #define MSR_IA32_THERM_STATUS 0x0000019c #define THERM_STATUS_PROCHOT (1 << 0) +#define THERM_STATUS_POWER_LIMIT (1 << 10) #define MSR_THERM2_CTL 0x0000019d @@ -241,6 +241,19 @@ #define MSR_IA32_TEMPERATURE_TARGET 0x000001a2 +#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 + +#define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1 + +#define PACKAGE_THERM_STATUS_PROCHOT (1 << 0) +#define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10) + +#define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2 + +#define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0) +#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1) +#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24) + /* MISC_ENABLE bits: architectural */ #define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << 0) #define MSR_IA32_MISC_ENABLE_TCC (1ULL << 1) diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index c5bc4c2d33f5..084ef95274cd 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -148,8 +148,8 @@ static inline unsigned long long native_read_pmc(int counter) #define rdmsr(msr, val1, val2) \ do { \ u64 __val = native_read_msr((msr)); \ - (val1) = (u32)__val; \ - (val2) = (u32)(__val >> 32); \ + (void)((val1) = (u32)__val); \ + (void)((val2) = (u32)(__val >> 32)); \ } while (0) static inline void wrmsr(unsigned msr, unsigned low, unsigned high) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 93da9c3f3341..932f0f86b4b7 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -17,7 +17,9 @@ int do_nmi_callback(struct pt_regs *regs, int cpu); extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int check_nmi_watchdog(void); +#if !defined(CONFIG_LOCKUP_DETECTOR) extern int nmi_watchdog_enabled; +#endif extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 254883d0c7e0..6e742cc4251b 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -68,8 +68,9 @@ union cpuid10_eax { union cpuid10_edx { struct { - unsigned int num_counters_fixed:4; - unsigned int reserved:28; + unsigned int num_counters_fixed:5; + unsigned int bit_width_fixed:8; + unsigned int reserved:19; } split; unsigned int full; }; @@ -140,6 +141,19 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) +#include <asm/stacktrace.h> + +/* + * We abuse bit 3 from flags to pass exact information, see perf_misc_flags + * and the comment with PERF_EFLAGS_EXACT. + */ +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->ip = (__ip); \ + (regs)->bp = caller_frame_pointer(); \ + (regs)->cs = __KERNEL_CS; \ + regs->flags = 0; \ +} + #else static inline void init_hw_perf_events(void) { } static inline void perf_events_lapic_init(void) { } diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 64a8ebff06fc..def500776b16 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -19,7 +19,6 @@ #define ARCH_P4_RESERVED_ESCR (2) /* IQ_ESCR(0,1) not always present */ #define ARCH_P4_MAX_ESCR (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR) #define ARCH_P4_MAX_CCCR (18) -#define ARCH_P4_MAX_COUNTER (ARCH_P4_MAX_CCCR / 2) #define P4_ESCR_EVENT_MASK 0x7e000000U #define P4_ESCR_EVENT_SHIFT 25 @@ -71,10 +70,6 @@ #define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) #define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) -/* Custom bits in reerved CCCR area */ -#define P4_CCCR_CACHE_OPS_MASK 0x0000003fU - - /* Non HT mask */ #define P4_CCCR_MASK \ (P4_CCCR_OVF | \ @@ -106,8 +101,7 @@ * ESCR and CCCR but rather an only packed value should * be unpacked and written to a proper addresses * - * the base idea is to pack as much info as - * possible + * the base idea is to pack as much info as possible */ #define p4_config_pack_escr(v) (((u64)(v)) << 32) #define p4_config_pack_cccr(v) (((u64)(v)) & 0xffffffffULL) @@ -130,8 +124,6 @@ t; \ }) -#define p4_config_unpack_cache_event(v) (((u64)(v)) & P4_CCCR_CACHE_OPS_MASK) - #define P4_CONFIG_HT_SHIFT 63 #define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) @@ -214,6 +206,12 @@ static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr) return escr; } +/* + * This are the events which should be used in "Event Select" + * field of ESCR register, they are like unique keys which allow + * the kernel to determinate which CCCR and COUNTER should be + * used to track an event + */ enum P4_EVENTS { P4_EVENT_TC_DELIVER_MODE, P4_EVENT_BPU_FETCH_REQUEST, @@ -561,7 +559,7 @@ enum P4_EVENT_OPCODES { * a caller should use P4_ESCR_EMASK_NAME helper to * pick the EventMask needed, for example * - * P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD) + * P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD) */ enum P4_ESCR_EMASKS { P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0), @@ -753,43 +751,50 @@ enum P4_ESCR_EMASKS { P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1), }; -/* P4 PEBS: stale for a while */ -#define P4_PEBS_METRIC_MASK 0x00001fffU -#define P4_PEBS_UOB_TAG 0x01000000U -#define P4_PEBS_ENABLE 0x02000000U - -/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */ -#define P4_PEBS__1stl_cache_load_miss_retired 0x3000001 -#define P4_PEBS__2ndl_cache_load_miss_retired 0x3000002 -#define P4_PEBS__dtlb_load_miss_retired 0x3000004 -#define P4_PEBS__dtlb_store_miss_retired 0x3000004 -#define P4_PEBS__dtlb_all_miss_retired 0x3000004 -#define P4_PEBS__tagged_mispred_branch 0x3018000 -#define P4_PEBS__mob_load_replay_retired 0x3000200 -#define P4_PEBS__split_load_retired 0x3000400 -#define P4_PEBS__split_store_retired 0x3000400 - -#define P4_VERT__1stl_cache_load_miss_retired 0x0000001 -#define P4_VERT__2ndl_cache_load_miss_retired 0x0000001 -#define P4_VERT__dtlb_load_miss_retired 0x0000001 -#define P4_VERT__dtlb_store_miss_retired 0x0000002 -#define P4_VERT__dtlb_all_miss_retired 0x0000003 -#define P4_VERT__tagged_mispred_branch 0x0000010 -#define P4_VERT__mob_load_replay_retired 0x0000001 -#define P4_VERT__split_load_retired 0x0000001 -#define P4_VERT__split_store_retired 0x0000002 - -enum P4_CACHE_EVENTS { - P4_CACHE__NONE, - - P4_CACHE__1stl_cache_load_miss_retired, - P4_CACHE__2ndl_cache_load_miss_retired, - P4_CACHE__dtlb_load_miss_retired, - P4_CACHE__dtlb_store_miss_retired, - P4_CACHE__itlb_reference_hit, - P4_CACHE__itlb_reference_miss, - - P4_CACHE__MAX +/* + * P4 PEBS specifics (Replay Event only) + * + * Format (bits): + * 0-6: metric from P4_PEBS_METRIC enum + * 7 : reserved + * 8 : reserved + * 9-11 : reserved + * + * Note we have UOP and PEBS bits reserved for now + * just in case if we will need them once + */ +#define P4_PEBS_CONFIG_ENABLE (1 << 7) +#define P4_PEBS_CONFIG_UOP_TAG (1 << 8) +#define P4_PEBS_CONFIG_METRIC_MASK 0x3f +#define P4_PEBS_CONFIG_MASK 0xff + +/* + * mem: Only counters MSR_IQ_COUNTER4 (16) and + * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling + */ +#define P4_PEBS_ENABLE 0x02000000U +#define P4_PEBS_ENABLE_UOP_TAG 0x01000000U + +#define p4_config_unpack_metric(v) (((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK) +#define p4_config_unpack_pebs(v) (((u64)(v)) & P4_PEBS_CONFIG_MASK) + +#define p4_config_pebs_has(v, mask) (p4_config_unpack_pebs(v) & (mask)) + +enum P4_PEBS_METRIC { + P4_PEBS_METRIC__none, + + P4_PEBS_METRIC__1stl_cache_load_miss_retired, + P4_PEBS_METRIC__2ndl_cache_load_miss_retired, + P4_PEBS_METRIC__dtlb_load_miss_retired, + P4_PEBS_METRIC__dtlb_store_miss_retired, + P4_PEBS_METRIC__dtlb_all_miss_retired, + P4_PEBS_METRIC__tagged_mispred_branch, + P4_PEBS_METRIC__mob_load_replay_retired, + P4_PEBS_METRIC__split_load_retired, + P4_PEBS_METRIC__split_store_retired, + + P4_PEBS_METRIC__max }; #endif /* PERF_EVENT_P4_H */ + diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7e5c6a60b8ee..325b7bdbebaa 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -762,6 +762,7 @@ extern void init_c1e_mask(void); extern unsigned long boot_option_idle_override; extern unsigned long idle_halt; extern unsigned long idle_nomwait; +extern bool c1e_detected; /* * on systems with caches, caches must be flashed as the absolute @@ -1025,4 +1026,24 @@ unsigned long calc_aperfmperf_ratio(struct aperfmperf *old, return ratio; } +/* + * AMD errata checking + */ +#ifdef CONFIG_CPU_SUP_AMD +extern const int amd_erratum_383[]; +extern const int amd_erratum_400[]; +extern bool cpu_has_amd_erratum(const int *); + +#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } +#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } +#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ + ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) +#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) +#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) +#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) + +#else +#define cpu_has_amd_erratum(x) (false) +#endif /* CONFIG_CPU_SUP_AMD */ + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 64cf2d24fad1..6c7fc25f2c34 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -84,5 +84,7 @@ #define REQUIRED_MASK5 0 #define REQUIRED_MASK6 0 #define REQUIRED_MASK7 0 +#define REQUIRED_MASK8 0 +#define REQUIRED_MASK9 0 #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index 606ede126972..d1e41b0f9b60 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -118,7 +118,7 @@ static inline void __down_read(struct rw_semaphore *sem) { asm volatile("# beginning down_read\n\t" LOCK_PREFIX _ASM_INC "(%1)\n\t" - /* adds 0x00000001, returns the old value */ + /* adds 0x00000001 */ " jns 1f\n" " call call_rwsem_down_read_failed\n" "1:\n\t" @@ -156,11 +156,9 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) { rwsem_count_t tmp; - - tmp = RWSEM_ACTIVE_WRITE_BIAS; asm volatile("# beginning down_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" - /* subtract 0x0000ffff, returns the old value */ + /* adds 0xffff0001, returns the old value */ " test %1,%1\n\t" /* was the count 0 before? */ " jz 1f\n" @@ -168,7 +166,7 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) "1:\n" "# ending down_write" : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (tmp) + : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) : "memory", "cc"); } @@ -195,16 +193,16 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) */ static inline void __up_read(struct rw_semaphore *sem) { - rwsem_count_t tmp = -RWSEM_ACTIVE_READ_BIAS; + rwsem_count_t tmp; asm volatile("# beginning __up_read\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* subtracts 1, returns the old value */ " jns 1f\n\t" - " call call_rwsem_wake\n" + " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n" "# ending __up_read\n" : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (tmp) + : "a" (sem), "1" (-RWSEM_ACTIVE_READ_BIAS) : "memory", "cc"); } @@ -216,10 +214,9 @@ static inline void __up_write(struct rw_semaphore *sem) rwsem_count_t tmp; asm volatile("# beginning __up_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" - /* tries to transition - 0xffff0001 -> 0x00000000 */ - " jz 1f\n" - " call call_rwsem_wake\n" + /* subtracts 0xffff0001, returns the old value */ + " jns 1f\n\t" + " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n\t" "# ending __up_write\n" : "+m" (sem->count), "=d" (tmp) diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 86b1506f4179..ef292c792d74 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -82,7 +82,7 @@ void *extend_brk(size_t size, size_t align); * executable.) */ #define RESERVE_BRK(name,sz) \ - static void __section(.discard) __used \ + static void __section(.discard.text) __used \ __brk_reservation_fn_##name##__(void) { \ asm volatile ( \ ".pushsection .brk_reservation,\"aw\",@nobits;" \ diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 4dab78edbad9..2b16a2ad23dc 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -1,6 +1,13 @@ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + */ + #ifndef _ASM_X86_STACKTRACE_H #define _ASM_X86_STACKTRACE_H +#include <linux/uaccess.h> + extern int kstack_depth_to_print; struct thread_info; @@ -42,4 +49,46 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data); +#ifdef CONFIG_X86_32 +#define STACKSLOTS_PER_LINE 8 +#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) +#else +#define STACKSLOTS_PER_LINE 4 +#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) +#endif + +extern void +show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, char *log_lvl); + +extern void +show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, unsigned long bp, char *log_lvl); + +extern unsigned int code_bytes; + +/* The form of the top of the frame on the stack */ +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +struct stack_frame_ia32 { + u32 next_frame; + u32 return_address; +}; + +static inline unsigned long caller_frame_pointer(void) +{ + struct stack_frame *frame; + + get_bp(frame); + +#ifdef CONFIG_FRAME_POINTER + frame = frame->next_frame; +#endif + + return (unsigned long)frame; +} + #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 9c371e4a9fa6..7fda040a76cd 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -417,6 +417,12 @@ HYPERVISOR_nmi_op(unsigned long op, unsigned long arg) return _hypercall2(int, nmi_op, op, arg); } +static inline unsigned long __must_check +HYPERVISOR_hvm_op(int op, void *arg) +{ + return _hypercall2(unsigned long, hvm_op, op, arg); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S index 580b4e296010..28595d6df47c 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.S +++ b/arch/x86/kernel/acpi/realmode/wakeup.S @@ -104,7 +104,7 @@ _start: movl %eax, %ecx orl %edx, %ecx jz 1f - movl $0xc0000080, %ecx + movl $MSR_EFER, %ecx wrmsr 1: diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 0d20286d78c6..fa044e1e30a2 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -2572,6 +2572,11 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, static int amd_iommu_domain_has_cap(struct iommu_domain *domain, unsigned long cap) { + switch (cap) { + case IOMMU_CAP_CACHE_COHERENCY: + return 1; + } + return 0; } @@ -2609,8 +2614,7 @@ int __init amd_iommu_init_passthrough(void) pt_domain->mode |= PAGE_MODE_NONE; - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - + for_each_pci_dev(dev) { if (!check_device(&dev->dev)) continue; diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index a35347501d36..8dd77800ff5d 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -43,10 +43,11 @@ #include <asm/fixmap.h> #include <asm/apb_timer.h> +#include <asm/mrst.h> #define APBT_MASK CLOCKSOURCE_MASK(32) #define APBT_SHIFT 22 -#define APBT_CLOCKEVENT_RATING 150 +#define APBT_CLOCKEVENT_RATING 110 #define APBT_CLOCKSOURCE_RATING 250 #define APBT_MIN_DELTA_USEC 200 @@ -83,8 +84,6 @@ struct apbt_dev { char name[10]; }; -int disable_apbt_percpu __cpuinitdata; - static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev); #ifdef CONFIG_SMP @@ -195,29 +194,6 @@ static struct clock_event_device apbt_clockevent = { }; /* - * if user does not want to use per CPU apb timer, just give it a lower rating - * than local apic timer and skip the late per cpu timer init. - */ -static inline int __init setup_x86_mrst_timer(char *arg) -{ - if (!arg) - return -EINVAL; - - if (strcmp("apbt_only", arg) == 0) - disable_apbt_percpu = 0; - else if (strcmp("lapic_and_apbt", arg) == 0) - disable_apbt_percpu = 1; - else { - pr_warning("X86 MRST timer option %s not recognised" - " use x86_mrst_timer=apbt_only or lapic_and_apbt\n", - arg); - return -EINVAL; - } - return 0; -} -__setup("x86_mrst_timer=", setup_x86_mrst_timer); - -/* * start count down from 0xffff_ffff. this is done by toggling the enable bit * then load initial load count to ~0. */ @@ -335,7 +311,7 @@ static int __init apbt_clockevent_register(void) adev->num = smp_processor_id(); memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device)); - if (disable_apbt_percpu) { + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100; global_clock_event = &adev->evt; printk(KERN_DEBUG "%s clockevent registered as global\n", @@ -429,7 +405,8 @@ static int apbt_cpuhp_notify(struct notifier_block *n, static __init int apbt_late_init(void) { - if (disable_apbt_percpu || !apb_timer_block_enabled) + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT || + !apb_timer_block_enabled) return 0; /* This notifier should be called after workqueue is ready */ hotcpu_notifier(apbt_cpuhp_notify, -20); @@ -450,6 +427,8 @@ static void apbt_set_mode(enum clock_event_mode mode, int timer_num; struct apbt_dev *adev = EVT_TO_APBT_DEV(evt); + BUG_ON(!apbt_virt_address); + timer_num = adev->num; pr_debug("%s CPU %d timer %d mode=%d\n", __func__, first_cpu(*evt->cpumask), timer_num, mode); @@ -676,7 +655,7 @@ void __init apbt_time_init(void) } #ifdef CONFIG_SMP /* kernel cmdline disable apb timer, so we will use lapic timers */ - if (disable_apbt_percpu) { + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { printk(KERN_INFO "apbt: disabled per cpu timer\n"); return; } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index b5d8b0bcf235..a2e0caf26e17 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -280,7 +280,7 @@ void __init early_gart_iommu_check(void) * or BIOS forget to put that in reserved. * try to update e820 to make that region as reserved. */ - u32 agp_aper_base = 0, agp_aper_order = 0; + u32 agp_aper_order = 0; int i, fix, slot, valid_agp = 0; u32 ctl; u32 aper_size = 0, aper_order = 0, last_aper_order = 0; @@ -291,7 +291,7 @@ void __init early_gart_iommu_check(void) return; /* This is mostly duplicate of iommu_hole_init */ - agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp); + search_agp_bridge(&agp_aper_order, &valid_agp); fix = 0; for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 565c1bfc507d..910f20b457c4 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -2,7 +2,12 @@ # Makefile for local APIC drivers and for the IO-APIC code # -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o nmi.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o +ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y) +obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o +endif +obj-$(CONFIG_HARDLOCKUP_DETECTOR) += hw_nmi.o + obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_SMP) += ipi.o diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c new file mode 100644 index 000000000000..cefd6942f0e9 --- /dev/null +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -0,0 +1,107 @@ +/* + * HW NMI watchdog support + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * Arch specific calls to support NMI watchdog + * + * Bits copied from original nmi.c file + * + */ +#include <asm/apic.h> + +#include <linux/cpumask.h> +#include <linux/kdebug.h> +#include <linux/notifier.h> +#include <linux/kprobes.h> +#include <linux/nmi.h> +#include <linux/module.h> + +/* For reliability, we're prepared to waste bits here. */ +static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; + +u64 hw_nmi_get_sample_period(void) +{ + return (u64)(cpu_khz) * 1000 * 60; +} + +#ifdef ARCH_HAS_NMI_WATCHDOG +void arch_trigger_all_cpu_backtrace(void) +{ + int i; + + cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); + + printk(KERN_INFO "sending NMI to all CPUs:\n"); + apic->send_IPI_all(NMI_VECTOR); + + /* Wait for up to 10 seconds for all CPUs to do the backtrace */ + for (i = 0; i < 10 * 1000; i++) { + if (cpumask_empty(to_cpumask(backtrace_mask))) + break; + mdelay(1); + } +} + +static int __kprobes +arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, + unsigned long cmd, void *__args) +{ + struct die_args *args = __args; + struct pt_regs *regs; + int cpu = smp_processor_id(); + + switch (cmd) { + case DIE_NMI: + case DIE_NMI_IPI: + break; + + default: + return NOTIFY_DONE; + } + + regs = args->regs; + + if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { + static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; + + arch_spin_lock(&lock); + printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); + show_regs(regs); + dump_stack(); + arch_spin_unlock(&lock); + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); + return NOTIFY_STOP; + } + + return NOTIFY_DONE; +} + +static __read_mostly struct notifier_block backtrace_notifier = { + .notifier_call = arch_trigger_all_cpu_backtrace_handler, + .next = NULL, + .priority = 1 +}; + +static int __init register_trigger_all_cpu_backtrace(void) +{ + register_die_notifier(&backtrace_notifier); + return 0; +} +early_initcall(register_trigger_all_cpu_backtrace); +#endif + +/* STUB calls to mimic old nmi_watchdog behaviour */ +#if defined(CONFIG_X86_LOCAL_APIC) +unsigned int nmi_watchdog = NMI_NONE; +EXPORT_SYMBOL(nmi_watchdog); +void acpi_nmi_enable(void) { return; } +void acpi_nmi_disable(void) { return; } +#endif +atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ +EXPORT_SYMBOL(nmi_active); +int unknown_nmi_panic; +void cpu_nmi_set_wd_enabled(void) { return; } +void stop_apic_nmi_watchdog(void *unused) { return; } +void setup_apic_nmi_watchdog(void *unused) { return; } +int __init check_nmi_watchdog(void) { return 0; } diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index 1edaf15c0b8e..a43f71cb30f8 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -401,13 +401,6 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) int cpu = smp_processor_id(); int rc = 0; - /* check for other users first */ - if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) - == NOTIFY_STOP) { - rc = 1; - touched = 1; - } - sum = get_timer_irqs(cpu); if (__get_cpu_var(nmi_touch)) { diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 3a785da34b6f..3f0ebe429a01 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -12,11 +12,11 @@ endif nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_common.o := $(nostackp) -obj-y := intel_cacheinfo.o addon_cpuid_features.o +obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o obj-y += vmware.o hypervisor.o sched.o mshyperv.o -obj-$(CONFIG_X86_32) += bugs.o cmpxchg.o +obj-$(CONFIG_X86_32) += bugs.o obj-$(CONFIG_X86_64) += bugs_64.o obj-$(CONFIG_CPU_SUP_INTEL) += intel.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e485825130d2..60a57b13082d 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -466,7 +466,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } } - if (c->x86 == 0x10 || c->x86 == 0x11) + if (c->x86 >= 0x10) set_cpu_cap(c, X86_FEATURE_REP_GOOD); /* get apicid instead of initial apic id from cpuid */ @@ -529,7 +529,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) num_cache_leaves = 3; } - if (c->x86 >= 0xf && c->x86 <= 0x11) + if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has_xmm2) { @@ -546,7 +546,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) fam10h_check_enable_mmcfg(); } - if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) { + if (c == &boot_cpu_data && c->x86 >= 0xf) { unsigned long long tseg; /* @@ -609,3 +609,74 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = { }; cpu_dev_register(amd_cpu_dev); + +/* + * AMD errata checking + * + * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or + * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that + * have an OSVW id assigned, which it takes as first argument. Both take a + * variable number of family-specific model-stepping ranges created by + * AMD_MODEL_RANGE(). Each erratum also has to be declared as extern const + * int[] in arch/x86/include/asm/processor.h. + * + * Example: + * + * const int amd_erratum_319[] = + * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2), + * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0), + * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); + */ + +const int amd_erratum_400[] = + AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), + AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); +EXPORT_SYMBOL_GPL(amd_erratum_400); + +const int amd_erratum_383[] = + AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); +EXPORT_SYMBOL_GPL(amd_erratum_383); + +bool cpu_has_amd_erratum(const int *erratum) +{ + struct cpuinfo_x86 *cpu = ¤t_cpu_data; + int osvw_id = *erratum++; + u32 range; + u32 ms; + + /* + * If called early enough that current_cpu_data hasn't been initialized + * yet, fall back to boot_cpu_data. + */ + if (cpu->x86 == 0) + cpu = &boot_cpu_data; + + if (cpu->x86_vendor != X86_VENDOR_AMD) + return false; + + if (osvw_id >= 0 && osvw_id < 65536 && + cpu_has(cpu, X86_FEATURE_OSVW)) { + u64 osvw_len; + + rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len); + if (osvw_id < osvw_len) { + u64 osvw_bits; + + rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6), + osvw_bits); + return osvw_bits & (1ULL << (osvw_id & 0x3f)); + } + } + + /* OSVW unavailable or ID unknown, match family-model-stepping range */ + ms = (cpu->x86_model << 8) | cpu->x86_mask; + while ((range = *erratum++)) + if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && + (ms >= AMD_MODEL_RANGE_START(range)) && + (ms <= AMD_MODEL_RANGE_END(range))) + return true; + + return false; +} + +EXPORT_SYMBOL_GPL(cpu_has_amd_erratum); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 68e4a6f2211e..f10273138382 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -551,6 +551,16 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[4] = excap; } + /* Additional Intel-defined flags: level 0x00000007 */ + if (c->cpuid_level >= 0x00000007) { + u32 eax, ebx, ecx, edx; + + cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); + + if (eax > 0) + c->x86_capability[9] = ebx; + } + /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); c->extended_cpuid_level = xlvl; @@ -576,6 +586,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + init_scattered_cpuid_features(c); } static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -731,7 +742,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ - init_scattered_cpuid_features(c); detect_nopl(c); } diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index dd531cc56a8f..8095f8611f8a 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -34,6 +34,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = { &x86_hyper_vmware, &x86_hyper_ms_hyperv, +#ifdef CONFIG_XEN_PVHVM + &x86_hyper_xen_hvm, +#endif }; const struct hypervisor_x86 *x86_hyper; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 33eae2062cf5..898c2f4eab88 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -347,8 +347,8 @@ static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node) return l3; } -static void __cpuinit -amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) +static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, + int index) { int node; @@ -396,20 +396,39 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) this_leaf->l3 = l3_caches[node]; } +/* + * check whether a slot used for disabling an L3 index is occupied. + * @l3: L3 cache descriptor + * @slot: slot number (0..1) + * + * @returns: the disabled index if used or negative value if slot free. + */ +int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot) +{ + unsigned int reg = 0; + + pci_read_config_dword(l3->dev, 0x1BC + slot * 4, ®); + + /* check whether this slot is activated already */ + if (reg & (3UL << 30)) + return reg & 0xfff; + + return -1; +} + static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, unsigned int slot) { - struct pci_dev *dev = this_leaf->l3->dev; - unsigned int reg = 0; + int index; if (!this_leaf->l3 || !this_leaf->l3->can_disable) return -EINVAL; - if (!dev) - return -EINVAL; + index = amd_get_l3_disable_slot(this_leaf->l3, slot); + if (index >= 0) + return sprintf(buf, "%d\n", index); - pci_read_config_dword(dev, 0x1BC + slot * 4, ®); - return sprintf(buf, "0x%08x\n", reg); + return sprintf(buf, "FREE\n"); } #define SHOW_CACHE_DISABLE(slot) \ @@ -451,37 +470,74 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu, } } - -static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, - const char *buf, size_t count, - unsigned int slot) +/* + * disable a L3 cache index by using a disable-slot + * + * @l3: L3 cache descriptor + * @cpu: A CPU on the node containing the L3 cache + * @slot: slot number (0..1) + * @index: index to disable + * + * @return: 0 on success, error status on failure + */ +int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot, + unsigned long index) { - struct pci_dev *dev = this_leaf->l3->dev; - int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - unsigned long val = 0; + int ret = 0; #define SUBCACHE_MASK (3UL << 20) #define SUBCACHE_INDEX 0xfff - if (!this_leaf->l3 || !this_leaf->l3->can_disable) + /* + * check whether this slot is already used or + * the index is already disabled + */ + ret = amd_get_l3_disable_slot(l3, slot); + if (ret >= 0) return -EINVAL; + /* + * check whether the other slot has disabled the + * same index already + */ + if (index == amd_get_l3_disable_slot(l3, !slot)) + return -EINVAL; + + /* do not allow writes outside of allowed bits */ + if ((index & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) || + ((index & SUBCACHE_INDEX) > l3->indices)) + return -EINVAL; + + amd_l3_disable_index(l3, cpu, slot, index); + + return 0; +} + +static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, + const char *buf, size_t count, + unsigned int slot) +{ + unsigned long val = 0; + int cpu, err = 0; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!dev) + if (!this_leaf->l3 || !this_leaf->l3->can_disable) return -EINVAL; - if (strict_strtoul(buf, 10, &val) < 0) - return -EINVAL; + cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - /* do not allow writes outside of allowed bits */ - if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) || - ((val & SUBCACHE_INDEX) > this_leaf->l3->indices)) + if (strict_strtoul(buf, 10, &val) < 0) return -EINVAL; - amd_l3_disable_index(this_leaf->l3, cpu, slot, val); - + err = amd_set_l3_disable_slot(this_leaf->l3, cpu, slot, val); + if (err) { + if (err == -EEXIST) + printk(KERN_WARNING "L3 disable slot %d in use!\n", + slot); + return err; + } return count; } @@ -502,7 +558,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, #else /* CONFIG_CPU_SUP_AMD */ static void __cpuinit -amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) +amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index) { }; #endif /* CONFIG_CPU_SUP_AMD */ @@ -518,7 +574,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index, if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { amd_cpuid4(index, &eax, &ebx, &ecx); - amd_check_l3_disable(index, this_leaf); + amd_check_l3_disable(this_leaf, index); } else { cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 1970ef911c99..e1269d62c569 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -51,7 +51,7 @@ static DEFINE_MUTEX(mce_read_mutex); #define rcu_dereference_check_mce(p) \ - rcu_dereference_check((p), \ + rcu_dereference_index_check((p), \ rcu_read_lock_sched_held() || \ lockdep_is_held(&mce_read_mutex)) diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index e1a0a3bf9716..c2a8b26d4fea 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -34,15 +34,25 @@ /* How long to wait between reporting thermal events */ #define CHECK_INTERVAL (300 * HZ) +#define THERMAL_THROTTLING_EVENT 0 +#define POWER_LIMIT_EVENT 1 + /* - * Current thermal throttling state: + * Current thermal event state: */ -struct thermal_state { - bool is_throttled; - +struct _thermal_state { + bool new_event; + int event; u64 next_check; - unsigned long throttle_count; - unsigned long last_throttle_count; + unsigned long count; + unsigned long last_count; +}; + +struct thermal_state { + struct _thermal_state core_throttle; + struct _thermal_state core_power_limit; + struct _thermal_state package_throttle; + struct _thermal_state package_power_limit; }; static DEFINE_PER_CPU(struct thermal_state, thermal_state); @@ -53,11 +63,13 @@ static u32 lvtthmr_init __read_mostly; #ifdef CONFIG_SYSFS #define define_therm_throt_sysdev_one_ro(_name) \ - static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL) + static SYSDEV_ATTR(_name, 0444, \ + therm_throt_sysdev_show_##_name, \ + NULL) \ -#define define_therm_throt_sysdev_show_func(name) \ +#define define_therm_throt_sysdev_show_func(event, name) \ \ -static ssize_t therm_throt_sysdev_show_##name( \ +static ssize_t therm_throt_sysdev_show_##event##_##name( \ struct sys_device *dev, \ struct sysdev_attribute *attr, \ char *buf) \ @@ -66,30 +78,42 @@ static ssize_t therm_throt_sysdev_show_##name( \ ssize_t ret; \ \ preempt_disable(); /* CPU hotplug */ \ - if (cpu_online(cpu)) \ + if (cpu_online(cpu)) { \ ret = sprintf(buf, "%lu\n", \ - per_cpu(thermal_state, cpu).name); \ - else \ + per_cpu(thermal_state, cpu).event.name); \ + } else \ ret = 0; \ preempt_enable(); \ \ return ret; \ } -define_therm_throt_sysdev_show_func(throttle_count); -define_therm_throt_sysdev_one_ro(throttle_count); +define_therm_throt_sysdev_show_func(core_throttle, count); +define_therm_throt_sysdev_one_ro(core_throttle_count); + +define_therm_throt_sysdev_show_func(core_power_limit, count); +define_therm_throt_sysdev_one_ro(core_power_limit_count); + +define_therm_throt_sysdev_show_func(package_throttle, count); +define_therm_throt_sysdev_one_ro(package_throttle_count); + +define_therm_throt_sysdev_show_func(package_power_limit, count); +define_therm_throt_sysdev_one_ro(package_power_limit_count); static struct attribute *thermal_throttle_attrs[] = { - &attr_throttle_count.attr, + &attr_core_throttle_count.attr, NULL }; -static struct attribute_group thermal_throttle_attr_group = { +static struct attribute_group thermal_attr_group = { .attrs = thermal_throttle_attrs, .name = "thermal_throttle" }; #endif /* CONFIG_SYSFS */ +#define CORE_LEVEL 0 +#define PACKAGE_LEVEL 1 + /*** * therm_throt_process - Process thermal throttling event from interrupt * @curr: Whether the condition is current or not (boolean), since the @@ -106,39 +130,70 @@ static struct attribute_group thermal_throttle_attr_group = { * 1 : Event should be logged further, and a message has been * printed to the syslog. */ -static int therm_throt_process(bool is_throttled) +static int therm_throt_process(bool new_event, int event, int level) { - struct thermal_state *state; - unsigned int this_cpu; - bool was_throttled; + struct _thermal_state *state; + unsigned int this_cpu = smp_processor_id(); + bool old_event; u64 now; + struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); - this_cpu = smp_processor_id(); now = get_jiffies_64(); - state = &per_cpu(thermal_state, this_cpu); + if (level == CORE_LEVEL) { + if (event == THERMAL_THROTTLING_EVENT) + state = &pstate->core_throttle; + else if (event == POWER_LIMIT_EVENT) + state = &pstate->core_power_limit; + else + return 0; + } else if (level == PACKAGE_LEVEL) { + if (event == THERMAL_THROTTLING_EVENT) + state = &pstate->package_throttle; + else if (event == POWER_LIMIT_EVENT) + state = &pstate->package_power_limit; + else + return 0; + } else + return 0; - was_throttled = state->is_throttled; - state->is_throttled = is_throttled; + old_event = state->new_event; + state->new_event = new_event; - if (is_throttled) - state->throttle_count++; + if (new_event) + state->count++; if (time_before64(now, state->next_check) && - state->throttle_count != state->last_throttle_count) + state->count != state->last_count) return 0; state->next_check = now + CHECK_INTERVAL; - state->last_throttle_count = state->throttle_count; + state->last_count = state->count; /* if we just entered the thermal event */ - if (is_throttled) { - printk(KERN_CRIT "CPU%d: Temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, state->throttle_count); + if (new_event) { + if (event == THERMAL_THROTTLING_EVENT) + printk(KERN_CRIT "CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package", + state->count); + else + printk(KERN_CRIT "CPU%d: %s power limit notification (total events = %lu)\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package", + state->count); add_taint(TAINT_MACHINE_CHECK); return 1; } - if (was_throttled) { - printk(KERN_INFO "CPU%d: Temperature/speed normal\n", this_cpu); + if (old_event) { + if (event == THERMAL_THROTTLING_EVENT) + printk(KERN_INFO "CPU%d: %s temperature/speed normal\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package"); + else + printk(KERN_INFO "CPU%d: %s power limit normal\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package"); return 1; } @@ -149,13 +204,32 @@ static int therm_throt_process(bool is_throttled) /* Add/Remove thermal_throttle interface for CPU device: */ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev) { - return sysfs_create_group(&sys_dev->kobj, - &thermal_throttle_attr_group); + int err; + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + + err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group); + if (err) + return err; + + if (cpu_has(c, X86_FEATURE_PLN)) + err = sysfs_add_file_to_group(&sys_dev->kobj, + &attr_core_power_limit_count.attr, + thermal_attr_group.name); + if (cpu_has(c, X86_FEATURE_PTS)) + err = sysfs_add_file_to_group(&sys_dev->kobj, + &attr_package_throttle_count.attr, + thermal_attr_group.name); + if (cpu_has(c, X86_FEATURE_PLN)) + err = sysfs_add_file_to_group(&sys_dev->kobj, + &attr_package_power_limit_count.attr, + thermal_attr_group.name); + + return err; } static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev) { - sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group); + sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group); } /* Mutex protecting device creation against CPU hotplug: */ @@ -226,14 +300,50 @@ device_initcall(thermal_throttle_init_device); #endif /* CONFIG_SYSFS */ +/* + * Set up the most two significant bit to notify mce log that this thermal + * event type. + * This is a temp solution. May be changed in the future with mce log + * infrasture. + */ +#define CORE_THROTTLED (0) +#define CORE_POWER_LIMIT ((__u64)1 << 62) +#define PACKAGE_THROTTLED ((__u64)2 << 62) +#define PACKAGE_POWER_LIMIT ((__u64)3 << 62) + /* Thermal transition interrupt handler */ static void intel_thermal_interrupt(void) { __u64 msr_val; + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); rdmsrl(MSR_IA32_THERM_STATUS, msr_val); - if (therm_throt_process((msr_val & THERM_STATUS_PROCHOT) != 0)) - mce_log_therm_throt_event(msr_val); + + if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + CORE_LEVEL) != 0) + mce_log_therm_throt_event(CORE_THROTTLED | msr_val); + + if (cpu_has(c, X86_FEATURE_PLN)) + if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, + POWER_LIMIT_EVENT, + CORE_LEVEL) != 0) + mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val); + + if (cpu_has(c, X86_FEATURE_PTS)) { + rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); + if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + PACKAGE_LEVEL) != 0) + mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val); + if (cpu_has(c, X86_FEATURE_PLN)) + if (therm_throt_process(msr_val & + PACKAGE_THERM_STATUS_POWER_LIMIT, + POWER_LIMIT_EVENT, + PACKAGE_LEVEL) != 0) + mce_log_therm_throt_event(PACKAGE_POWER_LIMIT + | msr_val); + } } static void unexpected_thermal_interrupt(void) @@ -335,8 +445,26 @@ void intel_init_thermal(struct cpuinfo_x86 *c) apic_write(APIC_LVTTHMR, h); rdmsr(MSR_IA32_THERM_INTERRUPT, l, h); - wrmsr(MSR_IA32_THERM_INTERRUPT, - l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h); + if (cpu_has(c, X86_FEATURE_PLN)) + wrmsr(MSR_IA32_THERM_INTERRUPT, + l | (THERM_INT_LOW_ENABLE + | THERM_INT_HIGH_ENABLE | THERM_INT_PLN_ENABLE), h); + else + wrmsr(MSR_IA32_THERM_INTERRUPT, + l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h); + + if (cpu_has(c, X86_FEATURE_PTS)) { + rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); + if (cpu_has(c, X86_FEATURE_PLN)) + wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, + l | (PACKAGE_THERM_INT_LOW_ENABLE + | PACKAGE_THERM_INT_HIGH_ENABLE + | PACKAGE_THERM_INT_PLN_ENABLE), h); + else + wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, + l | (PACKAGE_THERM_INT_LOW_ENABLE + | PACKAGE_THERM_INT_HIGH_ENABLE), h); + } smp_thermal_vector = intel_thermal_interrupt; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fd31a441c61c..7d28d7d03885 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -433,13 +433,12 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, { unsigned int mask_lo, mask_hi, base_lo, base_hi; unsigned int tmp, hi; - int cpu; /* * get_mtrr doesn't need to update mtrr_state, also it could be called * from any cpu, so try to print it out directly. */ - cpu = get_cpu(); + get_cpu(); rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5db5b7d65a18..f2da20fda02d 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -220,6 +220,7 @@ struct x86_pmu { struct perf_event *event); struct event_constraint *event_constraints; void (*quirks)(void); + int perfctr_second_write; int (*cpu_prepare)(int cpu); void (*cpu_starting)(int cpu); @@ -295,10 +296,10 @@ x86_perf_event_update(struct perf_event *event) * count to the generic event atomically: */ again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); rdmsrl(hwc->event_base + idx, new_raw_count); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; @@ -313,8 +314,8 @@ again: delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &hwc->period_left); + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); return new_raw_count; } @@ -438,7 +439,7 @@ static int x86_setup_perfctr(struct perf_event *event) if (!hwc->sample_period) { hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; - atomic64_set(&hwc->period_left, hwc->sample_period); + local64_set(&hwc->period_left, hwc->sample_period); } else { /* * If we have a PMU initialized but no APIC @@ -885,7 +886,7 @@ static int x86_perf_event_set_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - s64 left = atomic64_read(&hwc->period_left); + s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0, idx = hwc->idx; @@ -897,14 +898,14 @@ x86_perf_event_set_period(struct perf_event *event) */ if (unlikely(left <= -period)) { left = period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } @@ -923,10 +924,19 @@ x86_perf_event_set_period(struct perf_event *event) * The hw event starts counting from this event offset, * mark it to be able to extra future deltas: */ - atomic64_set(&hwc->prev_count, (u64)-left); + local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base + idx, + wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask); + + /* + * Due to erratum on certan cpu we need + * a second write to be sure the register + * is updated properly + */ + if (x86_pmu.perfctr_second_write) { + wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask); + } perf_event_update_userpage(event); @@ -969,7 +979,7 @@ static int x86_pmu_enable(struct perf_event *event) * skip the schedulability test here, it will be peformed * at commit time(->commit_txn) as a whole */ - if (cpuc->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuc->group_flag & PERF_EVENT_TXN) goto out; ret = x86_pmu.schedule_events(cpuc, n, assign); @@ -1096,7 +1106,7 @@ static void x86_pmu_disable(struct perf_event *event) * The events never got scheduled and ->cancel_txn will truncate * the event_list. */ - if (cpuc->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuc->group_flag & PERF_EVENT_TXN) return; x86_pmu_stop(event); @@ -1388,7 +1398,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - cpuc->group_flag |= PERF_EVENT_TXN_STARTED; + cpuc->group_flag |= PERF_EVENT_TXN; cpuc->n_txn = 0; } @@ -1401,7 +1411,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED; + cpuc->group_flag &= ~PERF_EVENT_TXN; /* * Truncate the collected events. */ @@ -1435,11 +1445,7 @@ static int x86_pmu_commit_txn(const struct pmu *pmu) */ memcpy(cpuc->assign, assign, n*sizeof(int)); - /* - * Clear out the txn count so that ->cancel_txn() which gets - * run after ->commit_txn() doesn't undo things. - */ - cpuc->n_txn = 0; + cpuc->group_flag &= ~PERF_EVENT_TXN; return 0; } @@ -1607,8 +1613,6 @@ static const struct stacktrace_ops backtrace_ops = { .walk_stack = print_context_stack_bp, }; -#include "../dumpstack.h" - static void perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) { @@ -1730,22 +1734,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } -void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) -{ - regs->ip = ip; - /* - * perf_arch_fetch_caller_regs adds another call, we need to increment - * the skip level - */ - regs->bp = rewind_frame_pointer(skip + 1); - regs->cs = __KERNEL_CS; - /* - * We abuse bit 3 to pass exact information, see perf_misc_flags - * and the comment with PERF_EFLAGS_EXACT. - */ - regs->flags = 0; -} - unsigned long perf_instruction_pointer(struct pt_regs *regs) { unsigned long ip; diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index ae85d69644d1..107711bf0ee8 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -21,22 +21,36 @@ struct p4_event_bind { char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on abscence */ }; -struct p4_cache_event_bind { +struct p4_pebs_bind { unsigned int metric_pebs; unsigned int metric_vert; }; -#define P4_GEN_CACHE_EVENT_BIND(name) \ - [P4_CACHE__##name] = { \ - .metric_pebs = P4_PEBS__##name, \ - .metric_vert = P4_VERT__##name, \ +/* it sets P4_PEBS_ENABLE_UOP_TAG as well */ +#define P4_GEN_PEBS_BIND(name, pebs, vert) \ + [P4_PEBS_METRIC__##name] = { \ + .metric_pebs = pebs | P4_PEBS_ENABLE_UOP_TAG, \ + .metric_vert = vert, \ } -static struct p4_cache_event_bind p4_cache_event_bind_map[] = { - P4_GEN_CACHE_EVENT_BIND(1stl_cache_load_miss_retired), - P4_GEN_CACHE_EVENT_BIND(2ndl_cache_load_miss_retired), - P4_GEN_CACHE_EVENT_BIND(dtlb_load_miss_retired), - P4_GEN_CACHE_EVENT_BIND(dtlb_store_miss_retired), +/* + * note we have P4_PEBS_ENABLE_UOP_TAG always set here + * + * it's needed for mapping P4_PEBS_CONFIG_METRIC_MASK bits of + * event configuration to find out which values are to be + * written into MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT + * resgisters + */ +static struct p4_pebs_bind p4_pebs_bind_map[] = { + P4_GEN_PEBS_BIND(1stl_cache_load_miss_retired, 0x0000001, 0x0000001), + P4_GEN_PEBS_BIND(2ndl_cache_load_miss_retired, 0x0000002, 0x0000001), + P4_GEN_PEBS_BIND(dtlb_load_miss_retired, 0x0000004, 0x0000001), + P4_GEN_PEBS_BIND(dtlb_store_miss_retired, 0x0000004, 0x0000002), + P4_GEN_PEBS_BIND(dtlb_all_miss_retired, 0x0000004, 0x0000003), + P4_GEN_PEBS_BIND(tagged_mispred_branch, 0x0018000, 0x0000010), + P4_GEN_PEBS_BIND(mob_load_replay_retired, 0x0000200, 0x0000001), + P4_GEN_PEBS_BIND(split_load_retired, 0x0000400, 0x0000001), + P4_GEN_PEBS_BIND(split_store_retired, 0x0000400, 0x0000002), }; /* @@ -281,10 +295,10 @@ static struct p4_event_bind p4_event_bind_map[] = { }, }; -#define P4_GEN_CACHE_EVENT(event, bit, cache_event) \ +#define P4_GEN_CACHE_EVENT(event, bit, metric) \ p4_config_pack_escr(P4_ESCR_EVENT(event) | \ P4_ESCR_EMASK_BIT(event, bit)) | \ - p4_config_pack_cccr(cache_event | \ + p4_config_pack_cccr(metric | \ P4_CCCR_ESEL(P4_OPCODE_ESEL(P4_OPCODE(event)))) static __initconst const u64 p4_hw_cache_event_ids @@ -296,34 +310,34 @@ static __initconst const u64 p4_hw_cache_event_ids [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0, [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, - P4_CACHE__1stl_cache_load_miss_retired), + P4_PEBS_METRIC__1stl_cache_load_miss_retired), }, }, [ C(LL ) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0, [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, - P4_CACHE__2ndl_cache_load_miss_retired), + P4_PEBS_METRIC__2ndl_cache_load_miss_retired), }, }, [ C(DTLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0, [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, - P4_CACHE__dtlb_load_miss_retired), + P4_PEBS_METRIC__dtlb_load_miss_retired), }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = 0x0, [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, - P4_CACHE__dtlb_store_miss_retired), + P4_PEBS_METRIC__dtlb_store_miss_retired), }, }, [ C(ITLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, HIT, - P4_CACHE__itlb_reference_hit), + P4_PEBS_METRIC__none), [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, MISS, - P4_CACHE__itlb_reference_miss), + P4_PEBS_METRIC__none), }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = -1, @@ -414,11 +428,37 @@ static u64 p4_pmu_event_map(int hw_event) return config; } +static int p4_validate_raw_event(struct perf_event *event) +{ + unsigned int v; + + /* user data may have out-of-bound event index */ + v = p4_config_unpack_event(event->attr.config); + if (v >= ARRAY_SIZE(p4_event_bind_map)) { + pr_warning("P4 PMU: Unknown event code: %d\n", v); + return -EINVAL; + } + + /* + * it may have some screwed PEBS bits + */ + if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE)) { + pr_warning("P4 PMU: PEBS are not supported yet\n"); + return -EINVAL; + } + v = p4_config_unpack_metric(event->attr.config); + if (v >= ARRAY_SIZE(p4_pebs_bind_map)) { + pr_warning("P4 PMU: Unknown metric code: %d\n", v); + return -EINVAL; + } + + return 0; +} + static int p4_hw_config(struct perf_event *event) { int cpu = get_cpu(); int rc = 0; - unsigned int evnt; u32 escr, cccr; /* @@ -438,12 +478,9 @@ static int p4_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) { - /* user data may have out-of-bound event index */ - evnt = p4_config_unpack_event(event->attr.config); - if (evnt >= ARRAY_SIZE(p4_event_bind_map)) { - rc = -EINVAL; + rc = p4_validate_raw_event(event); + if (rc) goto out; - } /* * We don't control raw events so it's up to the caller @@ -451,12 +488,15 @@ static int p4_hw_config(struct perf_event *event) * on HT machine but allow HT-compatible specifics to be * passed on) * + * Note that for RAW events we allow user to use P4_CCCR_RESERVED + * bits since we keep additional info here (for cache events and etc) + * * XXX: HT wide things should check perf_paranoid_cpu() && * CAP_SYS_ADMIN */ event->hw.config |= event->attr.config & (p4_config_pack_escr(P4_ESCR_MASK_HT) | - p4_config_pack_cccr(P4_CCCR_MASK_HT)); + p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED)); } rc = x86_setup_perfctr(event); @@ -482,6 +522,29 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc) return overflow; } +static void p4_pmu_disable_pebs(void) +{ + /* + * FIXME + * + * It's still allowed that two threads setup same cache + * events so we can't simply clear metrics until we knew + * noone is depending on us, so we need kind of counter + * for "ReplayEvent" users. + * + * What is more complex -- RAW events, if user (for some + * reason) will pass some cache event metric with improper + * event opcode -- it's fine from hardware point of view + * but completely nonsence from "meaning" of such action. + * + * So at moment let leave metrics turned on forever -- it's + * ok for now but need to be revisited! + * + * (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)0); + * (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)0); + */ +} + static inline void p4_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -507,6 +570,26 @@ static void p4_pmu_disable_all(void) continue; p4_pmu_disable_event(event); } + + p4_pmu_disable_pebs(); +} + +/* configuration must be valid */ +static void p4_pmu_enable_pebs(u64 config) +{ + struct p4_pebs_bind *bind; + unsigned int idx; + + BUILD_BUG_ON(P4_PEBS_METRIC__max > P4_PEBS_CONFIG_METRIC_MASK); + + idx = p4_config_unpack_metric(config); + if (idx == P4_PEBS_METRIC__none) + return; + + bind = &p4_pebs_bind_map[idx]; + + (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs); + (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert); } static void p4_pmu_enable_event(struct perf_event *event) @@ -515,9 +598,7 @@ static void p4_pmu_enable_event(struct perf_event *event) int thread = p4_ht_config_thread(hwc->config); u64 escr_conf = p4_config_unpack_escr(p4_clear_ht_bit(hwc->config)); unsigned int idx = p4_config_unpack_event(hwc->config); - unsigned int idx_cache = p4_config_unpack_cache_event(hwc->config); struct p4_event_bind *bind; - struct p4_cache_event_bind *bind_cache; u64 escr_addr, cccr; bind = &p4_event_bind_map[idx]; @@ -537,16 +618,10 @@ static void p4_pmu_enable_event(struct perf_event *event) cccr = p4_config_unpack_cccr(hwc->config); /* - * it could be Cache event so that we need to - * set metrics into additional MSRs + * it could be Cache event so we need to write metrics + * into additional MSRs */ - BUILD_BUG_ON(P4_CACHE__MAX > P4_CCCR_CACHE_OPS_MASK); - if (idx_cache > P4_CACHE__NONE && - idx_cache < ARRAY_SIZE(p4_cache_event_bind_map)) { - bind_cache = &p4_cache_event_bind_map[idx_cache]; - (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind_cache->metric_pebs); - (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind_cache->metric_vert); - } + p4_pmu_enable_pebs(hwc->config); (void)checking_wrmsrl(escr_addr, escr_conf); (void)checking_wrmsrl(hwc->config_base + hwc->idx, @@ -829,6 +904,15 @@ static __initconst const struct x86_pmu p4_pmu = { .max_period = (1ULL << 39) - 1, .hw_config = p4_hw_config, .schedule_events = p4_pmu_schedule_events, + /* + * This handles erratum N15 in intel doc 249199-029, + * the counter may not be updated correctly on write + * so we need a second write operation to do the trick + * (the official workaround didn't work) + * + * the former idea is taken from OProfile code + */ + .perfctr_second_write = 1, }; static __init int p4_pmu_init(void) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c new file mode 100644 index 000000000000..34b4dad6f0b8 --- /dev/null +++ b/arch/x86/kernel/cpu/scattered.c @@ -0,0 +1,63 @@ +/* + * Routines to indentify additional cpu features that are scattered in + * cpuid space. + */ +#include <linux/cpu.h> + +#include <asm/pat.h> +#include <asm/processor.h> + +#include <asm/apic.h> + +struct cpuid_bit { + u16 feature; + u8 reg; + u8 bit; + u32 level; + u32 sub_leaf; +}; + +enum cpuid_regs { + CR_EAX = 0, + CR_ECX, + CR_EDX, + CR_EBX +}; + +void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) +{ + u32 max_level; + u32 regs[4]; + const struct cpuid_bit *cb; + + static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { + { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, + { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, + { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, + { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, + { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, + { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 }, + { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a, 0 }, + { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, + { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, + { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a, 0 }, + { 0, 0, 0, 0, 0 } + }; + + for (cb = cpuid_bits; cb->feature; cb++) { + + /* Verify that the level is valid */ + max_level = cpuid_eax(cb->level & 0xffff0000); + if (max_level < cb->level || + max_level > (cb->level | 0xffff)) + continue; + + cpuid_count(cb->level, cb->sub_leaf, ®s[CR_EAX], + ®s[CR_EBX], ®s[CR_ECX], ®s[CR_EDX]); + + if (regs[cb->reg] & (1 << cb->bit)) + set_cpu_cap(c, cb->feature); + } +} diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/topology.c index 10fa5684a662..4397e987a1cf 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/topology.c @@ -1,62 +1,14 @@ /* - * Routines to indentify additional cpu features that are scattered in - * cpuid space. + * Check for extended topology enumeration cpuid leaf 0xb and if it + * exists, use it for populating initial_apicid and cpu topology + * detection. */ -#include <linux/cpu.h> +#include <linux/cpu.h> +#include <asm/apic.h> #include <asm/pat.h> #include <asm/processor.h> -#include <asm/apic.h> - -struct cpuid_bit { - u16 feature; - u8 reg; - u8 bit; - u32 level; -}; - -enum cpuid_regs { - CR_EAX = 0, - CR_ECX, - CR_EDX, - CR_EBX -}; - -void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) -{ - u32 max_level; - u32 regs[4]; - const struct cpuid_bit *cb; - - static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { - { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 }, - { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 }, - { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006 }, - { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007 }, - { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a }, - { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a }, - { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a }, - { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a }, - { 0, 0, 0, 0 } - }; - - for (cb = cpuid_bits; cb->feature; cb++) { - - /* Verify that the level is valid */ - max_level = cpuid_eax(cb->level & 0xffff0000); - if (max_level < cb->level || - max_level > (cb->level | 0xffff)) - continue; - - cpuid(cb->level, ®s[CR_EAX], ®s[CR_EBX], - ®s[CR_ECX], ®s[CR_EDX]); - - if (regs[cb->reg] & (1 << cb->bit)) - set_cpu_cap(c, cb->feature); - } -} - /* leaf 0xb SMT level */ #define SMT_LEVEL 0 diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index c89a386930b7..6e8752c1bd52 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -18,7 +18,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" int panic_on_unrecovered_nmi; int panic_on_io_nmi; diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h deleted file mode 100644 index e1a93be4fd44..000000000000 --- a/arch/x86/kernel/dumpstack.h +++ /dev/null @@ -1,56 +0,0 @@ -/* - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs - */ - -#ifndef DUMPSTACK_H -#define DUMPSTACK_H - -#ifdef CONFIG_X86_32 -#define STACKSLOTS_PER_LINE 8 -#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) -#else -#define STACKSLOTS_PER_LINE 4 -#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) -#endif - -#include <linux/uaccess.h> - -extern void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl); - -extern void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl); - -extern unsigned int code_bytes; - -/* The form of the top of the frame on the stack */ -struct stack_frame { - struct stack_frame *next_frame; - unsigned long return_address; -}; - -struct stack_frame_ia32 { - u32 next_frame; - u32 return_address; -}; - -static inline unsigned long rewind_frame_pointer(int n) -{ - struct stack_frame *frame; - - get_bp(frame); - -#ifdef CONFIG_FRAME_POINTER - while (n--) { - if (probe_kernel_address(&frame->next_frame, frame)) - break; - } -#endif - - return (unsigned long)frame; -} - -#endif /* DUMPSTACK_H */ diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 11540a189d93..0f6376ffa2d9 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -16,8 +16,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" - void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 272c9f1f05f3..57a21f11c791 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -16,7 +16,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" #define N_EXCEPTION_STACKS_END \ (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index cd49141cf153..258e93fa2630 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -611,14 +611,14 @@ ldt_ss: * compensating for the offset by changing to the ESPFIX segment with * a base address that matches for the difference. */ +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) mov %esp, %edx /* load kernel esp */ mov PT_OLDESP(%esp), %eax /* load userspace esp */ mov %dx, %ax /* eax: new kernel esp */ sub %eax, %edx /* offset (low word is 0) */ - PER_CPU(gdt_page, %ebx) shr $16, %edx - mov %dl, GDT_ENTRY_ESPFIX_SS * 8 + 4(%ebx) /* bits 16..23 */ - mov %dh, GDT_ENTRY_ESPFIX_SS * 8 + 7(%ebx) /* bits 24..31 */ + mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ + mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ pushl $__ESPFIX_SS CFI_ADJUST_CFA_OFFSET 4 push %eax /* new kernel esp */ @@ -791,9 +791,8 @@ ptregs_clone: * normal stack and adjusts ESP with the matching offset. */ /* fixup the stack */ - PER_CPU(gdt_page, %ebx) - mov GDT_ENTRY_ESPFIX_SS * 8 + 4(%ebx), %al /* bits 16..23 */ - mov GDT_ENTRY_ESPFIX_SS * 8 + 7(%ebx), %ah /* bits 24..31 */ + mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ + mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ shl $16, %eax addl %esp, %eax /* the adjusted stack pointer */ pushl $__KERNEL_DS @@ -1166,6 +1165,9 @@ ENTRY(xen_failsafe_callback) .previous ENDPROC(xen_failsafe_callback) +BUILD_INTERRUPT3(xen_hvm_callback_vector, XEN_HVM_EVTCHN_CALLBACK, + xen_evtchn_do_upcall) + #endif /* CONFIG_XEN */ #ifdef CONFIG_FUNCTION_TRACER diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 4db7c4d12ffa..c5ea5cdbe7b3 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1065,6 +1065,7 @@ ENTRY(\sym) END(\sym) .endm +#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) .macro paranoidzeroentry_ist sym do_sym ist ENTRY(\sym) INTR_FRAME @@ -1076,10 +1077,9 @@ ENTRY(\sym) TRACE_IRQS_OFF movq %rsp,%rdi /* pt_regs pointer */ xorl %esi,%esi /* no error code */ - PER_CPU(init_tss, %r12) - subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12) + subq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) call \do_sym - addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12) + addq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) jmp paranoid_exit /* %ebx: no swapgs flag */ CFI_ENDPROC END(\sym) @@ -1329,6 +1329,9 @@ ENTRY(xen_failsafe_callback) CFI_ENDPROC END(xen_failsafe_callback) +apicinterrupt XEN_HVM_EVTCHN_CALLBACK \ + xen_hvm_callback_vector xen_evtchn_do_upcall + #endif /* CONFIG_XEN */ /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 3d1e6f16b7a6..239046bd447f 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -234,9 +234,8 @@ ENTRY(secondary_startup_64) * init data section till per cpu areas are set up. */ movl $MSR_GS_BASE,%ecx - movq initial_gs(%rip),%rax - movq %rax,%rdx - shrq $32,%rdx + movl initial_gs(%rip),%eax + movl initial_gs+4(%rip),%edx wrmsr /* esi is pointer to real mode structure with interesting info. diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index a8f1b803d2fd..a474ec37c32f 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -208,6 +208,9 @@ int arch_bp_generic_fields(int x86_len, int x86_type, { /* Len */ switch (x86_len) { + case X86_BREAKPOINT_LEN_X: + *gen_len = sizeof(long); + break; case X86_BREAKPOINT_LEN_1: *gen_len = HW_BREAKPOINT_LEN_1; break; @@ -251,6 +254,29 @@ static int arch_build_bp_info(struct perf_event *bp) info->address = bp->attr.bp_addr; + /* Type */ + switch (bp->attr.bp_type) { + case HW_BREAKPOINT_W: + info->type = X86_BREAKPOINT_WRITE; + break; + case HW_BREAKPOINT_W | HW_BREAKPOINT_R: + info->type = X86_BREAKPOINT_RW; + break; + case HW_BREAKPOINT_X: + info->type = X86_BREAKPOINT_EXECUTE; + /* + * x86 inst breakpoints need to have a specific undefined len. + * But we still need to check userspace is not trying to setup + * an unsupported length, to get a range breakpoint for example. + */ + if (bp->attr.bp_len == sizeof(long)) { + info->len = X86_BREAKPOINT_LEN_X; + return 0; + } + default: + return -EINVAL; + } + /* Len */ switch (bp->attr.bp_len) { case HW_BREAKPOINT_LEN_1: @@ -271,21 +297,6 @@ static int arch_build_bp_info(struct perf_event *bp) return -EINVAL; } - /* Type */ - switch (bp->attr.bp_type) { - case HW_BREAKPOINT_W: - info->type = X86_BREAKPOINT_WRITE; - break; - case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - info->type = X86_BREAKPOINT_RW; - break; - case HW_BREAKPOINT_X: - info->type = X86_BREAKPOINT_EXECUTE; - break; - default: - return -EINVAL; - } - return 0; } /* @@ -305,6 +316,9 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) ret = -EINVAL; switch (info->len) { + case X86_BREAKPOINT_LEN_X: + align = sizeof(long) -1; + break; case X86_BREAKPOINT_LEN_1: align = 0; break; @@ -466,6 +480,13 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) perf_bp_event(bp, args->regs); + /* + * Set up resume flag to avoid breakpoint recursion when + * returning back to origin. + */ + if (bp->hw.info.type == X86_BREAKPOINT_EXECUTE) + args->regs->flags |= X86_EFLAGS_RF; + rcu_read_unlock(); } /* diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 01ab17ae2ae7..ef10940e1af0 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -49,55 +49,94 @@ #include <asm/system.h> #include <asm/apic.h> -/** - * pt_regs_to_gdb_regs - Convert ptrace regs to GDB regs - * @gdb_regs: A pointer to hold the registers in the order GDB wants. - * @regs: The &struct pt_regs of the current process. - * - * Convert the pt_regs in @regs into the format for registers that - * GDB expects, stored in @gdb_regs. - */ -void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { -#ifndef CONFIG_X86_32 - u32 *gdb_regs32 = (u32 *)gdb_regs; +#ifdef CONFIG_X86_32 + { "ax", 4, offsetof(struct pt_regs, ax) }, + { "cx", 4, offsetof(struct pt_regs, cx) }, + { "dx", 4, offsetof(struct pt_regs, dx) }, + { "bx", 4, offsetof(struct pt_regs, bx) }, + { "sp", 4, offsetof(struct pt_regs, sp) }, + { "bp", 4, offsetof(struct pt_regs, bp) }, + { "si", 4, offsetof(struct pt_regs, si) }, + { "di", 4, offsetof(struct pt_regs, di) }, + { "ip", 4, offsetof(struct pt_regs, ip) }, + { "flags", 4, offsetof(struct pt_regs, flags) }, + { "cs", 4, offsetof(struct pt_regs, cs) }, + { "ss", 4, offsetof(struct pt_regs, ss) }, + { "ds", 4, offsetof(struct pt_regs, ds) }, + { "es", 4, offsetof(struct pt_regs, es) }, + { "fs", 4, -1 }, + { "gs", 4, -1 }, +#else + { "ax", 8, offsetof(struct pt_regs, ax) }, + { "bx", 8, offsetof(struct pt_regs, bx) }, + { "cx", 8, offsetof(struct pt_regs, cx) }, + { "dx", 8, offsetof(struct pt_regs, dx) }, + { "si", 8, offsetof(struct pt_regs, dx) }, + { "di", 8, offsetof(struct pt_regs, di) }, + { "bp", 8, offsetof(struct pt_regs, bp) }, + { "sp", 8, offsetof(struct pt_regs, sp) }, + { "r8", 8, offsetof(struct pt_regs, r8) }, + { "r9", 8, offsetof(struct pt_regs, r9) }, + { "r10", 8, offsetof(struct pt_regs, r10) }, + { "r11", 8, offsetof(struct pt_regs, r11) }, + { "r12", 8, offsetof(struct pt_regs, r12) }, + { "r13", 8, offsetof(struct pt_regs, r13) }, + { "r14", 8, offsetof(struct pt_regs, r14) }, + { "r15", 8, offsetof(struct pt_regs, r15) }, + { "ip", 8, offsetof(struct pt_regs, ip) }, + { "flags", 4, offsetof(struct pt_regs, flags) }, + { "cs", 4, offsetof(struct pt_regs, cs) }, + { "ss", 4, offsetof(struct pt_regs, ss) }, #endif - gdb_regs[GDB_AX] = regs->ax; - gdb_regs[GDB_BX] = regs->bx; - gdb_regs[GDB_CX] = regs->cx; - gdb_regs[GDB_DX] = regs->dx; - gdb_regs[GDB_SI] = regs->si; - gdb_regs[GDB_DI] = regs->di; - gdb_regs[GDB_BP] = regs->bp; - gdb_regs[GDB_PC] = regs->ip; +}; + +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) +{ + if ( #ifdef CONFIG_X86_32 - gdb_regs[GDB_PS] = regs->flags; - gdb_regs[GDB_DS] = regs->ds; - gdb_regs[GDB_ES] = regs->es; - gdb_regs[GDB_CS] = regs->cs; - gdb_regs[GDB_FS] = 0xFFFF; - gdb_regs[GDB_GS] = 0xFFFF; - if (user_mode_vm(regs)) { - gdb_regs[GDB_SS] = regs->ss; - gdb_regs[GDB_SP] = regs->sp; - } else { - gdb_regs[GDB_SS] = __KERNEL_DS; - gdb_regs[GDB_SP] = kernel_stack_pointer(regs); + regno == GDB_SS || regno == GDB_FS || regno == GDB_GS || +#endif + regno == GDB_SP || regno == GDB_ORIG_AX) + return 0; + + if (dbg_reg_def[regno].offset != -1) + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + return 0; +} + +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno == GDB_ORIG_AX) { + memcpy(mem, ®s->orig_ax, sizeof(regs->orig_ax)); + return "orig_ax"; } -#else - gdb_regs[GDB_R8] = regs->r8; - gdb_regs[GDB_R9] = regs->r9; - gdb_regs[GDB_R10] = regs->r10; - gdb_regs[GDB_R11] = regs->r11; - gdb_regs[GDB_R12] = regs->r12; - gdb_regs[GDB_R13] = regs->r13; - gdb_regs[GDB_R14] = regs->r14; - gdb_regs[GDB_R15] = regs->r15; - gdb_regs32[GDB_PS] = regs->flags; - gdb_regs32[GDB_CS] = regs->cs; - gdb_regs32[GDB_SS] = regs->ss; - gdb_regs[GDB_SP] = kernel_stack_pointer(regs); + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1) + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + + switch (regno) { +#ifdef CONFIG_X86_32 + case GDB_SS: + if (!user_mode_vm(regs)) + *(unsigned long *)mem = __KERNEL_DS; + break; + case GDB_SP: + if (!user_mode_vm(regs)) + *(unsigned long *)mem = kernel_stack_pointer(regs); + break; + case GDB_GS: + case GDB_FS: + *(unsigned long *)mem = 0xFFFF; + break; #endif + } + return dbg_reg_def[regno].name; } /** @@ -150,54 +189,13 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) gdb_regs[GDB_SP] = p->thread.sp; } -/** - * gdb_regs_to_pt_regs - Convert GDB regs to ptrace regs. - * @gdb_regs: A pointer to hold the registers we've received from GDB. - * @regs: A pointer to a &struct pt_regs to hold these values in. - * - * Convert the GDB regs in @gdb_regs into the pt_regs, and store them - * in @regs. - */ -void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) -{ -#ifndef CONFIG_X86_32 - u32 *gdb_regs32 = (u32 *)gdb_regs; -#endif - regs->ax = gdb_regs[GDB_AX]; - regs->bx = gdb_regs[GDB_BX]; - regs->cx = gdb_regs[GDB_CX]; - regs->dx = gdb_regs[GDB_DX]; - regs->si = gdb_regs[GDB_SI]; - regs->di = gdb_regs[GDB_DI]; - regs->bp = gdb_regs[GDB_BP]; - regs->ip = gdb_regs[GDB_PC]; -#ifdef CONFIG_X86_32 - regs->flags = gdb_regs[GDB_PS]; - regs->ds = gdb_regs[GDB_DS]; - regs->es = gdb_regs[GDB_ES]; - regs->cs = gdb_regs[GDB_CS]; -#else - regs->r8 = gdb_regs[GDB_R8]; - regs->r9 = gdb_regs[GDB_R9]; - regs->r10 = gdb_regs[GDB_R10]; - regs->r11 = gdb_regs[GDB_R11]; - regs->r12 = gdb_regs[GDB_R12]; - regs->r13 = gdb_regs[GDB_R13]; - regs->r14 = gdb_regs[GDB_R14]; - regs->r15 = gdb_regs[GDB_R15]; - regs->flags = gdb_regs32[GDB_PS]; - regs->cs = gdb_regs32[GDB_CS]; - regs->ss = gdb_regs32[GDB_SS]; -#endif -} - static struct hw_breakpoint { unsigned enabled; unsigned long addr; int len; int type; struct perf_event **pev; -} breakinfo[4]; +} breakinfo[HBP_NUM]; static unsigned long early_dr7; @@ -205,7 +203,7 @@ static void kgdb_correct_hw_break(void) { int breakno; - for (breakno = 0; breakno < 4; breakno++) { + for (breakno = 0; breakno < HBP_NUM; breakno++) { struct perf_event *bp; struct arch_hw_breakpoint *info; int val; @@ -292,10 +290,10 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) { int i; - for (i = 0; i < 4; i++) + for (i = 0; i < HBP_NUM; i++) if (breakinfo[i].addr == addr && breakinfo[i].enabled) break; - if (i == 4) + if (i == HBP_NUM) return -1; if (hw_break_release_slot(i)) { @@ -313,7 +311,7 @@ static void kgdb_remove_all_hw_break(void) int cpu = raw_smp_processor_id(); struct perf_event *bp; - for (i = 0; i < 4; i++) { + for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; bp = *per_cpu_ptr(breakinfo[i].pev, cpu); @@ -333,10 +331,10 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) { int i; - for (i = 0; i < 4; i++) + for (i = 0; i < HBP_NUM; i++) if (!breakinfo[i].enabled) break; - if (i == 4) + if (i == HBP_NUM) return -1; switch (bptype) { @@ -397,7 +395,7 @@ void kgdb_disable_hw_debug(struct pt_regs *regs) /* Disable hardware debugging while we are in kgdb: */ set_debugreg(0UL, 7); - for (i = 0; i < 4; i++) { + for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; if (dbg_is_early) { @@ -458,7 +456,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, { unsigned long addr; char *ptr; - int newPC; switch (remcomInBuffer[0]) { case 'c': @@ -469,8 +466,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, linux_regs->ip = addr; case 'D': case 'k': - newPC = linux_regs->ip; - /* clear the trace bit */ linux_regs->flags &= ~X86_EFLAGS_TF; atomic_set(&kgdb_cpu_doing_single_step, -1); @@ -645,7 +640,7 @@ void kgdb_arch_late(void) attr.bp_len = HW_BREAKPOINT_LEN_1; attr.bp_type = HW_BREAKPOINT_W; attr.disabled = 1; - for (i = 0; i < 4; i++) { + for (i = 0; i < HBP_NUM; i++) { if (breakinfo[i].pev) continue; breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL); diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 675879b65ce6..1bfb6cf4dd55 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -126,16 +126,22 @@ static void __kprobes synthesize_reljump(void *from, void *to) } /* - * Check for the REX prefix which can only exist on X86_64 - * X86_32 always returns 0 + * Skip the prefixes of the instruction. */ -static int __kprobes is_REX_prefix(kprobe_opcode_t *insn) +static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) { + insn_attr_t attr; + + attr = inat_get_opcode_attribute((insn_byte_t)*insn); + while (inat_is_legacy_prefix(attr)) { + insn++; + attr = inat_get_opcode_attribute((insn_byte_t)*insn); + } #ifdef CONFIG_X86_64 - if ((*insn & 0xf0) == 0x40) - return 1; + if (inat_is_rex_prefix(attr)) + insn++; #endif - return 0; + return insn; } /* @@ -272,6 +278,9 @@ static int __kprobes can_probe(unsigned long paddr) */ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) { + /* Skip prefixes */ + insn = skip_prefixes(insn); + switch (*insn) { case 0xfa: /* cli */ case 0xfb: /* sti */ @@ -280,13 +289,6 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) return 1; } - /* - * on X86_64, 0x40-0x4f are REX prefixes so we need to look - * at the next byte instead.. but of course not recurse infinitely - */ - if (is_REX_prefix(insn)) - return is_IF_modifier(++insn); - return 0; } @@ -803,9 +805,8 @@ static void __kprobes resume_execution(struct kprobe *p, unsigned long orig_ip = (unsigned long)p->addr; kprobe_opcode_t *insn = p->ainsn.insn; - /*skip the REX prefix*/ - if (is_REX_prefix(insn)) - insn++; + /* Skip prefixes */ + insn = skip_prefixes(insn); regs->flags &= ~X86_EFLAGS_TF; switch (*insn) { diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c index 5915e0b33303..79ae68154e87 100644 --- a/arch/x86/kernel/mrst.c +++ b/arch/x86/kernel/mrst.c @@ -25,8 +25,34 @@ #include <asm/i8259.h> #include <asm/apb_timer.h> +/* + * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock, + * cmdline option x86_mrst_timer can be used to override the configuration + * to prefer one or the other. + * at runtime, there are basically three timer configurations: + * 1. per cpu apbt clock only + * 2. per cpu always-on lapic clocks only, this is Penwell/Medfield only + * 3. per cpu lapic clock (C3STOP) and one apbt clock, with broadcast. + * + * by default (without cmdline option), platform code first detects cpu type + * to see if we are on lincroft or penwell, then set up both lapic or apbt + * clocks accordingly. + * i.e. by default, medfield uses configuration #2, moorestown uses #1. + * config #3 is supported but not recommended on medfield. + * + * rating and feature summary: + * lapic (with C3STOP) --------- 100 + * apbt (always-on) ------------ 110 + * lapic (always-on,ARAT) ------ 150 + */ + +__cpuinitdata enum mrst_timer_options mrst_timer_options; + static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM]; static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM]; +enum mrst_cpu_type __mrst_cpu_chip; +EXPORT_SYMBOL_GPL(__mrst_cpu_chip); + int sfi_mtimer_num; struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX]; @@ -167,18 +193,6 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) return 0; } -/* - * the secondary clock in Moorestown can be APBT or LAPIC clock, default to - * APBT but cmdline option can also override it. - */ -static void __cpuinit mrst_setup_secondary_clock(void) -{ - /* restore default lapic clock if disabled by cmdline */ - if (disable_apbt_percpu) - return setup_secondary_APIC_clock(); - apbt_setup_secondary_clock(); -} - static unsigned long __init mrst_calibrate_tsc(void) { unsigned long flags, fast_calibrate; @@ -195,6 +209,21 @@ static unsigned long __init mrst_calibrate_tsc(void) void __init mrst_time_init(void) { + switch (mrst_timer_options) { + case MRST_TIMER_APBT_ONLY: + break; + case MRST_TIMER_LAPIC_APBT: + x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; + break; + default: + if (!boot_cpu_has(X86_FEATURE_ARAT)) + break; + x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; + return; + } + /* we need at least one APB timer */ sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr); pre_init_apic_IRQ0(); apbt_time_init(); @@ -205,16 +234,21 @@ void __init mrst_rtc_init(void) sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc); } -/* - * if we use per cpu apb timer, the bootclock already setup. if we use lapic - * timer and one apbt timer for broadcast, we need to set up lapic boot clock. - */ -static void __init mrst_setup_boot_clock(void) +void __cpuinit mrst_arch_setup(void) { - pr_info("%s: per cpu apbt flag %d \n", __func__, disable_apbt_percpu); - if (disable_apbt_percpu) - setup_boot_APIC_clock(); -}; + if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27) + __mrst_cpu_chip = MRST_CPU_CHIP_PENWELL; + else if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x26) + __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + else { + pr_err("Unknown Moorestown CPU (%d:%d), default to Lincroft\n", + boot_cpu_data.x86, boot_cpu_data.x86_model); + __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + } + pr_debug("Moorestown CPU %s identified\n", + (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) ? + "Lincroft" : "Penwell"); +} /* MID systems don't have i8042 controller */ static int mrst_i8042_detect(void) @@ -232,11 +266,13 @@ void __init x86_mrst_early_setup(void) x86_init.resources.reserve_resources = x86_init_noop; x86_init.timers.timer_init = mrst_time_init; - x86_init.timers.setup_percpu_clockev = mrst_setup_boot_clock; + x86_init.timers.setup_percpu_clockev = x86_init_noop; x86_init.irqs.pre_vector_init = x86_init_noop; - x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock; + x86_init.oem.arch_setup = mrst_arch_setup; + + x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock; x86_platform.calibrate_tsc = mrst_calibrate_tsc; x86_platform.i8042_detect = mrst_i8042_detect; @@ -250,3 +286,26 @@ void __init x86_mrst_early_setup(void) x86_init.mpparse.get_smp_config = x86_init_uint_noop; } + +/* + * if user does not want to use per CPU apb timer, just give it a lower rating + * than local apic timer and skip the late per cpu timer init. + */ +static inline int __init setup_x86_mrst_timer(char *arg) +{ + if (!arg) + return -EINVAL; + + if (strcmp("apbt_only", arg) == 0) + mrst_timer_options = MRST_TIMER_APBT_ONLY; + else if (strcmp("lapic_and_apbt", arg) == 0) + mrst_timer_options = MRST_TIMER_LAPIC_APBT; + else { + pr_warning("X86 MRST timer option %s not recognised" + " use x86_mrst_timer=apbt_only or lapic_and_apbt\n", + arg); + return -EINVAL; + } + return 0; +} +__setup("x86_mrst_timer=", setup_x86_mrst_timer); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index cbcf013a0ec6..d401f1d2d06e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -526,44 +526,10 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) return (edx & MWAIT_EDX_C1); } -/* - * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e. - * For more information see - * - Erratum #400 for NPT family 0xf and family 0x10 CPUs - * - Erratum #365 for family 0x11 (not affected because C1e not in use) - */ -static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c) -{ - u64 val; - if (c->x86_vendor != X86_VENDOR_AMD) - goto no_c1e_idle; - - /* Family 0x0f models < rev F do not have C1E */ - if (c->x86 == 0x0F && c->x86_model >= 0x40) - return 1; - - if (c->x86 == 0x10) { - /* - * check OSVW bit for CPUs that are not affected - * by erratum #400 - */ - if (cpu_has(c, X86_FEATURE_OSVW)) { - rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val); - if (val >= 2) { - rdmsrl(MSR_AMD64_OSVW_STATUS, val); - if (!(val & BIT(1))) - goto no_c1e_idle; - } - } - return 1; - } - -no_c1e_idle: - return 0; -} +bool c1e_detected; +EXPORT_SYMBOL(c1e_detected); static cpumask_var_t c1e_mask; -static int c1e_detected; void c1e_remove_cpu(int cpu) { @@ -585,12 +551,12 @@ static void c1e_idle(void) u32 lo, hi; rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi); + if (lo & K8_INTP_C1E_ACTIVE_MASK) { - c1e_detected = 1; + c1e_detected = true; if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); printk(KERN_INFO "System has AMD C1E enabled\n"); - set_cpu_cap(&boot_cpu_data, X86_FEATURE_AMDC1E); } } @@ -639,7 +605,8 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) */ printk(KERN_INFO "using mwait in idle threads.\n"); pm_idle = mwait_idle; - } else if (check_c1e_idle(c)) { + } else if (cpu_has_amd_erratum(amd_erratum_400)) { + /* E400: APIC timer interrupt does not wake up CPU from C1e */ printk(KERN_INFO "using C1E aware idle routine\n"); pm_idle = c1e_idle; } else diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 8d128783af47..96586c3cbbbf 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -57,6 +57,8 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <trace/events/power.h> + asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); /* @@ -111,6 +113,8 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); + + trace_power_end(smp_processor_id()); } tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3c2422a99f1f..3d9ea531ddd1 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -51,6 +51,8 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <trace/events/power.h> + asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); @@ -138,6 +140,9 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); + + trace_power_end(smp_processor_id()); + /* In many cases the interrupt that ended idle has already called exit_idle. But some idle loops can be woken up without interrupt. */ diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 922eefbb3f6c..b53c525368a7 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -23,11 +23,16 @@ static int save_stack_stack(void *data, char *name) return 0; } -static void save_stack_address(void *data, unsigned long addr, int reliable) +static void +__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) { struct stack_trace *trace = data; +#ifdef CONFIG_FRAME_POINTER if (!reliable) return; +#endif + if (nosched && in_sched_functions(addr)) + return; if (trace->skip > 0) { trace->skip--; return; @@ -36,20 +41,15 @@ static void save_stack_address(void *data, unsigned long addr, int reliable) trace->entries[trace->nr_entries++] = addr; } +static void save_stack_address(void *data, unsigned long addr, int reliable) +{ + return __save_stack_address(data, addr, reliable, false); +} + static void save_stack_address_nosched(void *data, unsigned long addr, int reliable) { - struct stack_trace *trace = (struct stack_trace *)data; - if (!reliable) - return; - if (in_sched_functions(addr)) - return; - if (trace->skip > 0) { - trace->skip--; - return; - } - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = addr; + return __save_stack_address(data, addr, reliable, true); } static const struct stacktrace_ops save_stack_ops = { @@ -96,12 +96,13 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk); /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */ -struct stack_frame { +struct stack_frame_user { const void __user *next_fp; unsigned long ret_addr; }; -static int copy_stack_frame(const void __user *fp, struct stack_frame *frame) +static int +copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) { int ret; @@ -126,7 +127,7 @@ static inline void __save_stack_trace_user(struct stack_trace *trace) trace->entries[trace->nr_entries++] = regs->ip; while (trace->nr_entries < trace->max_entries) { - struct stack_frame frame; + struct stack_frame_user frame; frame.next_fp = NULL; frame.ret_addr = 0; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 725ef4d17cd5..60788dee0f8a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -392,7 +392,13 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; + #ifdef CONFIG_X86_LOCAL_APIC + if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) + == NOTIFY_STOP) + return; + +#ifndef CONFIG_LOCKUP_DETECTOR /* * Ok, so this is none of the documented NMI sources, * so it must be the NMI watchdog. @@ -400,6 +406,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (nmi_watchdog_tick(regs, reason)) return; if (!do_nmi_callback(regs, cpu)) +#endif /* !CONFIG_LOCKUP_DETECTOR */ unknown_nmi_error(reason, regs); #else unknown_nmi_error(reason, regs); diff --git a/arch/x86/kernel/verify_cpu_64.S b/arch/x86/kernel/verify_cpu_64.S index 45b6f8a975a1..56a8c2a867d9 100644 --- a/arch/x86/kernel/verify_cpu_64.S +++ b/arch/x86/kernel/verify_cpu_64.S @@ -31,6 +31,7 @@ */ #include <asm/cpufeature.h> +#include <asm/msr-index.h> verify_cpu: pushfl # Save caller passed flags @@ -88,7 +89,7 @@ verify_cpu_sse_test: je verify_cpu_sse_ok test %di,%di jz verify_cpu_no_longmode # only try to force SSE on AMD - movl $0xc0010015,%ecx # HWCR + movl $MSR_K7_HWCR,%ecx rdmsr btr $15,%eax # enable SSE wrmsr diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 37e68fc5e24a..980149867a19 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -36,15 +36,14 @@ int check_for_xstate(struct i387_fxsave_struct __user *buf, err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0], sizeof(struct _fpx_sw_bytes)); - if (err) - return err; + return -EFAULT; /* * First Magic check failed. */ if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1) - return -1; + return -EINVAL; /* * Check for error scenarios. @@ -52,19 +51,21 @@ int check_for_xstate(struct i387_fxsave_struct __user *buf, if (fx_sw_user->xstate_size < min_xstate_size || fx_sw_user->xstate_size > xstate_size || fx_sw_user->xstate_size > fx_sw_user->extended_size) - return -1; + return -EINVAL; err = __get_user(magic2, (__u32 *) (((void *)fpstate) + fx_sw_user->extended_size - FP_XSTATE_MAGIC2_SIZE)); + if (err) + return err; /* * Check for the presence of second magic word at the end of memory * layout. This detects the case where the user just copied the legacy * fpstate layout with out copying the extended state information * in the memory layout. */ - if (err || magic2 != FP_XSTATE_MAGIC2) - return -1; + if (magic2 != FP_XSTATE_MAGIC2) + return -EFAULT; return 0; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 56c9b6bd7655..bc5b9b8d4a33 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -131,7 +131,7 @@ static struct svm_direct_access_msrs { u32 index; /* Index of the MSR */ bool always; /* True if intercept is always on */ } direct_access_msrs[] = { - { .index = MSR_K6_STAR, .always = true }, + { .index = MSR_STAR, .always = true }, { .index = MSR_IA32_SYSENTER_CS, .always = true }, #ifdef CONFIG_X86_64 { .index = MSR_GS_BASE, .always = true }, @@ -384,8 +384,7 @@ static void svm_init_erratum_383(void) int err; u64 val; - /* Only Fam10h is affected */ - if (boot_cpu_data.x86 != 0x10) + if (!cpu_has_amd_erratum(amd_erratum_383)) return; /* Use _safe variants to not break nested virtualization */ @@ -2433,7 +2432,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) *data = tsc_offset + native_read_tsc(); break; } - case MSR_K6_STAR: + case MSR_STAR: *data = svm->vmcb->save.star; break; #ifdef CONFIG_X86_64 @@ -2557,7 +2556,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) break; } - case MSR_K6_STAR: + case MSR_STAR: svm->vmcb->save.star = data; break; #ifdef CONFIG_X86_64 diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 27a0222c2946..49b25eee25ac 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -240,14 +240,14 @@ static u64 host_efer; static void ept_save_pdptrs(struct kvm_vcpu *vcpu); /* - * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it + * Keep MSR_STAR at the end, as setup_msrs() will try to optimize it * away by decrementing the array size. */ static const u32 vmx_msr_index[] = { #ifdef CONFIG_X86_64 MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif - MSR_EFER, MSR_TSC_AUX, MSR_K6_STAR, + MSR_EFER, MSR_TSC_AUX, MSR_STAR, }; #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) @@ -1117,10 +1117,10 @@ static void setup_msrs(struct vcpu_vmx *vmx) if (index >= 0 && vmx->rdtscp_enabled) move_msr_up(vmx, index, save_nmsrs++); /* - * MSR_K6_STAR is only needed on long mode guests, and only + * MSR_STAR is only needed on long mode guests, and only * if efer.sce is enabled. */ - index = __find_msr_index(vmx, MSR_K6_STAR); + index = __find_msr_index(vmx, MSR_STAR); if ((index >= 0) && (vmx->vcpu.arch.efer & EFER_SCE)) move_msr_up(vmx, index, save_nmsrs++); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 97aab036dabf..25f19078b321 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -733,7 +733,7 @@ static u32 msrs_to_save[] = { HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_APIC_ASSIST_PAGE, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_K6_STAR, + MSR_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f871e04b6965..e10cf070ede0 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -30,6 +30,7 @@ ifeq ($(CONFIG_X86_32),y) lib-y += checksum_32.o lib-y += strstr_32.o lib-y += semaphore_32.o string_32.o + lib-y += cmpxchg.o ifneq ($(CONFIG_X86_CMPXCHG64),y) lib-y += cmpxchg8b_emu.o atomic64_386_32.o endif diff --git a/arch/x86/kernel/cpu/cmpxchg.c b/arch/x86/lib/cmpxchg.c index 2056ccf572cc..5d619f6df3ee 100644 --- a/arch/x86/kernel/cpu/cmpxchg.c +++ b/arch/x86/lib/cmpxchg.c @@ -52,21 +52,3 @@ unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new) } EXPORT_SYMBOL(cmpxchg_386_u32); #endif - -#ifndef CONFIG_X86_CMPXCHG64 -unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new) -{ - u64 prev; - unsigned long flags; - - /* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */ - local_irq_save(flags); - prev = *(u64 *)ptr; - if (prev == old) - *(u64 *)ptr = new; - local_irq_restore(flags); - return prev; -} -EXPORT_SYMBOL(cmpxchg_486_u64); -#endif - diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index a725b7f760ae..0002a3a33081 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -37,6 +37,28 @@ struct addr_marker { const char *name; }; +/* indices for address_markers; keep sync'd w/ address_markers below */ +enum address_markers_idx { + USER_SPACE_NR = 0, +#ifdef CONFIG_X86_64 + KERNEL_SPACE_NR, + LOW_KERNEL_NR, + VMALLOC_START_NR, + VMEMMAP_START_NR, + HIGH_KERNEL_NR, + MODULES_VADDR_NR, + MODULES_END_NR, +#else + KERNEL_SPACE_NR, + VMALLOC_START_NR, + VMALLOC_END_NR, +# ifdef CONFIG_HIGHMEM + PKMAP_BASE_NR, +# endif + FIXADDR_START_NR, +#endif +}; + /* Address space markers hints */ static struct addr_marker address_markers[] = { { 0, "User Space" }, @@ -331,14 +353,12 @@ static int pt_dump_init(void) #ifdef CONFIG_X86_32 /* Not a compile-time constant on x86-32 */ - address_markers[2].start_address = VMALLOC_START; - address_markers[3].start_address = VMALLOC_END; + address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; + address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; # ifdef CONFIG_HIGHMEM - address_markers[4].start_address = PKMAP_BASE; - address_markers[5].start_address = FIXADDR_START; -# else - address_markers[4].start_address = FIXADDR_START; + address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE; # endif + address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; #endif pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 12e4d2d3c110..3ba6e0608c55 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -62,8 +62,8 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, static void __iomem *__ioremap_caller(resource_size_t phys_addr, unsigned long size, unsigned long prot_val, void *caller) { - unsigned long pfn, offset, vaddr; - resource_size_t last_addr; + unsigned long offset, vaddr; + resource_size_t pfn, last_pfn, last_addr; const resource_size_t unaligned_phys_addr = phys_addr; const unsigned long unaligned_size = size; struct vm_struct *area; @@ -100,10 +100,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ - for (pfn = phys_addr >> PAGE_SHIFT; - (pfn << PAGE_SHIFT) < (last_addr & PAGE_MASK); - pfn++) { - + last_pfn = last_addr >> PAGE_SHIFT; + for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) { int is_ram = page_is_ram(pfn); if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) @@ -115,7 +113,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, * Mappings have to be page-aligned */ offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; + phys_addr &= PHYSICAL_PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; retval = reserve_memtype(phys_addr, (u64)phys_addr + size, @@ -613,7 +611,7 @@ void __init early_iounmap(void __iomem *addr, unsigned long size) return; } offset = virt_addr & ~PAGE_MASK; - nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT; + nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT; idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; while (nrpages > 0) { diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 5d0e67fff1a6..e5d5e2ce9f77 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -45,6 +45,8 @@ struct kmmio_fault_page { * Protected by kmmio_lock, when linked into kmmio_page_table. */ int count; + + bool scheduled_for_release; }; struct kmmio_delayed_release { @@ -398,8 +400,11 @@ static void release_kmmio_fault_page(unsigned long page, BUG_ON(f->count < 0); if (!f->count) { disarm_kmmio_fault_page(f); - f->release_next = *release_list; - *release_list = f; + if (!f->scheduled_for_release) { + f->release_next = *release_list; + *release_list = f; + f->scheduled_for_release = true; + } } } @@ -471,8 +476,10 @@ static void remove_kmmio_fault_pages(struct rcu_head *head) prevp = &f->release_next; } else { *prevp = f->release_next; + f->release_next = NULL; + f->scheduled_for_release = false; } - f = f->release_next; + f = *prevp; } spin_unlock_irqrestore(&kmmio_lock, flags); @@ -510,6 +517,9 @@ void unregister_kmmio_probe(struct kmmio_probe *p) kmmio_count--; spin_unlock_irqrestore(&kmmio_lock, flags); + if (!release_list) + return; + drelease = kmalloc(sizeof(*drelease), GFP_ATOMIC); if (!drelease) { pr_crit("leaking kmmio_fault_page objects.\n"); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 64121a18b8cb..f6ff57b7efa5 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -158,7 +158,7 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) return req_type; } -static int pat_pagerange_is_ram(unsigned long start, unsigned long end) +static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end) { int ram_page = 0, not_rampage = 0; unsigned long page_nr; diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c index 308e32570d84..38e6d174c497 100644 --- a/arch/x86/mm/pf_in.c +++ b/arch/x86/mm/pf_in.c @@ -40,16 +40,16 @@ static unsigned char prefix_codes[] = { static unsigned int reg_rop[] = { 0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F }; -static unsigned int reg_wop[] = { 0x88, 0x89 }; +static unsigned int reg_wop[] = { 0x88, 0x89, 0xAA, 0xAB }; static unsigned int imm_wop[] = { 0xC6, 0xC7 }; /* IA32 Manual 3, 3-432*/ -static unsigned int rw8[] = { 0x88, 0x8A, 0xC6 }; +static unsigned int rw8[] = { 0x88, 0x8A, 0xC6, 0xAA }; static unsigned int rw32[] = { - 0x89, 0x8B, 0xC7, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F + 0x89, 0x8B, 0xC7, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F, 0xAB }; -static unsigned int mw8[] = { 0x88, 0x8A, 0xC6, 0xB60F, 0xBE0F }; +static unsigned int mw8[] = { 0x88, 0x8A, 0xC6, 0xB60F, 0xBE0F, 0xAA }; static unsigned int mw16[] = { 0xB70F, 0xBF0F }; -static unsigned int mw32[] = { 0x89, 0x8B, 0xC7 }; +static unsigned int mw32[] = { 0x89, 0x8B, 0xC7, 0xAB }; static unsigned int mw64[] = {}; #else /* not __i386__ */ static unsigned char prefix_codes[] = { @@ -63,20 +63,20 @@ static unsigned char prefix_codes[] = { static unsigned int reg_rop[] = { 0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F }; -static unsigned int reg_wop[] = { 0x88, 0x89 }; +static unsigned int reg_wop[] = { 0x88, 0x89, 0xAA, 0xAB }; static unsigned int imm_wop[] = { 0xC6, 0xC7 }; -static unsigned int rw8[] = { 0xC6, 0x88, 0x8A }; +static unsigned int rw8[] = { 0xC6, 0x88, 0x8A, 0xAA }; static unsigned int rw32[] = { - 0xC7, 0x89, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F + 0xC7, 0x89, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F, 0xAB }; /* 8 bit only */ -static unsigned int mw8[] = { 0xC6, 0x88, 0x8A, 0xB60F, 0xBE0F }; +static unsigned int mw8[] = { 0xC6, 0x88, 0x8A, 0xB60F, 0xBE0F, 0xAA }; /* 16 bit only */ static unsigned int mw16[] = { 0xB70F, 0xBF0F }; /* 16 or 32 bit */ static unsigned int mw32[] = { 0xC7 }; /* 16, 32 or 64 bit */ -static unsigned int mw64[] = { 0x89, 0x8B }; +static unsigned int mw64[] = { 0x89, 0x8B, 0xAB }; #endif /* not __i386__ */ struct prefix_bits { @@ -410,7 +410,6 @@ static unsigned long *get_reg_w32(int no, struct pt_regs *regs) unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs) { unsigned int opcode; - unsigned char mod_rm; int reg; unsigned char *p; struct prefix_bits prf; @@ -437,8 +436,13 @@ unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs) goto err; do_work: - mod_rm = *p; - reg = ((mod_rm >> 3) & 0x7) | (prf.rexr << 3); + /* for STOS, source register is fixed */ + if (opcode == 0xAA || opcode == 0xAB) { + reg = arg_AX; + } else { + unsigned char mod_rm = *p; + reg = ((mod_rm >> 3) & 0x7) | (prf.rexr << 3); + } switch (get_ins_reg_width(ins_addr)) { case 1: return *get_reg_w8(reg, prf.rex, regs); diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index 8565d944f7cf..38868adf07ea 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -90,6 +90,27 @@ static void do_test(unsigned long size) iounmap(p); } +/* + * Tests how mmiotrace behaves in face of multiple ioremap / iounmaps in + * a short time. We had a bug in deferred freeing procedure which tried + * to free this region multiple times (ioremap can reuse the same address + * for many mappings). + */ +static void do_test_bulk_ioremapping(void) +{ + void __iomem *p; + int i; + + for (i = 0; i < 10; ++i) { + p = ioremap_nocache(mmio_address, PAGE_SIZE); + if (p) + iounmap(p); + } + + /* Force freeing. If it will crash we will know why. */ + synchronize_rcu(); +} + static int __init init(void) { unsigned long size = (read_far) ? (8 << 20) : (16 << 10); @@ -104,6 +125,7 @@ static int __init init(void) "and writing 16 kB of rubbish in there.\n", size >> 10, mmio_address); do_test(size); + do_test_bulk_ioremapping(); pr_info("All done.\n"); return 0; } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 426f3a1a64d3..c03f14ab6667 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -278,11 +278,9 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) static void do_flush_tlb_all(void *info) { - unsigned long cpu = smp_processor_id(); - __flush_tlb_all(); if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) - leave_mm(cpu); + leave_mm(smp_processor_id()); } void flush_tlb_all(void) diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index b28d2f1253bb..1ba67dc8006a 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -634,6 +634,18 @@ static int __init ppro_init(char **cpu_type) if (force_arch_perfmon && cpu_has_arch_perfmon) return 0; + /* + * Documentation on identifying Intel processors by CPU family + * and model can be found in the Intel Software Developer's + * Manuals (SDM): + * + * http://www.intel.com/products/processor/manuals/ + * + * As of May 2010 the documentation for this was in the: + * "Intel 64 and IA-32 Architectures Software Developer's + * Manual Volume 3B: System Programming Guide", "Table B-1 + * CPUID Signature Values of DisplayFamily_DisplayModel". + */ switch (cpu_model) { case 0 ... 2: *cpu_type = "i386/ppro"; @@ -655,12 +667,12 @@ static int __init ppro_init(char **cpu_type) case 15: case 23: *cpu_type = "i386/core_2"; break; + case 0x1a: case 0x2e: - case 26: spec = &op_arch_perfmon_spec; *cpu_type = "i386/core_i7"; break; - case 28: + case 0x1c: *cpu_type = "i386/atom"; break; default: diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 6b4ffedb93c9..4a2afa1bac51 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -120,7 +120,8 @@ $(obj)/vdso32-syms.lds: $(vdso32.so-y:%=$(obj)/vdso32-%-syms.lds) FORCE quiet_cmd_vdso = VDSO $@ cmd_vdso = $(CC) -nostdlib -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ - -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) + -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ + sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) GCOV_PROFILE := n diff --git a/arch/x86/vdso/checkundef.sh b/arch/x86/vdso/checkundef.sh new file mode 100755 index 000000000000..7ee90a9b549d --- /dev/null +++ b/arch/x86/vdso/checkundef.sh @@ -0,0 +1,10 @@ +#!/bin/sh +nm="$1" +file="$2" +$nm "$file" | grep '^ *U' > /dev/null 2>&1 +if [ $? -eq 1 ]; then + exit 0 +else + echo "$file: undefined symbols found" >&2 + exit 1 +fi diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 02b442e92007..36df991985b2 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -374,7 +374,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) #ifdef CONFIG_X86_64 -__initcall(sysenter_setup); +subsys_initcall(sysenter_setup); #ifdef CONFIG_SYSCTL /* Register vsyscall32 into the ABI table */ diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index ac74869b8140..43456ee17692 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -74,7 +74,7 @@ static int __init init_vdso_vars(void) vdso_enabled = 0; return -ENOMEM; } -__initcall(init_vdso_vars); +subsys_initcall(init_vdso_vars); struct linux_binprm; diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index b83e119fbeb0..68128a1b401a 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -13,6 +13,11 @@ config XEN kernel to boot in a paravirtualized environment under the Xen hypervisor. +config XEN_PVHVM + def_bool y + depends on XEN + depends on X86_LOCAL_APIC + config XEN_MAX_DOMAIN_MEMORY int "Maximum allowed size of a domain in gigabytes" default 8 if X86_32 diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3bb4fc21f4f2..930954685980 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -12,7 +12,7 @@ CFLAGS_mmu.o := $(nostackp) obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ - grant-table.o suspend.o + grant-table.o suspend.o platform-pci-unplug.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 65d8d79b46a8..d4ff5e83621d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -11,6 +11,7 @@ * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/smp.h> @@ -35,8 +36,10 @@ #include <xen/interface/version.h> #include <xen/interface/physdev.h> #include <xen/interface/vcpu.h> +#include <xen/interface/memory.h> #include <xen/features.h> #include <xen/page.h> +#include <xen/hvm.h> #include <xen/hvc-console.h> #include <asm/paravirt.h> @@ -55,7 +58,9 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/reboot.h> +#include <asm/setup.h> #include <asm/stackprotector.h> +#include <asm/hypervisor.h> #include "xen-ops.h" #include "mmu.h" @@ -76,6 +81,10 @@ struct shared_info xen_dummy_shared_info; void *xen_initial_gdt; +RESERVE_BRK(shared_info_page_brk, PAGE_SIZE); +__read_mostly int xen_have_vector_callback; +EXPORT_SYMBOL_GPL(xen_have_vector_callback); + /* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. @@ -97,6 +106,14 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; */ static int have_vcpu_info_placement = 1; +static void clamp_max_cpus(void) +{ +#ifdef CONFIG_SMP + if (setup_max_cpus > MAX_VIRT_CPUS) + setup_max_cpus = MAX_VIRT_CPUS; +#endif +} + static void xen_vcpu_setup(int cpu) { struct vcpu_register_vcpu_info info; @@ -104,13 +121,17 @@ static void xen_vcpu_setup(int cpu) struct vcpu_info *vcpup; BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); - per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; - if (!have_vcpu_info_placement) - return; /* already tested, not available */ + if (cpu < MAX_VIRT_CPUS) + per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; - vcpup = &per_cpu(xen_vcpu_info, cpu); + if (!have_vcpu_info_placement) { + if (cpu >= MAX_VIRT_CPUS) + clamp_max_cpus(); + return; + } + vcpup = &per_cpu(xen_vcpu_info, cpu); info.mfn = arbitrary_virt_to_mfn(vcpup); info.offset = offset_in_page(vcpup); @@ -125,6 +146,7 @@ static void xen_vcpu_setup(int cpu) if (err) { printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err); have_vcpu_info_placement = 0; + clamp_max_cpus(); } else { /* This cpu is using the registered vcpu info, even if later ones fail to. */ @@ -731,7 +753,6 @@ static void set_xen_basic_apic_ops(void) #endif - static void xen_clts(void) { struct multicall_space mcs; @@ -926,10 +947,6 @@ static const struct pv_init_ops xen_init_ops __initdata = { .patch = xen_patch, }; -static const struct pv_time_ops xen_time_ops __initdata = { - .sched_clock = xen_sched_clock, -}; - static const struct pv_cpu_ops xen_cpu_ops __initdata = { .cpuid = xen_cpuid, @@ -1028,6 +1045,23 @@ static void xen_crash_shutdown(struct pt_regs *regs) xen_reboot(SHUTDOWN_crash); } +static int +xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) +{ + xen_reboot(SHUTDOWN_crash); + return NOTIFY_DONE; +} + +static struct notifier_block xen_panic_block = { + .notifier_call= xen_panic_event, +}; + +int xen_panic_handler_init(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &xen_panic_block); + return 0; +} + static const struct machine_ops __initdata xen_machine_ops = { .restart = xen_restart, .halt = xen_machine_halt, @@ -1067,7 +1101,6 @@ asmlinkage void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; pv_init_ops = xen_init_ops; - pv_time_ops = xen_time_ops; pv_cpu_ops = xen_cpu_ops; pv_apic_ops = xen_apic_ops; @@ -1075,13 +1108,7 @@ asmlinkage void __init xen_start_kernel(void) x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; - x86_init.timers.timer_init = xen_time_init; - x86_init.timers.setup_percpu_clockev = x86_init_noop; - x86_cpuinit.setup_percpu_clockev = x86_init_noop; - - x86_platform.calibrate_tsc = xen_tsc_khz; - x86_platform.get_wallclock = xen_get_wallclock; - x86_platform.set_wallclock = xen_set_wallclock; + xen_init_time_ops(); /* * Set up some pagetable state before starting to set any ptes. @@ -1206,3 +1233,139 @@ asmlinkage void __init xen_start_kernel(void) x86_64_start_reservations((char *)__pa_symbol(&boot_params)); #endif } + +static uint32_t xen_cpuid_base(void) +{ + uint32_t base, eax, ebx, ecx, edx; + char signature[13]; + + for (base = 0x40000000; base < 0x40010000; base += 0x100) { + cpuid(base, &eax, &ebx, &ecx, &edx); + *(uint32_t *)(signature + 0) = ebx; + *(uint32_t *)(signature + 4) = ecx; + *(uint32_t *)(signature + 8) = edx; + signature[12] = 0; + + if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2)) + return base; + } + + return 0; +} + +static int init_hvm_pv_info(int *major, int *minor) +{ + uint32_t eax, ebx, ecx, edx, pages, msr, base; + u64 pfn; + + base = xen_cpuid_base(); + cpuid(base + 1, &eax, &ebx, &ecx, &edx); + + *major = eax >> 16; + *minor = eax & 0xffff; + printk(KERN_INFO "Xen version %d.%d.\n", *major, *minor); + + cpuid(base + 2, &pages, &msr, &ecx, &edx); + + pfn = __pa(hypercall_page); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + + xen_setup_features(); + + pv_info = xen_info; + pv_info.kernel_rpl = 0; + + xen_domain_type = XEN_HVM_DOMAIN; + + return 0; +} + +void xen_hvm_init_shared_info(void) +{ + int cpu; + struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + + if (!shared_info_page) + shared_info_page = (struct shared_info *) + extend_brk(PAGE_SIZE, PAGE_SIZE); + xatp.domid = DOMID_SELF; + xatp.idx = 0; + xatp.space = XENMAPSPACE_shared_info; + xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; + if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) + BUG(); + + HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; + + /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info + * page, we use it in the event channel upcall and in some pvclock + * related functions. We don't need the vcpu_info placement + * optimizations because we don't use any pv_mmu or pv_irq op on + * HVM. + * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_init_shared_info is run at resume time too and + * in that case multiple vcpus might be online. */ + for_each_online_cpu(cpu) { + per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + } +} + +#ifdef CONFIG_XEN_PVHVM +static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + switch (action) { + case CPU_UP_PREPARE: + per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata xen_hvm_cpu_notifier = { + .notifier_call = xen_hvm_cpu_notify, +}; + +static void __init xen_hvm_guest_init(void) +{ + int r; + int major, minor; + + r = init_hvm_pv_info(&major, &minor); + if (r < 0) + return; + + xen_hvm_init_shared_info(); + + if (xen_feature(XENFEAT_hvm_callback_vector)) + xen_have_vector_callback = 1; + register_cpu_notifier(&xen_hvm_cpu_notifier); + xen_unplug_emulated_devices(); + have_vcpu_info_placement = 0; + x86_init.irqs.intr_init = xen_init_IRQ; + xen_hvm_init_time_ops(); + xen_hvm_init_mmu_ops(); +} + +static bool __init xen_hvm_platform(void) +{ + if (xen_pv_domain()) + return false; + + if (!xen_cpuid_base()) + return false; + + return true; +} + +const __refconst struct hypervisor_x86 x86_hyper_xen_hvm = { + .name = "Xen HVM", + .detect = xen_hvm_platform, + .init_platform = xen_hvm_guest_init, +}; +EXPORT_SYMBOL(x86_hyper_xen_hvm); +#endif diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 914f04695ce5..413b19b3d0fe 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -58,6 +58,7 @@ #include <xen/page.h> #include <xen/interface/xen.h> +#include <xen/interface/hvm/hvm_op.h> #include <xen/interface/version.h> #include <xen/hvc-console.h> @@ -1941,6 +1942,40 @@ void __init xen_init_mmu_ops(void) pv_mmu_ops = xen_mmu_ops; } +#ifdef CONFIG_XEN_PVHVM +static void xen_hvm_exit_mmap(struct mm_struct *mm) +{ + struct xen_hvm_pagetable_dying a; + int rc; + + a.domid = DOMID_SELF; + a.gpa = __pa(mm->pgd); + rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a); + WARN_ON_ONCE(rc < 0); +} + +static int is_pagetable_dying_supported(void) +{ + struct xen_hvm_pagetable_dying a; + int rc = 0; + + a.domid = DOMID_SELF; + a.gpa = 0x00; + rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a); + if (rc < 0) { + printk(KERN_DEBUG "HVMOP_pagetable_dying not supported\n"); + return 0; + } + return 1; +} + +void __init xen_hvm_init_mmu_ops(void) +{ + if (is_pagetable_dying_supported()) + pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap; +} +#endif + #ifdef CONFIG_XEN_DEBUG_FS static struct dentry *d_mmu_debug; diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 5fe6bc7f5ecf..fa938c4aa2f7 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -60,4 +60,5 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, unsigned long xen_read_cr2_direct(void); extern void xen_init_mmu_ops(void); +extern void xen_hvm_init_mmu_ops(void); #endif /* _XEN_MMU_H */ diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c new file mode 100644 index 000000000000..554c002a1e1a --- /dev/null +++ b/arch/x86/xen/platform-pci-unplug.c @@ -0,0 +1,137 @@ +/****************************************************************************** + * platform-pci-unplug.c + * + * Xen platform PCI device driver + * Copyright (c) 2010, Citrix + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> + +#include <xen/platform_pci.h> + +#define XEN_PLATFORM_ERR_MAGIC -1 +#define XEN_PLATFORM_ERR_PROTOCOL -2 +#define XEN_PLATFORM_ERR_BLACKLIST -3 + +/* store the value of xen_emul_unplug after the unplug is done */ +int xen_platform_pci_unplug; +EXPORT_SYMBOL_GPL(xen_platform_pci_unplug); +#ifdef CONFIG_XEN_PVHVM +static int xen_emul_unplug; + +static int __init check_platform_magic(void) +{ + short magic; + char protocol; + + magic = inw(XEN_IOPORT_MAGIC); + if (magic != XEN_IOPORT_MAGIC_VAL) { + printk(KERN_ERR "Xen Platform PCI: unrecognised magic value\n"); + return XEN_PLATFORM_ERR_MAGIC; + } + + protocol = inb(XEN_IOPORT_PROTOVER); + + printk(KERN_DEBUG "Xen Platform PCI: I/O protocol version %d\n", + protocol); + + switch (protocol) { + case 1: + outw(XEN_IOPORT_LINUX_PRODNUM, XEN_IOPORT_PRODNUM); + outl(XEN_IOPORT_LINUX_DRVVER, XEN_IOPORT_DRVVER); + if (inw(XEN_IOPORT_MAGIC) != XEN_IOPORT_MAGIC_VAL) { + printk(KERN_ERR "Xen Platform: blacklisted by host\n"); + return XEN_PLATFORM_ERR_BLACKLIST; + } + break; + default: + printk(KERN_WARNING "Xen Platform PCI: unknown I/O protocol version"); + return XEN_PLATFORM_ERR_PROTOCOL; + } + + return 0; +} + +void __init xen_unplug_emulated_devices(void) +{ + int r; + + /* check the version of the xen platform PCI device */ + r = check_platform_magic(); + /* If the version matches enable the Xen platform PCI driver. + * Also enable the Xen platform PCI driver if the version is really old + * and the user told us to ignore it. */ + if (r && !(r == XEN_PLATFORM_ERR_MAGIC && + (xen_emul_unplug & XEN_UNPLUG_IGNORE))) + return; + /* Set the default value of xen_emul_unplug depending on whether or + * not the Xen PV frontends and the Xen platform PCI driver have + * been compiled for this kernel (modules or built-in are both OK). */ + if (!xen_emul_unplug) { + if (xen_must_unplug_nics()) { + printk(KERN_INFO "Netfront and the Xen platform PCI driver have " + "been compiled for this kernel: unplug emulated NICs.\n"); + xen_emul_unplug |= XEN_UNPLUG_ALL_NICS; + } + if (xen_must_unplug_disks()) { + printk(KERN_INFO "Blkfront and the Xen platform PCI driver have " + "been compiled for this kernel: unplug emulated disks.\n" + "You might have to change the root device\n" + "from /dev/hd[a-d] to /dev/xvd[a-d]\n" + "in your root= kernel command line option\n"); + xen_emul_unplug |= XEN_UNPLUG_ALL_IDE_DISKS; + } + } + /* Now unplug the emulated devices */ + if (!(xen_emul_unplug & XEN_UNPLUG_IGNORE)) + outw(xen_emul_unplug, XEN_IOPORT_UNPLUG); + xen_platform_pci_unplug = xen_emul_unplug; +} + +static int __init parse_xen_emul_unplug(char *arg) +{ + char *p, *q; + int l; + + for (p = arg; p; p = q) { + q = strchr(p, ','); + if (q) { + l = q - p; + q++; + } else { + l = strlen(p); + } + if (!strncmp(p, "all", l)) + xen_emul_unplug |= XEN_UNPLUG_ALL; + else if (!strncmp(p, "ide-disks", l)) + xen_emul_unplug |= XEN_UNPLUG_ALL_IDE_DISKS; + else if (!strncmp(p, "aux-ide-disks", l)) + xen_emul_unplug |= XEN_UNPLUG_AUX_IDE_DISKS; + else if (!strncmp(p, "nics", l)) + xen_emul_unplug |= XEN_UNPLUG_ALL_NICS; + else if (!strncmp(p, "ignore", l)) + xen_emul_unplug |= XEN_UNPLUG_IGNORE; + else + printk(KERN_WARNING "unrecognised option '%s' " + "in parameter 'xen_emul_unplug'\n", p); + } + return 0; +} +early_param("xen_emul_unplug", parse_xen_emul_unplug); +#endif diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ad0047f47cd4..328b00305426 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -20,6 +20,7 @@ #include <xen/page.h> #include <xen/interface/callback.h> #include <xen/interface/physdev.h> +#include <xen/interface/memory.h> #include <xen/features.h> #include "xen-ops.h" @@ -32,6 +33,73 @@ extern void xen_sysenter_target(void); extern void xen_syscall_target(void); extern void xen_syscall32_target(void); +static unsigned long __init xen_release_chunk(phys_addr_t start_addr, + phys_addr_t end_addr) +{ + struct xen_memory_reservation reservation = { + .address_bits = 0, + .extent_order = 0, + .domid = DOMID_SELF + }; + unsigned long start, end; + unsigned long len = 0; + unsigned long pfn; + int ret; + + start = PFN_UP(start_addr); + end = PFN_DOWN(end_addr); + + if (end <= start) + return 0; + + printk(KERN_INFO "xen_release_chunk: looking at area pfn %lx-%lx: ", + start, end); + for(pfn = start; pfn < end; pfn++) { + unsigned long mfn = pfn_to_mfn(pfn); + + /* Make sure pfn exists to start with */ + if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn) + continue; + + set_xen_guest_handle(reservation.extent_start, &mfn); + reservation.nr_extents = 1; + + ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, + &reservation); + WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n", + start, end, ret); + if (ret == 1) { + set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + len++; + } + } + printk(KERN_CONT "%ld pages freed\n", len); + + return len; +} + +static unsigned long __init xen_return_unused_memory(unsigned long max_pfn, + const struct e820map *e820) +{ + phys_addr_t max_addr = PFN_PHYS(max_pfn); + phys_addr_t last_end = 0; + unsigned long released = 0; + int i; + + for (i = 0; i < e820->nr_map && last_end < max_addr; i++) { + phys_addr_t end = e820->map[i].addr; + end = min(max_addr, end); + + released += xen_release_chunk(last_end, end); + last_end = e820->map[i].addr + e820->map[i].size; + } + + if (last_end < max_addr) + released += xen_release_chunk(last_end, max_addr); + + printk(KERN_INFO "released %ld pages of unused memory\n", released); + return released; +} /** * machine_specific_memory_setup - Hook for machine specific memory setup. @@ -67,6 +135,8 @@ char * __init xen_memory_setup(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + xen_return_unused_memory(xen_start_info->nr_pages, &e820); + return "Xen"; } @@ -156,6 +226,8 @@ void __init xen_arch_setup(void) struct physdev_set_iopl set_iopl; int rc; + xen_panic_handler_init(); + HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index a29693fd3138..25f232b18a82 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -394,6 +394,8 @@ static void stop_self(void *v) load_cr3(swapper_pg_dir); /* should set up a minimal gdt */ + set_cpu_online(cpu, false); + HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL); BUG(); } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index a9c661108034..1d789d56877c 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -26,6 +26,18 @@ void xen_pre_suspend(void) BUG(); } +void xen_hvm_post_suspend(int suspend_cancelled) +{ + int cpu; + xen_hvm_init_shared_info(); + xen_callback_vector(); + if (xen_feature(XENFEAT_hvm_safe_pvclock)) { + for_each_online_cpu(cpu) { + xen_setup_runstate_info(cpu); + } + } +} + void xen_post_suspend(int suspend_cancelled) { xen_build_mfn_list_list(); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index b3c6c59ed302..1a5353a753fc 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -20,6 +20,7 @@ #include <asm/xen/hypercall.h> #include <xen/events.h> +#include <xen/features.h> #include <xen/interface/xen.h> #include <xen/interface/vcpu.h> @@ -155,47 +156,8 @@ static void do_stolen_accounting(void) account_idle_ticks(ticks); } -/* - * Xen sched_clock implementation. Returns the number of unstolen - * nanoseconds, which is nanoseconds the VCPU spent in RUNNING+BLOCKED - * states. - */ -unsigned long long xen_sched_clock(void) -{ - struct vcpu_runstate_info state; - cycle_t now; - u64 ret; - s64 offset; - - /* - * Ideally sched_clock should be called on a per-cpu basis - * anyway, so preempt should already be disabled, but that's - * not current practice at the moment. - */ - preempt_disable(); - - now = xen_clocksource_read(); - - get_runstate_snapshot(&state); - - WARN_ON(state.state != RUNSTATE_running); - - offset = now - state.state_entry_time; - if (offset < 0) - offset = 0; - - ret = state.time[RUNSTATE_blocked] + - state.time[RUNSTATE_running] + - offset; - - preempt_enable(); - - return ret; -} - - /* Get the TSC speed from Xen */ -unsigned long xen_tsc_khz(void) +static unsigned long xen_tsc_khz(void) { struct pvclock_vcpu_time_info *info = &HYPERVISOR_shared_info->vcpu_info[0].time; @@ -230,7 +192,7 @@ static void xen_read_wallclock(struct timespec *ts) put_cpu_var(xen_vcpu); } -unsigned long xen_get_wallclock(void) +static unsigned long xen_get_wallclock(void) { struct timespec ts; @@ -238,7 +200,7 @@ unsigned long xen_get_wallclock(void) return ts.tv_sec; } -int xen_set_wallclock(unsigned long now) +static int xen_set_wallclock(unsigned long now) { /* do nothing for domU */ return -1; @@ -473,7 +435,11 @@ void xen_timer_resume(void) } } -__init void xen_time_init(void) +static const struct pv_time_ops xen_time_ops __initdata = { + .sched_clock = xen_clocksource_read, +}; + +static __init void xen_time_init(void) { int cpu = smp_processor_id(); struct timespec tp; @@ -497,3 +463,47 @@ __init void xen_time_init(void) xen_setup_timer(cpu); xen_setup_cpu_clockevents(); } + +__init void xen_init_time_ops(void) +{ + pv_time_ops = xen_time_ops; + + x86_init.timers.timer_init = xen_time_init; + x86_init.timers.setup_percpu_clockev = x86_init_noop; + x86_cpuinit.setup_percpu_clockev = x86_init_noop; + + x86_platform.calibrate_tsc = xen_tsc_khz; + x86_platform.get_wallclock = xen_get_wallclock; + x86_platform.set_wallclock = xen_set_wallclock; +} + +#ifdef CONFIG_XEN_PVHVM +static void xen_hvm_setup_cpu_clockevents(void) +{ + int cpu = smp_processor_id(); + xen_setup_runstate_info(cpu); + xen_setup_timer(cpu); + xen_setup_cpu_clockevents(); +} + +__init void xen_hvm_init_time_ops(void) +{ + /* vector callback is needed otherwise we cannot receive interrupts + * on cpu > 0 */ + if (!xen_have_vector_callback && num_present_cpus() > 1) + return; + if (!xen_feature(XENFEAT_hvm_safe_pvclock)) { + printk(KERN_INFO "Xen doesn't support pvclock on HVM," + "disable pv timer\n"); + return; + } + + pv_time_ops = xen_time_ops; + x86_init.timers.setup_percpu_clockev = xen_time_init; + x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents; + + x86_platform.calibrate_tsc = xen_tsc_khz; + x86_platform.get_wallclock = xen_get_wallclock; + x86_platform.set_wallclock = xen_set_wallclock; +} +#endif diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index f9153a300bce..7c8ab86163e9 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -38,6 +38,10 @@ void xen_enable_sysenter(void); void xen_enable_syscall(void); void xen_vcpu_restore(void); +void xen_callback_vector(void); +void xen_hvm_init_shared_info(void); +void __init xen_unplug_emulated_devices(void); + void __init xen_build_dynamic_phys_to_machine(void); void xen_init_irq_ops(void); @@ -46,11 +50,8 @@ void xen_setup_runstate_info(int cpu); void xen_teardown_timer(int cpu); cycle_t xen_clocksource_read(void); void xen_setup_cpu_clockevents(void); -unsigned long xen_tsc_khz(void); -void __init xen_time_init(void); -unsigned long xen_get_wallclock(void); -int xen_set_wallclock(unsigned long time); -unsigned long long xen_sched_clock(void); +void __init xen_init_time_ops(void); +void __init xen_hvm_init_time_ops(void); irqreturn_t xen_debug_interrupt(int irq, void *dev_id); @@ -101,4 +102,6 @@ void xen_sysret32(void); void xen_sysret64(void); void xen_adjust_exception_frame(void); +extern int xen_panic_handler_init(void); + #endif /* XEN_OPS_H */ diff --git a/arch/xtensa/include/asm/local64.h b/arch/xtensa/include/asm/local64.h new file mode 100644 index 000000000000..36c93b5cc239 --- /dev/null +++ b/arch/xtensa/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> |