Merge branch 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (38 commits)
  x86: Move get/set_wallclock to x86_platform_ops
  x86: platform: Fix section annotations
  x86: apic namespace cleanup
  x86: Distangle ioapic and i8259
  x86: Add Moorestown early detection
  x86: Add hardware_subarch ID for Moorestown
  x86: Add early platform detection
  x86: Move tsc_init to late_time_init
  x86: Move tsc_calibration to x86_init_ops
  x86: Replace the now identical time_32/64.c by time.c
  x86: time_32/64.c unify profile_pc
  x86: Move calibrate_cpu to tsc.c
  x86: Make timer setup and global variables the same in time_32/64.c
  x86: Remove mca bus ifdef from timer interrupt
  x86: Simplify timer_ack magic in time_32.c
  x86: Prepare unification of time_32/64.c
  x86: Remove do_timer hook
  x86: Add timer_init to x86_init_ops
  x86: Move percpu clockevents setup to x86_init_ops
  x86: Move xen_post_allocator_init into xen_pagetable_setup_done
  ...

Fix up conflicts in arch/x86/include/asm/io_apic.h

Documentation/x86/boot.txt

@@ -599,6 +599,7 @@ Protocol:	2.07+
   0x00000000	The default x86/PC environment
   0x00000001	lguest
   0x00000002	Xen
+  0x00000003	Moorestown MID
 
 Field name:	hardware_subarch_data
 Type:		write (subarch-dependent)

arch/x86/Kconfig

@@ -325,6 +325,7 @@ config X86_EXTENDED_PLATFORM
 		SGI 320/540 (Visual Workstation)
 		Summit/EXA (IBM x440)
 		Unisys ES7000 IA32 series
+		Moorestown MID devices
 
 	  If you have one of these systems, or if you want to build a
 	  generic distribution kernel, say Y here - otherwise say N.
@@ -384,6 +385,18 @@ config X86_ELAN
 
 	  If unsure, choose "PC-compatible" instead.
 
+config X86_MRST
+       bool "Moorestown MID platform"
+	depends on X86_32
+	depends on X86_EXTENDED_PLATFORM
+	---help---
+	  Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin
+	  Internet Device(MID) platform. Moorestown consists of two chips:
+	  Lincroft (CPU core, graphics, and memory controller) and Langwell IOH.
+	  Unlike standard x86 PCs, Moorestown does not have many legacy devices
+	  nor standard legacy replacement devices/features. e.g. Moorestown does
+	  not contain i8259, i8254, HPET, legacy BIOS, most of the io ports.
+
 config X86_RDC321X
 	bool "RDC R-321x SoC"
 	depends on X86_32

arch/x86/include/asm/apic.h

@@ -70,9 +70,6 @@ static inline void default_inquire_remote_apic(int apicid)
  */
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
-#else
-#define setup_boot_clock setup_boot_APIC_clock
-#define setup_secondary_clock setup_secondary_APIC_clock
 #endif
 
 #ifdef CONFIG_X86_64
@@ -252,6 +249,8 @@ static inline void lapic_shutdown(void) { }
 static inline void init_apic_mappings(void) { }
 static inline void disable_local_APIC(void) { }
 static inline void apic_disable(void) { }
+# define setup_boot_APIC_clock x86_init_noop
+# define setup_secondary_APIC_clock x86_init_noop
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_64
@@ -300,7 +299,7 @@ struct apic {
 	int (*cpu_present_to_apicid)(int mps_cpu);
 	physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
 	void (*setup_portio_remap)(void);
-	int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
+	int (*check_phys_apicid_present)(int phys_apicid);
 	void (*enable_apic_mode)(void);
 	int (*phys_pkg_id)(int cpuid_apic, int index_msb);
 
@@ -434,7 +433,7 @@ extern struct apic apic_x2apic_uv_x;
 DECLARE_PER_CPU(int, x2apic_extra_bits);
 
 extern int default_cpu_present_to_apicid(int mps_cpu);
-extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid);
+extern int default_check_phys_apicid_present(int phys_apicid);
 #endif
 
 static inline void default_wait_for_init_deassert(atomic_t *deassert)
@@ -550,9 +549,9 @@ static inline int __default_cpu_present_to_apicid(int mps_cpu)
 }
 
 static inline int
-__default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+__default_check_phys_apicid_present(int phys_apicid)
 {
-	return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
+	return physid_isset(phys_apicid, phys_cpu_present_map);
 }
 
 #ifdef CONFIG_X86_32
@@ -562,13 +561,13 @@ static inline int default_cpu_present_to_apicid(int mps_cpu)
 }
 
 static inline int
-default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+default_check_phys_apicid_present(int phys_apicid)
 {
-	return __default_check_phys_apicid_present(boot_cpu_physical_apicid);
+	return __default_check_phys_apicid_present(phys_apicid);
 }
 #else
 extern int default_cpu_present_to_apicid(int mps_cpu);
-extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid);
+extern int default_check_phys_apicid_present(int phys_apicid);
 #endif
 
 static inline physid_mask_t default_apicid_to_cpu_present(int phys_apicid)

arch/x86/include/asm/bootparam.h

@@ -110,4 +110,14 @@ struct boot_params {
 	__u8  _pad9[276];				/* 0xeec */
 } __attribute__((packed));
 
+enum {
+	X86_SUBARCH_PC = 0,
+	X86_SUBARCH_LGUEST,
+	X86_SUBARCH_XEN,
+	X86_SUBARCH_MRST,
+	X86_NR_SUBARCHS,
+};
+
+
+
 #endif /* _ASM_X86_BOOTPARAM_H */

arch/x86/include/asm/do_timer.h

@@ -1,16 +0,0 @@
-/* defines for inline arch setup functions */
-#include <linux/clockchips.h>
-
-#include <asm/i8259.h>
-#include <asm/i8253.h>
-
-/**
- * do_timer_interrupt_hook - hook into timer tick
- *
- * Call the pit clock event handler. see asm/i8253.h
- **/
-
-static inline void do_timer_interrupt_hook(void)
-{
-	global_clock_event->event_handler(global_clock_event);
-}

arch/x86/include/asm/e820.h

@@ -126,8 +126,6 @@ extern void e820_reserve_resources(void);
 extern void e820_reserve_resources_late(void);
 extern void setup_memory_map(void);
 extern char *default_machine_specific_memory_setup(void);
-extern char *machine_specific_memory_setup(void);
-extern char *memory_setup(void);
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 

arch/x86/include/asm/hypervisor.h

@@ -20,7 +20,7 @@
 #ifndef ASM_X86__HYPERVISOR_H
 #define ASM_X86__HYPERVISOR_H
 
-extern unsigned long get_hypervisor_tsc_freq(void);
 extern void init_hypervisor(struct cpuinfo_x86 *c);
+extern void init_hypervisor_platform(void);
 
 #endif

arch/x86/include/asm/io_apic.h

@@ -143,6 +143,8 @@ extern int noioapicreroute;
 /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
 extern int timer_through_8259;
 
+extern void io_apic_disable_legacy(void);
+
 /*
  * If we use the IO-APIC for IRQ routing, disable automatic
  * assignment of PCI IRQ's.
@@ -176,6 +178,7 @@ extern int setup_ioapic_entry(int apic, int irq,
 			      int polarity, int vector, int pin);
 extern void ioapic_write_entry(int apic, int pin,
 			       struct IO_APIC_route_entry e);
+extern void setup_ioapic_ids_from_mpc(void);
 
 struct mp_ioapic_gsi{
 	int gsi_base;
@@ -187,12 +190,14 @@ int mp_find_ioapic_pin(int ioapic, int gsi);
 void __init mp_register_ioapic(int id, u32 address, u32 gsi_base);
 
 #else  /* !CONFIG_X86_IO_APIC */
+
 #define io_apic_assign_pci_irqs 0
+#define setup_ioapic_ids_from_mpc x86_init_noop
 static const int timer_through_8259 = 0;
 static inline void ioapic_init_mappings(void)	{ }
 static inline void ioapic_insert_resources(void) { }
-
 static inline void probe_nr_irqs_gsi(void)	{ }
+
 #endif
 
 #endif /* _ASM_X86_IO_APIC_H */

arch/x86/include/asm/irq.h

@@ -37,7 +37,6 @@ extern void fixup_irqs(void);
 #endif
 
 extern void (*generic_interrupt_extension)(void);
-extern void init_IRQ(void);
 extern void native_init_IRQ(void);
 extern bool handle_irq(unsigned irq, struct pt_regs *regs);
 
@@ -47,4 +46,6 @@ extern unsigned int do_IRQ(struct pt_regs *regs);
 extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
 extern int vector_used_by_percpu_irq(unsigned int vector);
 
+extern void init_ISA_irqs(void);
+
 #endif /* _ASM_X86_IRQ_H */

arch/x86/include/asm/mpspec.h

@@ -4,6 +4,7 @@
 #include <linux/init.h>
 
 #include <asm/mpspec_def.h>
+#include <asm/x86_init.h>
 
 extern int apic_version[MAX_APICS];
 extern int pic_mode;
@@ -41,9 +42,6 @@ extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
 
 #endif /* CONFIG_X86_64 */
 
-extern void early_find_smp_config(void);
-extern void early_get_smp_config(void);
-
 #if defined(CONFIG_MCA) || defined(CONFIG_EISA)
 extern int mp_bus_id_to_type[MAX_MP_BUSSES];
 #endif
@@ -52,20 +50,55 @@ extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 
 extern unsigned int boot_cpu_physical_apicid;
 extern unsigned int max_physical_apicid;
-extern int smp_found_config;
 extern int mpc_default_type;
 extern unsigned long mp_lapic_addr;
 
-extern void get_smp_config(void);
+#ifdef CONFIG_X86_LOCAL_APIC
+extern int smp_found_config;
+#else
+# define smp_found_config 0
+#endif
+
+static inline void get_smp_config(void)
+{
+	x86_init.mpparse.get_smp_config(0);
+}
+
+static inline void early_get_smp_config(void)
+{
+	x86_init.mpparse.get_smp_config(1);
+}
+
+static inline void find_smp_config(void)
+{
+	x86_init.mpparse.find_smp_config(1);
+}
+
+static inline void early_find_smp_config(void)
+{
+	x86_init.mpparse.find_smp_config(0);
+}
 
 #ifdef CONFIG_X86_MPPARSE
-extern void find_smp_config(void);
 extern void early_reserve_e820_mpc_new(void);
 extern int enable_update_mptable;
+extern int default_mpc_apic_id(struct mpc_cpu *m);
+extern void default_smp_read_mpc_oem(struct mpc_table *mpc);
+# ifdef CONFIG_X86_IO_APIC
+extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str);
+# else
+#  define default_mpc_oem_bus_info NULL
+# endif
+extern void default_find_smp_config(unsigned int reserve);
+extern void default_get_smp_config(unsigned int early);
 #else
-static inline void find_smp_config(void) { }
 static inline void early_reserve_e820_mpc_new(void) { }
 #define enable_update_mptable 0
+#define default_mpc_apic_id NULL
+#define default_smp_read_mpc_oem NULL
+#define default_mpc_oem_bus_info NULL
+#define default_find_smp_config x86_init_uint_noop
+#define default_get_smp_config x86_init_uint_noop
 #endif
 
 void __cpuinit generic_processor_info(int apicid, int version);

arch/x86/include/asm/paravirt.h

@@ -24,22 +24,6 @@ static inline void load_sp0(struct tss_struct *tss,
 	PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread);
 }
 
-#define ARCH_SETUP			pv_init_ops.arch_setup();
-static inline unsigned long get_wallclock(void)
-{
-	return PVOP_CALL0(unsigned long, pv_time_ops.get_wallclock);
-}
-
-static inline int set_wallclock(unsigned long nowtime)
-{
-	return PVOP_CALL1(int, pv_time_ops.set_wallclock, nowtime);
-}
-
-static inline void (*choose_time_init(void))(void)
-{
-	return pv_time_ops.time_init;
-}
-
 /* The paravirtualized CPUID instruction. */
 static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
 			   unsigned int *ecx, unsigned int *edx)
@@ -245,7 +229,6 @@ static inline unsigned long long paravirt_sched_clock(void)
 {
 	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
 }
-#define calibrate_tsc() (pv_time_ops.get_tsc_khz())
 
 static inline unsigned long long paravirt_read_pmc(int counter)
 {
@@ -363,34 +346,6 @@ static inline void slow_down_io(void)
 #endif
 }
 
-#ifdef CONFIG_X86_LOCAL_APIC
-static inline void setup_boot_clock(void)
-{
-	PVOP_VCALL0(pv_apic_ops.setup_boot_clock);
-}
-
-static inline void setup_secondary_clock(void)
-{
-	PVOP_VCALL0(pv_apic_ops.setup_secondary_clock);
-}
-#endif
-
-static inline void paravirt_post_allocator_init(void)
-{
-	if (pv_init_ops.post_allocator_init)
-		(*pv_init_ops.post_allocator_init)();
-}
-
-static inline void paravirt_pagetable_setup_start(pgd_t *base)
-{
-	(*pv_mmu_ops.pagetable_setup_start)(base);
-}
-
-static inline void paravirt_pagetable_setup_done(pgd_t *base)
-{
-	(*pv_mmu_ops.pagetable_setup_done)(base);
-}
-
 #ifdef CONFIG_SMP
 static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 				    unsigned long start_esp)
@@ -948,6 +903,8 @@ static inline unsigned long __raw_local_irq_save(void)
 #undef PVOP_VCALL4
 #undef PVOP_CALL4
 
+extern void default_banner(void);
+
 #else  /* __ASSEMBLY__ */
 
 #define _PVSITE(ptype, clobbers, ops, word, algn)	\
@@ -1088,5 +1045,7 @@ static inline unsigned long __raw_local_irq_save(void)
 #endif	/* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */
-#endif /* CONFIG_PARAVIRT */
+#else  /* CONFIG_PARAVIRT */
+# define default_banner x86_init_noop
+#endif /* !CONFIG_PARAVIRT */
 #endif /* _ASM_X86_PARAVIRT_H */

arch/x86/include/asm/paravirt_types.h

@@ -78,14 +78,6 @@ struct pv_init_ops {
 	 */
 	unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
 			  unsigned long addr, unsigned len);
-
-	/* Basic arch-specific setup */
-	void (*arch_setup)(void);
-	char *(*memory_setup)(void);
-	void (*post_allocator_init)(void);
-
-	/* Print a banner to identify the environment */
-	void (*banner)(void);
 };
 
 
@@ -96,12 +88,6 @@ struct pv_lazy_ops {
 };
 
 struct pv_time_ops {
-	void (*time_init)(void);
-
-	/* Set and set time of day */
-	unsigned long (*get_wallclock)(void);
-	int (*set_wallclock)(unsigned long);
-
 	unsigned long long (*sched_clock)(void);
 	unsigned long (*get_tsc_khz)(void);
 };
@@ -203,8 +189,6 @@ struct pv_cpu_ops {
 };
 
 struct pv_irq_ops {
-	void (*init_IRQ)(void);
-
 	/*
 	 * Get/set interrupt state.  save_fl and restore_fl are only
 	 * expected to use X86_EFLAGS_IF; all other bits
@@ -229,9 +213,6 @@ struct pv_irq_ops {
 
 struct pv_apic_ops {
 #ifdef CONFIG_X86_LOCAL_APIC
-	void (*setup_boot_clock)(void);
-	void (*setup_secondary_clock)(void);
-
 	void (*startup_ipi_hook)(int phys_apicid,
 				 unsigned long start_eip,
 				 unsigned long start_esp);
@@ -239,15 +220,6 @@ struct pv_apic_ops {
 };
 
 struct pv_mmu_ops {
-	/*
-	 * Called before/after init_mm pagetable setup. setup_start
-	 * may reset %cr3, and may pre-install parts of the pagetable;
-	 * pagetable setup is expected to preserve any existing
-	 * mapping.
-	 */
-	void (*pagetable_setup_start)(pgd_t *pgd_base);
-	void (*pagetable_setup_done)(pgd_t *pgd_base);
-
 	unsigned long (*read_cr2)(void);
 	void (*write_cr2)(unsigned long);
 

arch/x86/include/asm/pgtable.h

@@ -56,16 +56,6 @@ extern struct list_head pgd_list;
 #define pte_update(mm, addr, ptep)              do { } while (0)
 #define pte_update_defer(mm, addr, ptep)        do { } while (0)
 
-static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
-{
-	native_pagetable_setup_start(base);
-}
-
-static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
-{
-	native_pagetable_setup_done(base);
-}
-
 #define pgd_val(x)	native_pgd_val(x)
 #define __pgd(x)	native_make_pgd(x)
 

arch/x86/include/asm/pgtable_types.h

@@ -299,8 +299,8 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pte);
 extern void native_pagetable_setup_start(pgd_t *base);
 extern void native_pagetable_setup_done(pgd_t *base);
 #else
-static inline void native_pagetable_setup_start(pgd_t *base) {}
-static inline void native_pagetable_setup_done(pgd_t *base) {}
+#define native_pagetable_setup_start x86_init_pgd_noop
+#define native_pagetable_setup_done  x86_init_pgd_noop
 #endif
 
 struct seq_file;

arch/x86/include/asm/setup.h

@@ -5,43 +5,6 @@
 
 #define COMMAND_LINE_SIZE 2048
 
-#ifndef __ASSEMBLY__
-
-/*
- * Any setup quirks to be performed?
- */
-struct mpc_cpu;
-struct mpc_bus;
-struct mpc_oemtable;
-
-struct x86_quirks {
-	int (*arch_pre_time_init)(void);
-	int (*arch_time_init)(void);
-	int (*arch_pre_intr_init)(void);
-	int (*arch_intr_init)(void);
-	int (*arch_trap_init)(void);
-	char * (*arch_memory_setup)(void);
-	int (*mach_get_smp_config)(unsigned int early);
-	int (*mach_find_smp_config)(unsigned int reserve);
-
-	int *mpc_record;
-	int (*mpc_apic_id)(struct mpc_cpu *m);
-	void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name);
-	void (*mpc_oem_pci_bus)(struct mpc_bus *m);
-	void (*smp_read_mpc_oem)(struct mpc_oemtable *oemtable,
-				unsigned short oemsize);
-	int (*setup_ioapic_ids)(void);
-};
-
-extern void x86_quirk_intr_init(void);
-
-extern void x86_quirk_trap_init(void);
-
-extern void x86_quirk_pre_time_init(void);
-extern void x86_quirk_time_init(void);
-
-#endif /* __ASSEMBLY__ */
-
 #ifdef __i386__
 
 #include <linux/pfn.h>
@@ -61,6 +24,7 @@ extern void x86_quirk_time_init(void);
 
 #ifndef __ASSEMBLY__
 #include <asm/bootparam.h>
+#include <asm/x86_init.h>
 
 /* Interrupt control for vSMPowered x86_64 systems */
 #ifdef CONFIG_X86_64
@@ -79,11 +43,16 @@ static inline void visws_early_detect(void) { }
 static inline int is_visws_box(void) { return 0; }
 #endif
 
-extern struct x86_quirks *x86_quirks;
 extern unsigned long saved_video_mode;
 
-#ifndef CONFIG_PARAVIRT
-#define paravirt_post_allocator_init()	do {} while (0)
+extern void reserve_standard_io_resources(void);
+extern void i386_reserve_resources(void);
+extern void setup_default_timer_irq(void);
+
+#ifdef CONFIG_X86_MRST
+extern void x86_mrst_early_setup(void);
+#else
+static inline void x86_mrst_early_setup(void) { }
 #endif
 
 #ifndef _SETUP

arch/x86/include/asm/time.h

@@ -4,60 +4,7 @@
 extern void hpet_time_init(void);
 
 #include <asm/mc146818rtc.h>
-#ifdef CONFIG_X86_32
-#include <linux/efi.h>
-
-static inline unsigned long native_get_wallclock(void)
-{
-	unsigned long retval;
-
-	if (efi_enabled)
-		retval = efi_get_time();
-	else
-		retval = mach_get_cmos_time();
-
-	return retval;
-}
-
-static inline int native_set_wallclock(unsigned long nowtime)
-{
-	int retval;
-
-	if (efi_enabled)
-		retval = efi_set_rtc_mmss(nowtime);
-	else
-		retval = mach_set_rtc_mmss(nowtime);
-
-	return retval;
-}
-
-#else
-extern void native_time_init_hook(void);
-
-static inline unsigned long native_get_wallclock(void)
-{
-	return mach_get_cmos_time();
-}
-
-static inline int native_set_wallclock(unsigned long nowtime)
-{
-	return mach_set_rtc_mmss(nowtime);
-}
-
-#endif
 
 extern void time_init(void);
 
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else /* !CONFIG_PARAVIRT */
-
-#define get_wallclock() native_get_wallclock()
-#define set_wallclock(x) native_set_wallclock(x)
-#define choose_time_init() hpet_time_init
-
-#endif /* CONFIG_PARAVIRT */
-
-extern unsigned long __init calibrate_cpu(void);
-
 #endif /* _ASM_X86_TIME_H */

arch/x86/include/asm/timer.h

@@ -8,20 +8,16 @@
 #define TICK_SIZE (tick_nsec / 1000)
 
 unsigned long long native_sched_clock(void);
-unsigned long native_calibrate_tsc(void);
+extern int recalibrate_cpu_khz(void);
 
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC)
 extern int timer_ack;
-extern irqreturn_t timer_interrupt(int irq, void *dev_id);
-#endif /* CONFIG_X86_32 */
-extern int recalibrate_cpu_khz(void);
+#else
+# define timer_ack (0)
+#endif
 
 extern int no_timer_check;
 
-#ifndef CONFIG_PARAVIRT
-#define calibrate_tsc() native_calibrate_tsc()
-#endif
-
 /* Accelerators for sched_clock()
  * convert from cycles(64bits) => nanoseconds (64bits)
  *  basic equation:

arch/x86/include/asm/tsc.h

@@ -48,7 +48,8 @@ static __always_inline cycles_t vget_cycles(void)
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
-int check_tsc_unstable(void);
+extern int check_tsc_unstable(void);
+extern unsigned long native_calibrate_tsc(void);
 
 /*
  * Boot-time check whether the TSCs are synchronized across

arch/x86/include/asm/vmware.h

@@ -20,7 +20,7 @@
 #ifndef ASM_X86__VMWARE_H
 #define ASM_X86__VMWARE_H
 
-extern unsigned long vmware_get_tsc_khz(void);
+extern void vmware_platform_setup(void);
 extern int vmware_platform(void);
 extern void vmware_set_feature_bits(struct cpuinfo_x86 *c);
 

arch/x86/include/asm/x86_init.h

@@ -0,0 +1,133 @@
+#ifndef _ASM_X86_PLATFORM_H
+#define _ASM_X86_PLATFORM_H
+
+#include <asm/pgtable_types.h>
+#include <asm/bootparam.h>
+
+struct mpc_bus;
+struct mpc_cpu;
+struct mpc_table;
+
+/**
+ * struct x86_init_mpparse - platform specific mpparse ops
+ * @mpc_record:			platform specific mpc record accounting
+ * @setup_ioapic_ids:		platform specific ioapic id override
+ * @mpc_apic_id:		platform specific mpc apic id assignment
+ * @smp_read_mpc_oem:		platform specific oem mpc table setup
+ * @mpc_oem_pci_bus:		platform specific pci bus setup (default NULL)
+ * @mpc_oem_bus_info:		platform specific mpc bus info
+ * @find_smp_config:		find the smp configuration
+ * @get_smp_config:		get the smp configuration
+ */
+struct x86_init_mpparse {
+	void (*mpc_record)(unsigned int mode);
+	void (*setup_ioapic_ids)(void);
+	int (*mpc_apic_id)(struct mpc_cpu *m);
+	void (*smp_read_mpc_oem)(struct mpc_table *mpc);
+	void (*mpc_oem_pci_bus)(struct mpc_bus *m);
+	void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name);
+	void (*find_smp_config)(unsigned int reserve);
+	void (*get_smp_config)(unsigned int early);
+};
+
+/**
+ * struct x86_init_resources - platform specific resource related ops
+ * @probe_roms:			probe BIOS roms
+ * @reserve_resources:		reserve the standard resources for the
+ *				platform
+ * @memory_setup:		platform specific memory setup
+ *
+ */
+struct x86_init_resources {
+	void (*probe_roms)(void);
+	void (*reserve_resources)(void);
+	char *(*memory_setup)(void);
+};
+
+/**
+ * struct x86_init_irqs - platform specific interrupt setup
+ * @pre_vector_init:		init code to run before interrupt vectors
+ *				are set up.
+ * @intr_init:			interrupt init code
+ * @trap_init:			platform specific trap setup
+ */
+struct x86_init_irqs {
+	void (*pre_vector_init)(void);
+	void (*intr_init)(void);
+	void (*trap_init)(void);
+};
+
+/**
+ * struct x86_init_oem - oem platform specific customizing functions
+ * @arch_setup:			platform specific architecure setup
+ * @banner:			print a platform specific banner
+ */
+struct x86_init_oem {
+	void (*arch_setup)(void);
+	void (*banner)(void);
+};
+
+/**
+ * struct x86_init_paging - platform specific paging functions
+ * @pagetable_setup_start:	platform specific pre paging_init() call
+ * @pagetable_setup_done:	platform specific post paging_init() call
+ */
+struct x86_init_paging {
+	void (*pagetable_setup_start)(pgd_t *base);
+	void (*pagetable_setup_done)(pgd_t *base);
+};
+
+/**
+ * struct x86_init_timers - platform specific timer setup
+ * @setup_perpcu_clockev:	set up the per cpu clock event device for the
+ *				boot cpu
+ * @tsc_pre_init:		platform function called before TSC init
+ * @timer_init:			initialize the platform timer (default PIT/HPET)
+ */
+struct x86_init_timers {
+	void (*setup_percpu_clockev)(void);
+	void (*tsc_pre_init)(void);
+	void (*timer_init)(void);
+};
+
+/**
+ * struct x86_init_ops - functions for platform specific setup
+ *
+ */
+struct x86_init_ops {
+	struct x86_init_resources	resources;
+	struct x86_init_mpparse		mpparse;
+	struct x86_init_irqs		irqs;
+	struct x86_init_oem		oem;
+	struct x86_init_paging		paging;
+	struct x86_init_timers		timers;
+};
+
+/**
+ * struct x86_cpuinit_ops - platform specific cpu hotplug setups
+ * @setup_percpu_clockev:	set up the per cpu clock event device
+ */
+struct x86_cpuinit_ops {
+	void (*setup_percpu_clockev)(void);
+};
+
+/**
+ * struct x86_platform_ops - platform specific runtime functions
+ * @calibrate_tsc:		calibrate TSC
+ * @get_wallclock:		get time from HW clock like RTC etc.
+ * @set_wallclock:		set time back to HW clock
+ */
+struct x86_platform_ops {
+	unsigned long (*calibrate_tsc)(void);
+	unsigned long (*get_wallclock)(void);
+	int (*set_wallclock)(unsigned long nowtime);
+};
+
+extern struct x86_init_ops x86_init;
+extern struct x86_cpuinit_ops x86_cpuinit;
+extern struct x86_platform_ops x86_platform;
+
+extern void x86_init_noop(void);
+extern void x86_init_uint_noop(unsigned int unused);
+
+#endif

arch/x86/kernel/Makefile

@@ -31,8 +31,8 @@ GCOV_PROFILE_paravirt.o		:= n
 
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y			+= time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o i8259.o irqinit.o
+obj-y			+= time.o ioport.o ldt.o dumpstack.o
+obj-y			+= setup.o x86_init.o i8259.o irqinit.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
@@ -105,6 +105,7 @@ obj-$(CONFIG_SCx200)		+= scx200.o
 scx200-y			+= scx200_32.o
 
 obj-$(CONFIG_OLPC)		+= olpc.o
+obj-$(CONFIG_X86_MRST)		+= mrst.o
 
 microcode-y				:= microcode_core.o
 microcode-$(CONFIG_MICROCODE_INTEL)	+= microcode_intel.o

arch/x86/kernel/apic/apic.c

@@ -36,6 +36,7 @@
 #include <linux/mm.h>
 
 #include <asm/perf_counter.h>
+#include <asm/x86_init.h>
 #include <asm/pgalloc.h>
 #include <asm/atomic.h>
 #include <asm/mpspec.h>
@@ -1709,7 +1710,7 @@ int __init APIC_init_uniprocessor(void)
 	localise_nmi_watchdog();
 #endif
 
-	setup_boot_clock();
+	x86_init.timers.setup_percpu_clockev();
 #ifdef CONFIG_X86_64
 	check_nmi_watchdog();
 #endif

arch/x86/kernel/apic/bigsmp_32.c

@@ -112,7 +112,7 @@ static physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map)
 	return physids_promote(0xFFL);
 }
 
-static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid)
+static int bigsmp_check_phys_apicid_present(int phys_apicid)
 {
 	return 1;
 }

arch/x86/kernel/apic/io_apic.c

@@ -96,6 +96,11 @@ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 /* # of MP IRQ source entries */
 int mp_irq_entries;
 
+/* Number of legacy interrupts */
+static int nr_legacy_irqs __read_mostly = NR_IRQS_LEGACY;
+/* GSI interrupts */
+static int nr_irqs_gsi = NR_IRQS_LEGACY;
+
 #if defined (CONFIG_MCA) || defined (CONFIG_EISA)
 int mp_bus_id_to_type[MAX_MP_BUSSES];
 #endif
@@ -173,6 +178,12 @@ static struct irq_cfg irq_cfgx[NR_IRQS] = {
 	[15] = { .vector = IRQ15_VECTOR, },
 };
 
+void __init io_apic_disable_legacy(void)
+{
+	nr_legacy_irqs = 0;
+	nr_irqs_gsi = 0;
+}
+
 int __init arch_early_irq_init(void)
 {
 	struct irq_cfg *cfg;
@@ -190,7 +201,7 @@ int __init arch_early_irq_init(void)
 		desc->chip_data = &cfg[i];
 		zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
 		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
-		if (i < NR_IRQS_LEGACY)
+		if (i < nr_legacy_irqs)
 			cpumask_setall(cfg[i].domain);
 	}
 
@@ -867,7 +878,7 @@ static int __init find_isa_irq_apic(int irq, int type)
  */
 static int EISA_ELCR(unsigned int irq)
 {
-	if (irq < NR_IRQS_LEGACY) {
+	if (irq < nr_legacy_irqs) {
 		unsigned int port = 0x4d0 + (irq >> 3);
 		return (inb(port) >> (irq & 7)) & 1;
 	}
@@ -1464,7 +1475,7 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
 	}
 
 	ioapic_register_intr(irq, desc, trigger);
-	if (irq < NR_IRQS_LEGACY)
+	if (irq < nr_legacy_irqs)
 		disable_8259A_irq(irq);
 
 	ioapic_write_entry(apic_id, pin, entry);
@@ -1831,7 +1842,7 @@ __apicdebuginit(void) print_PIC(void)
 	unsigned int v;
 	unsigned long flags;
 
-	if (apic_verbosity == APIC_QUIET)
+	if (apic_verbosity == APIC_QUIET || !nr_legacy_irqs)
 		return;
 
 	printk(KERN_DEBUG "\nprinting PIC contents\n");
@@ -1894,6 +1905,10 @@ void __init enable_IO_APIC(void)
 		spin_unlock_irqrestore(&ioapic_lock, flags);
 		nr_ioapic_registers[apic] = reg_01.bits.entries+1;
 	}
+
+	if (!nr_legacy_irqs)
+		return;
+
 	for(apic = 0; apic < nr_ioapics; apic++) {
 		int pin;
 		/* See if any of the pins is in ExtINT mode */
@@ -1948,6 +1963,9 @@ void disable_IO_APIC(void)
 	 */
 	clear_IO_APIC();
 
+	if (!nr_legacy_irqs)
+		return;
+
 	/*
 	 * If the i8259 is routed through an IOAPIC
 	 * Put that IOAPIC in virtual wire mode
@@ -1994,7 +2012,7 @@ void disable_IO_APIC(void)
  * by Matt Domsch <Matt_Domsch@dell.com>  Tue Dec 21 12:25:05 CST 1999
  */
 
-static void __init setup_ioapic_ids_from_mpc(void)
+void __init setup_ioapic_ids_from_mpc(void)
 {
 	union IO_APIC_reg_00 reg_00;
 	physid_mask_t phys_id_present_map;
@@ -2003,9 +2021,8 @@ static void __init setup_ioapic_ids_from_mpc(void)
 	unsigned char old_id;
 	unsigned long flags;
 
-	if (x86_quirks->setup_ioapic_ids && x86_quirks->setup_ioapic_ids())
+	if (acpi_ioapic)
 		return;
-
 	/*
 	 * Don't check I/O APIC IDs for xAPIC systems.  They have
 	 * no meaning without the serial APIC bus.
@@ -2179,7 +2196,7 @@ static unsigned int startup_ioapic_irq(unsigned int irq)
 	struct irq_cfg *cfg;
 
 	spin_lock_irqsave(&ioapic_lock, flags);
-	if (irq < NR_IRQS_LEGACY) {
+	if (irq < nr_legacy_irqs) {
 		disable_8259A_irq(irq);
 		if (i8259A_irq_pending(irq))
 			was_pending = 1;
@@ -2657,7 +2674,7 @@ static inline void init_IO_APIC_traps(void)
 			 * so default to an old-fashioned 8259
 			 * interrupt if we can..
 			 */
-			if (irq < NR_IRQS_LEGACY)
+			if (irq < nr_legacy_irqs)
 				make_8259A_irq(irq);
 			else
 				/* Strange. Oh, well.. */
@@ -2993,7 +3010,7 @@ out:
  * the I/O APIC in all cases now.  No actual device should request
  * it anyway.  --macro
  */
-#define PIC_IRQS	(1 << PIC_CASCADE_IR)
+#define PIC_IRQS	(1UL << PIC_CASCADE_IR)
 
 void __init setup_IO_APIC(void)
 {
@@ -3001,21 +3018,19 @@ void __init setup_IO_APIC(void)
 	/*
 	 * calling enable_IO_APIC() is moved to setup_local_APIC for BP
 	 */
-
-	io_apic_irqs = ~PIC_IRQS;
+	io_apic_irqs = nr_legacy_irqs ? ~PIC_IRQS : ~0UL;
 
 	apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
 	/*
          * Set up IO-APIC IRQ routing.
          */
-#ifdef CONFIG_X86_32
-	if (!acpi_ioapic)
-		setup_ioapic_ids_from_mpc();
-#endif
+	x86_init.mpparse.setup_ioapic_ids();
+
 	sync_Arb_IDs();
 	setup_IO_APIC_irqs();
 	init_IO_APIC_traps();
-	check_timer();
+	if (nr_legacy_irqs)
+		check_timer();
 }
 
 /*
@@ -3116,7 +3131,6 @@ static int __init ioapic_init_sysfs(void)
 
 device_initcall(ioapic_init_sysfs);
 
-static int nr_irqs_gsi = NR_IRQS_LEGACY;
 /*
  * Dynamic irq allocate and deallocation
  */
@@ -3856,7 +3870,7 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
 	/*
 	 * IRQs < 16 are already in the irq_2_pin[] map
 	 */
-	if (irq >= NR_IRQS_LEGACY) {
+	if (irq >= nr_legacy_irqs) {
 		cfg = desc->chip_data;
 		if (add_pin_to_irq_node_nopanic(cfg, node, ioapic, pin)) {
 			printk(KERN_INFO "can not add pin %d for irq %d\n",

arch/x86/kernel/apic/numaq_32.c

@@ -66,7 +66,6 @@ struct mpc_trans {
 	unsigned short			trans_reserved;
 };
 
-/* x86_quirks member */
 static int				mpc_record;
 
 static struct mpc_trans			*translation_table[MAX_MPC_ENTRY];
@@ -130,10 +129,9 @@ void __cpuinit numaq_tsc_disable(void)
 	}
 }
 
-static int __init numaq_pre_time_init(void)
+static void __init numaq_tsc_init(void)
 {
 	numaq_tsc_disable();
-	return 0;
 }
 
 static inline int generate_logical_apicid(int quad, int phys_apicid)
@@ -177,6 +175,19 @@ static void mpc_oem_pci_bus(struct mpc_bus *m)
 	quad_local_to_mp_bus_id[quad][local] = m->busid;
 }
 
+/*
+ * Called from mpparse code.
+ * mode = 0: prescan
+ * mode = 1: one mpc entry scanned
+ */
+static void numaq_mpc_record(unsigned int mode)
+{
+	if (!mode)
+		mpc_record = 0;
+	else
+		mpc_record++;
+}
+
 static void __init MP_translation_info(struct mpc_trans *m)
 {
 	printk(KERN_INFO
@@ -206,9 +217,9 @@ static int __init mpf_checksum(unsigned char *mp, int len)
 /*
  * Read/parse the MPC oem tables
  */
-static void __init
- smp_read_mpc_oem(struct mpc_oemtable *oemtable, unsigned short oemsize)
+static void __init smp_read_mpc_oem(struct mpc_table *mpc)
 {
+	struct mpc_oemtable *oemtable = (void *)(long)mpc->oemptr;
 	int count = sizeof(*oemtable);	/* the header size */
 	unsigned char *oemptr = ((unsigned char *)oemtable) + count;
 
@@ -250,29 +261,6 @@ static void __init
 	}
 }
 
-static int __init numaq_setup_ioapic_ids(void)
-{
-	/* so can skip it */
-	return 1;
-}
-
-static struct x86_quirks numaq_x86_quirks __initdata = {
-	.arch_pre_time_init		= numaq_pre_time_init,
-	.arch_time_init			= NULL,
-	.arch_pre_intr_init		= NULL,
-	.arch_memory_setup		= NULL,
-	.arch_intr_init			= NULL,
-	.arch_trap_init			= NULL,
-	.mach_get_smp_config		= NULL,
-	.mach_find_smp_config		= NULL,
-	.mpc_record			= &mpc_record,
-	.mpc_apic_id			= mpc_apic_id,
-	.mpc_oem_bus_info		= mpc_oem_bus_info,
-	.mpc_oem_pci_bus		= mpc_oem_pci_bus,
-	.smp_read_mpc_oem		= smp_read_mpc_oem,
-	.setup_ioapic_ids		= numaq_setup_ioapic_ids,
-};
-
 static __init void early_check_numaq(void)
 {
 	/*
@@ -286,8 +274,15 @@ static __init void early_check_numaq(void)
 	if (smp_found_config)
 		early_get_smp_config();
 
-	if (found_numaq)
-		x86_quirks = &numaq_x86_quirks;
+	if (found_numaq) {
+		x86_init.mpparse.mpc_record = numaq_mpc_record;
+		x86_init.mpparse.setup_ioapic_ids = x86_init_noop;
+		x86_init.mpparse.mpc_apic_id = mpc_apic_id;
+		x86_init.mpparse.smp_read_mpc_oem = smp_read_mpc_oem;
+		x86_init.mpparse.mpc_oem_pci_bus = mpc_oem_pci_bus;
+		x86_init.mpparse.mpc_oem_bus_info = mpc_oem_bus_info;
+		x86_init.timers.tsc_pre_init = numaq_tsc_init;
+	}
 }
 
 int __init get_memcfg_numaq(void)
@@ -418,7 +413,7 @@ static inline physid_mask_t numaq_apicid_to_cpu_present(int logical_apicid)
 /* Where the IO area was mapped on multiquad, always 0 otherwise */
 void *xquad_portio;
 
-static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid)
+static inline int numaq_check_phys_apicid_present(int phys_apicid)
 {
 	return 1;
 }

arch/x86/kernel/apic/summit_32.c

@@ -272,7 +272,7 @@ static physid_mask_t summit_apicid_to_cpu_present(int apicid)
 	return physid_mask_of_physid(0);
 }
 
-static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid)
+static int summit_check_phys_apicid_present(int physical_apicid)
 {
 	return 1;
 }

arch/x86/kernel/cpu/hypervisor.c

@@ -34,13 +34,6 @@ detect_hypervisor_vendor(struct cpuinfo_x86 *c)
 		c->x86_hyper_vendor = X86_HYPER_VENDOR_NONE;
 }
 
-unsigned long get_hypervisor_tsc_freq(void)
-{
-	if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE)
-		return vmware_get_tsc_khz();
-	return 0;
-}
-
 static inline void __cpuinit
 hypervisor_set_feature_bits(struct cpuinfo_x86 *c)
 {
@@ -55,3 +48,10 @@ void __cpuinit init_hypervisor(struct cpuinfo_x86 *c)
 	detect_hypervisor_vendor(c);
 	hypervisor_set_feature_bits(c);
 }
+
+void __init init_hypervisor_platform(void)
+{
+	init_hypervisor(&boot_cpu_data);
+	if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE)
+		vmware_platform_setup();
+}

arch/x86/kernel/cpu/vmware.c

@@ -24,6 +24,7 @@
 #include <linux/dmi.h>
 #include <asm/div64.h>
 #include <asm/vmware.h>
+#include <asm/x86_init.h>
 
 #define CPUID_VMWARE_INFO_LEAF	0x40000000
 #define VMWARE_HYPERVISOR_MAGIC	0x564D5868
@@ -47,21 +48,29 @@ static inline int __vmware_platform(void)
 	return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC;
 }
 
-static unsigned long __vmware_get_tsc_khz(void)
+static unsigned long vmware_get_tsc_khz(void)
 {
 	uint64_t tsc_hz;
 	uint32_t eax, ebx, ecx, edx;
 
 	VMWARE_PORT(GETHZ, eax, ebx, ecx, edx);
 
-	if (ebx == UINT_MAX)
-		return 0;
 	tsc_hz = eax | (((uint64_t)ebx) << 32);
 	do_div(tsc_hz, 1000);
 	BUG_ON(tsc_hz >> 32);
 	return tsc_hz;
 }
 
+void __init vmware_platform_setup(void)
+{
+	uint32_t eax, ebx, ecx, edx;
+
+	VMWARE_PORT(GETHZ, eax, ebx, ecx, edx);
+
+	if (ebx != UINT_MAX)
+		x86_platform.calibrate_tsc = vmware_get_tsc_khz;
+}
+
 /*
  * While checking the dmi string infomation, just checking the product
  * serial key should be enough, as this will always have a VMware
@@ -87,12 +96,6 @@ int vmware_platform(void)
 	return 0;
 }
 
-unsigned long vmware_get_tsc_khz(void)
-{
-	BUG_ON(!vmware_platform());
-	return __vmware_get_tsc_khz();
-}
-
 /*
  * VMware hypervisor takes care of exporting a reliable TSC to the guest.
  * Still, due to timing difference when running on virtual cpus, the TSC can

arch/x86/kernel/e820.c

@@ -1455,28 +1455,11 @@ char *__init default_machine_specific_memory_setup(void)
 	return who;
 }
 
-char *__init __attribute__((weak)) machine_specific_memory_setup(void)
-{
-	if (x86_quirks->arch_memory_setup) {
-		char *who = x86_quirks->arch_memory_setup();
-
-		if (who)
-			return who;
-	}
-	return default_machine_specific_memory_setup();
-}
-
-/* Overridden in paravirt.c if CONFIG_PARAVIRT */
-char * __init __attribute__((weak)) memory_setup(void)
-{
-	return machine_specific_memory_setup();
-}
-
 void __init setup_memory_map(void)
 {
 	char *who;
 
-	who = memory_setup();
+	who = x86_init.resources.memory_setup();
 	memcpy(&e820_saved, &e820, sizeof(struct e820map));
 	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
 	e820_print_map(who);

arch/x86/kernel/efi.c

@@ -42,6 +42,7 @@
 #include <asm/time.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
+#include <asm/x86_init.h>
 
 #define EFI_DEBUG	1
 #define PFX 		"EFI: "
@@ -453,6 +454,9 @@ void __init efi_init(void)
 	if (add_efi_memmap)
 		do_add_efi_memmap();
 
+	x86_platform.get_wallclock = efi_get_time;
+	x86_platform.set_wallclock = efi_set_rtc_mmss;
+
 	/* Setup for EFI runtime service */
 	reboot_type = BOOT_EFI;
 

arch/x86/kernel/head32.c

@@ -11,8 +11,21 @@
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/e820.h>
-#include <asm/bios_ebda.h>
+#include <asm/page.h>
 #include <asm/trampoline.h>
+#include <asm/apic.h>
+#include <asm/io_apic.h>
+#include <asm/bios_ebda.h>
+
+static void __init i386_default_early_setup(void)
+{
+	/* Initilize 32bit specific setup functions */
+	x86_init.resources.probe_roms = probe_roms;
+	x86_init.resources.reserve_resources = i386_reserve_resources;
+	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
+
+	reserve_ebda_region();
+}
 
 void __init i386_start_kernel(void)
 {
@@ -29,7 +42,16 @@ void __init i386_start_kernel(void)
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
-	reserve_ebda_region();
+
+	/* Call the subarch specific early setup function */
+	switch (boot_params.hdr.hardware_subarch) {
+	case X86_SUBARCH_MRST:
+		x86_mrst_early_setup();
+		break;
+	default:
+		i386_default_early_setup();
+		break;
+	}
 
 	/*
 	 * At this point everything still needed from the boot loader

arch/x86/kernel/head64.c

@@ -23,8 +23,8 @@
 #include <asm/sections.h>
 #include <asm/kdebug.h>
 #include <asm/e820.h>
-#include <asm/bios_ebda.h>
 #include <asm/trampoline.h>
+#include <asm/bios_ebda.h>
 
 static void __init zap_identity_mappings(void)
 {

arch/x86/kernel/head_32.S

@@ -157,6 +157,7 @@ subarch_entries:
 	.long default_entry		/* normal x86/PC */
 	.long lguest_entry		/* lguest hypervisor */
 	.long xen_entry			/* Xen hypervisor */
+	.long default_entry		/* Moorestown MID */
 num_subarch_entries = (. - subarch_entries) / 4
 .previous
 #endif /* CONFIG_PARAVIRT */

arch/x86/kernel/irqinit.c

@@ -116,7 +116,7 @@ int vector_used_by_percpu_irq(unsigned int vector)
 	return 0;
 }
 
-static void __init init_ISA_irqs(void)
+void __init init_ISA_irqs(void)
 {
 	int i;
 
@@ -140,8 +140,10 @@ static void __init init_ISA_irqs(void)
 	}
 }
 
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+void __init init_IRQ(void)
+{
+	x86_init.irqs.intr_init();
+}
 
 static void __init smp_intr_init(void)
 {
@@ -213,32 +215,12 @@ static void __init apic_intr_init(void)
 #endif
 }
 
-/**
- * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
- *
- * Description:
- *	Perform any necessary interrupt initialisation prior to setting up
- *	the "ordinary" interrupt call gates.  For legacy reasons, the ISA
- *	interrupts should be initialised here if the machine emulates a PC
- *	in any way.
- **/
-static void __init x86_quirk_pre_intr_init(void)
-{
-#ifdef CONFIG_X86_32
-	if (x86_quirks->arch_pre_intr_init) {
-		if (x86_quirks->arch_pre_intr_init())
-			return;
-	}
-#endif
-	init_ISA_irqs();
-}
-
 void __init native_init_IRQ(void)
 {
 	int i;
 
 	/* Execute any quirks before the call gates are initialised: */
-	x86_quirk_pre_intr_init();
+	x86_init.irqs.pre_vector_init();
 
 	apic_intr_init();
 
@@ -257,12 +239,6 @@ void __init native_init_IRQ(void)
 		setup_irq(2, &irq2);
 
 #ifdef CONFIG_X86_32
-	/*
-	 * Call quirks after call gates are initialised (usually add in
-	 * the architecture specific gates):
-	 */
-	x86_quirk_intr_init();
-
 	/*
 	 * External FPU? Set up irq13 if so, for
 	 * original braindamaged IBM FERR coupling.

arch/x86/kernel/kvmclock.c

@@ -22,6 +22,8 @@
 #include <asm/msr.h>
 #include <asm/apic.h>
 #include <linux/percpu.h>
+
+#include <asm/x86_init.h>
 #include <asm/reboot.h>
 
 #define KVM_SCALE 22
@@ -182,12 +184,13 @@ void __init kvmclock_init(void)
 	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
 		if (kvm_register_clock("boot clock"))
 			return;
-		pv_time_ops.get_wallclock = kvm_get_wallclock;
-		pv_time_ops.set_wallclock = kvm_set_wallclock;
 		pv_time_ops.sched_clock = kvm_clock_read;
-		pv_time_ops.get_tsc_khz = kvm_get_tsc_khz;
+		x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+		x86_platform.get_wallclock = kvm_get_wallclock;
+		x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-		pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+		x86_cpuinit.setup_percpu_clockev =
+			kvm_setup_secondary_clock;
 #endif
 #ifdef CONFIG_SMP
 		smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;

arch/x86/kernel/mpparse.c

@@ -45,6 +45,11 @@ static int __init mpf_checksum(unsigned char *mp, int len)
 	return sum & 0xFF;
 }
 
+int __init default_mpc_apic_id(struct mpc_cpu *m)
+{
+	return m->apicid;
+}
+
 static void __init MP_processor_info(struct mpc_cpu *m)
 {
 	int apicid;
@@ -55,10 +60,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 		return;
 	}
 
-	if (x86_quirks->mpc_apic_id)
-		apicid = x86_quirks->mpc_apic_id(m);
-	else
-		apicid = m->apicid;
+	apicid = x86_init.mpparse.mpc_apic_id(m);
 
 	if (m->cpuflag & CPU_BOOTPROCESSOR) {
 		bootup_cpu = " (Bootup-CPU)";
@@ -70,16 +72,18 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 }
 
 #ifdef CONFIG_X86_IO_APIC
-static void __init MP_bus_info(struct mpc_bus *m)
+void __init default_mpc_oem_bus_info(struct mpc_bus *m, char *str)
 {
-	char str[7];
 	memcpy(str, m->bustype, 6);
 	str[6] = 0;
+	apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->busid, str);
+}
 
-	if (x86_quirks->mpc_oem_bus_info)
-		x86_quirks->mpc_oem_bus_info(m, str);
-	else
-		apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->busid, str);
+static void __init MP_bus_info(struct mpc_bus *m)
+{
+	char str[7];
+
+	x86_init.mpparse.mpc_oem_bus_info(m, str);
 
 #if MAX_MP_BUSSES < 256
 	if (m->busid >= MAX_MP_BUSSES) {
@@ -96,8 +100,8 @@ static void __init MP_bus_info(struct mpc_bus *m)
 		mp_bus_id_to_type[m->busid] = MP_BUS_ISA;
 #endif
 	} else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI) - 1) == 0) {
-		if (x86_quirks->mpc_oem_pci_bus)
-			x86_quirks->mpc_oem_pci_bus(m);
+		if (x86_init.mpparse.mpc_oem_pci_bus)
+			x86_init.mpparse.mpc_oem_pci_bus(m);
 
 		clear_bit(m->busid, mp_bus_not_pci);
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
@@ -291,6 +295,8 @@ static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt)
 			1, mpc, mpc->length, 1);
 }
 
+void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { }
+
 static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 {
 	char str[16];
@@ -312,16 +318,13 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 	if (early)
 		return 1;
 
-	if (mpc->oemptr && x86_quirks->smp_read_mpc_oem) {
-		struct mpc_oemtable *oem_table = (void *)(long)mpc->oemptr;
-		x86_quirks->smp_read_mpc_oem(oem_table, mpc->oemsize);
-	}
+	if (mpc->oemptr)
+		x86_init.mpparse.smp_read_mpc_oem(mpc);
 
 	/*
 	 *      Now process the configuration blocks.
 	 */
-	if (x86_quirks->mpc_record)
-		*x86_quirks->mpc_record = 0;
+	x86_init.mpparse.mpc_record(0);
 
 	while (count < mpc->length) {
 		switch (*mpt) {
@@ -353,8 +356,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 			count = mpc->length;
 			break;
 		}
-		if (x86_quirks->mpc_record)
-			(*x86_quirks->mpc_record)++;
+		x86_init.mpparse.mpc_record(1);
 	}
 
 #ifdef CONFIG_X86_BIGSMP
@@ -608,7 +610,7 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early)
 /*
  * Scan the memory blocks for an SMP configuration block.
  */
-static void __init __get_smp_config(unsigned int early)
+void __init default_get_smp_config(unsigned int early)
 {
 	struct mpf_intel *mpf = mpf_found;
 
@@ -625,11 +627,6 @@ static void __init __get_smp_config(unsigned int early)
 	if (acpi_lapic && acpi_ioapic)
 		return;
 
-	if (x86_quirks->mach_get_smp_config) {
-		if (x86_quirks->mach_get_smp_config(early))
-			return;
-	}
-
 	printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
 	       mpf->specification);
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
@@ -670,16 +667,6 @@ static void __init __get_smp_config(unsigned int early)
 	 */
 }
 
-void __init early_get_smp_config(void)
-{
-	__get_smp_config(1);
-}
-
-void __init get_smp_config(void)
-{
-	__get_smp_config(0);
-}
-
 static void __init smp_reserve_bootmem(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
@@ -745,14 +732,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 	return 0;
 }
 
-static void __init __find_smp_config(unsigned int reserve)
+void __init default_find_smp_config(unsigned int reserve)
 {
 	unsigned int address;
 
-	if (x86_quirks->mach_find_smp_config) {
-		if (x86_quirks->mach_find_smp_config(reserve))
-			return;
-	}
 	/*
 	 * FIXME: Linux assumes you have 640K of base ram..
 	 * this continues the error...
@@ -787,16 +770,6 @@ static void __init __find_smp_config(unsigned int reserve)
 		smp_scan_config(address, 0x400, reserve);
 }
 
-void __init early_find_smp_config(void)
-{
-	__find_smp_config(0);
-}
-
-void __init find_smp_config(void)
-{
-	__find_smp_config(1);
-}
-
 #ifdef CONFIG_X86_IO_APIC
 static u8 __initdata irq_used[MAX_IRQ_SOURCES];
 

arch/x86/kernel/mrst.c

@@ -0,0 +1,24 @@
+/*
+ * mrst.c: Intel Moorestown platform specific setup code
+ *
+ * (C) Copyright 2008 Intel Corporation
+ * Author: Jacob Pan (jacob.jun.pan@intel.com)
+ *
+ * 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; version 2
+ * of the License.
+ */
+#include <linux/init.h>
+
+#include <asm/setup.h>
+
+/*
+ * Moorestown specific x86_init function overrides and early setup
+ * calls.
+ */
+void __init x86_mrst_early_setup(void)
+{
+	x86_init.resources.probe_roms = x86_init_noop;
+	x86_init.resources.reserve_resources = x86_init_noop;
+}

arch/x86/kernel/paravirt.c

@@ -54,17 +54,12 @@ u64 _paravirt_ident_64(u64 x)
 	return x;
 }
 
-static void __init default_banner(void)
+void __init default_banner(void)
 {
 	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
 	       pv_info.name);
 }
 
-char *memory_setup(void)
-{
-	return pv_init_ops.memory_setup();
-}
-
 /* Simple instruction patching code. */
 #define DEF_NATIVE(ops, name, code)					\
 	extern const char start_##ops##_##name[], end_##ops##_##name[];	\
@@ -188,11 +183,6 @@ unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
 	return insn_len;
 }
 
-void init_IRQ(void)
-{
-	pv_irq_ops.init_IRQ();
-}
-
 static void native_flush_tlb(void)
 {
 	__native_flush_tlb();
@@ -218,13 +208,6 @@ extern void native_irq_enable_sysexit(void);
 extern void native_usergs_sysret32(void);
 extern void native_usergs_sysret64(void);
 
-static int __init print_banner(void)
-{
-	pv_init_ops.banner();
-	return 0;
-}
-core_initcall(print_banner);
-
 static struct resource reserve_ioports = {
 	.start = 0,
 	.end = IO_SPACE_LIMIT,
@@ -320,21 +303,13 @@ struct pv_info pv_info = {
 
 struct pv_init_ops pv_init_ops = {
 	.patch = native_patch,
-	.banner = default_banner,
-	.arch_setup = paravirt_nop,
-	.memory_setup = machine_specific_memory_setup,
 };
 
 struct pv_time_ops pv_time_ops = {
-	.time_init = hpet_time_init,
-	.get_wallclock = native_get_wallclock,
-	.set_wallclock = native_set_wallclock,
 	.sched_clock = native_sched_clock,
-	.get_tsc_khz = native_calibrate_tsc,
 };
 
 struct pv_irq_ops pv_irq_ops = {
-	.init_IRQ = native_init_IRQ,
 	.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
 	.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
 	.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
@@ -409,8 +384,6 @@ struct pv_cpu_ops pv_cpu_ops = {
 
 struct pv_apic_ops pv_apic_ops = {
 #ifdef CONFIG_X86_LOCAL_APIC
-	.setup_boot_clock = setup_boot_APIC_clock,
-	.setup_secondary_clock = setup_secondary_APIC_clock,
 	.startup_ipi_hook = paravirt_nop,
 #endif
 };
@@ -424,13 +397,6 @@ struct pv_apic_ops pv_apic_ops = {
 #endif
 
 struct pv_mmu_ops pv_mmu_ops = {
-#ifndef CONFIG_X86_64
-	.pagetable_setup_start = native_pagetable_setup_start,
-	.pagetable_setup_done = native_pagetable_setup_done,
-#else
-	.pagetable_setup_start = paravirt_nop,
-	.pagetable_setup_done = paravirt_nop,
-#endif
 
 	.read_cr2 = native_read_cr2,
 	.write_cr2 = native_write_cr2,

arch/x86/kernel/rtc.c

@@ -8,6 +8,7 @@
 #include <linux/pnp.h>
 
 #include <asm/vsyscall.h>
+#include <asm/x86_init.h>
 #include <asm/time.h>
 
 #ifdef CONFIG_X86_32
@@ -165,13 +166,13 @@ void rtc_cmos_write(unsigned char val, unsigned char addr)
 }
 EXPORT_SYMBOL(rtc_cmos_write);
 
-static int set_rtc_mmss(unsigned long nowtime)
+int update_persistent_clock(struct timespec now)
 {
 	unsigned long flags;
 	int retval;
 
 	spin_lock_irqsave(&rtc_lock, flags);
-	retval = set_wallclock(nowtime);
+	retval = x86_platform.set_wallclock(now.tv_sec);
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	return retval;
@@ -183,18 +184,13 @@ void read_persistent_clock(struct timespec *ts)
 	unsigned long retval, flags;
 
 	spin_lock_irqsave(&rtc_lock, flags);
-	retval = get_wallclock();
+	retval = x86_platform.get_wallclock();
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	ts->tv_sec = retval;
 	ts->tv_nsec = 0;
 }
 
-int update_persistent_clock(struct timespec now)
-{
-	return set_rtc_mmss(now.tv_sec);
-}
-
 unsigned long long native_read_tsc(void)
 {
 	return __native_read_tsc();

arch/x86/kernel/setup.c

@@ -109,10 +109,6 @@
 #include <asm/numa_64.h>
 #endif
 
-#ifndef ARCH_SETUP
-#define ARCH_SETUP
-#endif
-
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
  * The direct mapping extends to max_pfn_mapped, so that we can directly access
@@ -134,9 +130,9 @@ int default_cpu_present_to_apicid(int mps_cpu)
 	return __default_cpu_present_to_apicid(mps_cpu);
 }
 
-int default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+int default_check_phys_apicid_present(int phys_apicid)
 {
-	return __default_check_phys_apicid_present(boot_cpu_physical_apicid);
+	return __default_check_phys_apicid_present(phys_apicid);
 }
 #endif
 
@@ -172,13 +168,6 @@ static struct resource bss_resource = {
 
 
 #ifdef CONFIG_X86_32
-static struct resource video_ram_resource = {
-	.name	= "Video RAM area",
-	.start	= 0xa0000,
-	.end	= 0xbffff,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
-};
-
 /* cpu data as detected by the assembly code in head.S */
 struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1};
 /* common cpu data for all cpus */
@@ -606,7 +595,7 @@ static struct resource standard_io_resources[] = {
 		.flags = IORESOURCE_BUSY | IORESOURCE_IO }
 };
 
-static void __init reserve_standard_io_resources(void)
+void __init reserve_standard_io_resources(void)
 {
 	int i;
 
@@ -638,10 +627,6 @@ static int __init setup_elfcorehdr(char *arg)
 early_param("elfcorehdr", setup_elfcorehdr);
 #endif
 
-static struct x86_quirks default_x86_quirks __initdata;
-
-struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
-
 #ifdef CONFIG_X86_RESERVE_LOW_64K
 static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
 {
@@ -773,7 +758,7 @@ void __init setup_arch(char **cmdline_p)
 	}
 #endif
 
-	ARCH_SETUP
+	x86_init.oem.arch_setup();
 
 	setup_memory_map();
 	parse_setup_data();
@@ -844,11 +829,9 @@ void __init setup_arch(char **cmdline_p)
 	 * VMware detection requires dmi to be available, so this
 	 * needs to be done after dmi_scan_machine, for the BP.
 	 */
-	init_hypervisor(&boot_cpu_data);
+	init_hypervisor_platform();
 
-#ifdef CONFIG_X86_32
-	probe_roms();
-#endif
+	x86_init.resources.probe_roms();
 
 	/* after parse_early_param, so could debug it */
 	insert_resource(&iomem_resource, &code_resource);
@@ -983,10 +966,9 @@ void __init setup_arch(char **cmdline_p)
 	kvmclock_init();
 #endif
 
-	paravirt_pagetable_setup_start(swapper_pg_dir);
+	x86_init.paging.pagetable_setup_start(swapper_pg_dir);
 	paging_init();
-	paravirt_pagetable_setup_done(swapper_pg_dir);
-	paravirt_post_allocator_init();
+	x86_init.paging.pagetable_setup_done(swapper_pg_dir);
 
 	tboot_probe();
 
@@ -1003,13 +985,11 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	acpi_boot_init();
 
-#if defined(CONFIG_X86_MPPARSE) || defined(CONFIG_X86_VISWS)
 	/*
 	 * get boot-time SMP configuration:
 	 */
 	if (smp_found_config)
 		get_smp_config();
-#endif
 
 	prefill_possible_map();
 
@@ -1028,10 +1008,7 @@ void __init setup_arch(char **cmdline_p)
 	e820_reserve_resources();
 	e820_mark_nosave_regions(max_low_pfn);
 
-#ifdef CONFIG_X86_32
-	request_resource(&iomem_resource, &video_ram_resource);
-#endif
-	reserve_standard_io_resources();
+	x86_init.resources.reserve_resources();
 
 	e820_setup_gap();
 
@@ -1043,78 +1020,22 @@ void __init setup_arch(char **cmdline_p)
 	conswitchp = &dummy_con;
 #endif
 #endif
+	x86_init.oem.banner();
 }
 
 #ifdef CONFIG_X86_32
 
-/**
- * x86_quirk_intr_init - post gate setup interrupt initialisation
- *
- * Description:
- *	Fill in any interrupts that may have been left out by the general
- *	init_IRQ() routine.  interrupts having to do with the machine rather
- *	than the devices on the I/O bus (like APIC interrupts in intel MP
- *	systems) are started here.
- **/
-void __init x86_quirk_intr_init(void)
-{
-	if (x86_quirks->arch_intr_init) {
-		if (x86_quirks->arch_intr_init())
-			return;
-	}
-}
-
-/**
- * x86_quirk_trap_init - initialise system specific traps
- *
- * Description:
- *	Called as the final act of trap_init().  Used in VISWS to initialise
- *	the various board specific APIC traps.
- **/
-void __init x86_quirk_trap_init(void)
-{
-	if (x86_quirks->arch_trap_init) {
-		if (x86_quirks->arch_trap_init())
-			return;
-	}
-}
-
-static struct irqaction irq0  = {
-	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
-	.name = "timer"
+static struct resource video_ram_resource = {
+	.name	= "Video RAM area",
+	.start	= 0xa0000,
+	.end	= 0xbffff,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
 };
 
-/**
- * x86_quirk_pre_time_init - do any specific initialisations before.
- *
- **/
-void __init x86_quirk_pre_time_init(void)
+void __init i386_reserve_resources(void)
 {
-	if (x86_quirks->arch_pre_time_init)
-		x86_quirks->arch_pre_time_init();
+	request_resource(&iomem_resource, &video_ram_resource);
+	reserve_standard_io_resources();
 }
 
-/**
- * x86_quirk_time_init - do any specific initialisations for the system timer.
- *
- * Description:
- *	Must plug the system timer interrupt source at HZ into the IRQ listed
- *	in irq_vectors.h:TIMER_IRQ
- **/
-void __init x86_quirk_time_init(void)
-{
-	if (x86_quirks->arch_time_init) {
-		/*
-		 * A nonzero return code does not mean failure, it means
-		 * that the architecture quirk does not want any
-		 * generic (timer) setup to be performed after this:
-		 */
-		if (x86_quirks->arch_time_init())
-			return;
-	}
-
-	irq0.mask = cpumask_of_cpu(0);
-	setup_irq(0, &irq0);
-}
 #endif /* CONFIG_X86_32 */

arch/x86/kernel/smpboot.c

@@ -324,7 +324,7 @@ notrace static void __cpuinit start_secondary(void *unused)
 	/* enable local interrupts */
 	local_irq_enable();
 
-	setup_secondary_clock();
+	x86_cpuinit.setup_percpu_clockev();
 
 	wmb();
 	cpu_idle();
@@ -1114,7 +1114,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
 	printk(KERN_INFO "CPU%d: ", 0);
 	print_cpu_info(&cpu_data(0));
-	setup_boot_clock();
+	x86_init.timers.setup_percpu_clockev();
 
 	if (is_uv_system())
 		uv_system_init();

arch/x86/kernel/time.c

@@ -0,0 +1,121 @@
+/*
+ *  Copyright (c) 1991,1992,1995  Linus Torvalds
+ *  Copyright (c) 1994  Alan Modra
+ *  Copyright (c) 1995  Markus Kuhn
+ *  Copyright (c) 1996  Ingo Molnar
+ *  Copyright (c) 1998  Andrea Arcangeli
+ *  Copyright (c) 2002,2006  Vojtech Pavlik
+ *  Copyright (c) 2003  Andi Kleen
+ *
+ */
+
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/mca.h>
+
+#include <asm/vsyscall.h>
+#include <asm/x86_init.h>
+#include <asm/i8259.h>
+#include <asm/i8253.h>
+#include <asm/timer.h>
+#include <asm/hpet.h>
+#include <asm/time.h>
+
+#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC)
+int timer_ack;
+#endif
+
+#ifdef CONFIG_X86_64
+volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
+#endif
+
+unsigned long profile_pc(struct pt_regs *regs)
+{
+	unsigned long pc = instruction_pointer(regs);
+
+	if (!user_mode_vm(regs) && in_lock_functions(pc)) {
+#ifdef CONFIG_FRAME_POINTER
+		return *(unsigned long *)(regs->bp + sizeof(long));
+#else
+		unsigned long *sp = (unsigned long *)regs->sp;
+		/*
+		 * Return address is either directly at stack pointer
+		 * or above a saved flags. Eflags has bits 22-31 zero,
+		 * kernel addresses don't.
+		 */
+		if (sp[0] >> 22)
+			return sp[0];
+		if (sp[1] >> 22)
+			return sp[1];
+#endif
+	}
+	return pc;
+}
+EXPORT_SYMBOL(profile_pc);
+
+/*
+ * Default timer interrupt handler for PIT/HPET
+ */
+static irqreturn_t timer_interrupt(int irq, void *dev_id)
+{
+	/* Keep nmi watchdog up to date */
+	inc_irq_stat(irq0_irqs);
+
+	/* Optimized out for !IO_APIC and x86_64 */
+	if (timer_ack) {
+		/*
+		 * Subtle, when I/O APICs are used we have to ack timer IRQ
+		 * manually to deassert NMI lines for the watchdog if run
+		 * on an 82489DX-based system.
+		 */
+		spin_lock(&i8259A_lock);
+		outb(0x0c, PIC_MASTER_OCW3);
+		/* Ack the IRQ; AEOI will end it automatically. */
+		inb(PIC_MASTER_POLL);
+		spin_unlock(&i8259A_lock);
+	}
+
+	global_clock_event->event_handler(global_clock_event);
+
+	/* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */
+	if (MCA_bus)
+		outb_p(inb_p(0x61)| 0x80, 0x61);
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction irq0  = {
+	.handler = timer_interrupt,
+	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
+	.name = "timer"
+};
+
+void __init setup_default_timer_irq(void)
+{
+	irq0.mask = cpumask_of_cpu(0);
+	setup_irq(0, &irq0);
+}
+
+/* Default timer init function */
+void __init hpet_time_init(void)
+{
+	if (!hpet_enable())
+		setup_pit_timer();
+	setup_default_timer_irq();
+}
+
+static __init void x86_late_time_init(void)
+{
+	x86_init.timers.timer_init();
+	tsc_init();
+}
+
+/*
+ * Initialize TSC and delay the periodic timer init to
+ * late x86_late_time_init() so ioremap works.
+ */
+void __init time_init(void)
+{
+	late_time_init = x86_late_time_init;
+}

arch/x86/kernel/time_32.c

@@ -1,137 +0,0 @@
-/*
- *  Copyright (C) 1991, 1992, 1995  Linus Torvalds
- *
- * This file contains the PC-specific time handling details:
- * reading the RTC at bootup, etc..
- * 1994-07-02    Alan Modra
- *	fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime
- * 1995-03-26    Markus Kuhn
- *      fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887
- *      precision CMOS clock update
- * 1996-05-03    Ingo Molnar
- *      fixed time warps in do_[slow|fast]_gettimeoffset()
- * 1997-09-10	Updated NTP code according to technical memorandum Jan '96
- *		"A Kernel Model for Precision Timekeeping" by Dave Mills
- * 1998-09-05    (Various)
- *	More robust do_fast_gettimeoffset() algorithm implemented
- *	(works with APM, Cyrix 6x86MX and Centaur C6),
- *	monotonic gettimeofday() with fast_get_timeoffset(),
- *	drift-proof precision TSC calibration on boot
- *	(C. Scott Ananian <cananian@alumni.princeton.edu>, Andrew D.
- *	Balsa <andrebalsa@altern.org>, Philip Gladstone <philip@raptor.com>;
- *	ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@tu-harburg.de>).
- * 1998-12-16    Andrea Arcangeli
- *	Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy
- *	because was not accounting lost_ticks.
- * 1998-12-24 Copyright (C) 1998  Andrea Arcangeli
- *	Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
- *	serialize accesses to xtime/lost_ticks).
- */
-
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/time.h>
-#include <linux/mca.h>
-
-#include <asm/setup.h>
-#include <asm/hpet.h>
-#include <asm/time.h>
-#include <asm/timer.h>
-
-#include <asm/do_timer.h>
-
-int timer_ack;
-
-unsigned long profile_pc(struct pt_regs *regs)
-{
-	unsigned long pc = instruction_pointer(regs);
-
-#ifdef CONFIG_SMP
-	if (!user_mode_vm(regs) && in_lock_functions(pc)) {
-#ifdef CONFIG_FRAME_POINTER
-		return *(unsigned long *)(regs->bp + sizeof(long));
-#else
-		unsigned long *sp = (unsigned long *)&regs->sp;
-
-		/* Return address is either directly at stack pointer
-		   or above a saved flags. Eflags has bits 22-31 zero,
-		   kernel addresses don't. */
-		if (sp[0] >> 22)
-			return sp[0];
-		if (sp[1] >> 22)
-			return sp[1];
-#endif
-	}
-#endif
-	return pc;
-}
-EXPORT_SYMBOL(profile_pc);
-
-/*
- * This is the same as the above, except we _also_ save the current
- * Time Stamp Counter value at the time of the timer interrupt, so that
- * we later on can estimate the time of day more exactly.
- */
-irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	/* Keep nmi watchdog up to date */
-	inc_irq_stat(irq0_irqs);
-
-#ifdef CONFIG_X86_IO_APIC
-	if (timer_ack) {
-		/*
-		 * Subtle, when I/O APICs are used we have to ack timer IRQ
-		 * manually to deassert NMI lines for the watchdog if run
-		 * on an 82489DX-based system.
-		 */
-		spin_lock(&i8259A_lock);
-		outb(0x0c, PIC_MASTER_OCW3);
-		/* Ack the IRQ; AEOI will end it automatically. */
-		inb(PIC_MASTER_POLL);
-		spin_unlock(&i8259A_lock);
-	}
-#endif
-
-	do_timer_interrupt_hook();
-
-#ifdef CONFIG_MCA
-	if (MCA_bus) {
-		/* The PS/2 uses level-triggered interrupts.  You can't
-		turn them off, nor would you want to (any attempt to
-		enable edge-triggered interrupts usually gets intercepted by a
-		special hardware circuit).  Hence we have to acknowledge
-		the timer interrupt.  Through some incredibly stupid
-		design idea, the reset for IRQ 0 is done by setting the
-		high bit of the PPI port B (0x61).  Note that some PS/2s,
-		notably the 55SX, work fine if this is removed.  */
-
-		u8 irq_v = inb_p(0x61);		/* read the current state */
-		outb_p(irq_v | 0x80, 0x61);	/* reset the IRQ */
-	}
-#endif
-
-	return IRQ_HANDLED;
-}
-
-/* Duplicate of time_init() below, with hpet_enable part added */
-void __init hpet_time_init(void)
-{
-	if (!hpet_enable())
-		setup_pit_timer();
-	x86_quirk_time_init();
-}
-
-/*
- * This is called directly from init code; we must delay timer setup in the
- * HPET case as we can't make the decision to turn on HPET this early in the
- * boot process.
- *
- * The chosen time_init function will usually be hpet_time_init, above, but
- * in the case of virtual hardware, an alternative function may be substituted.
- */
-void __init time_init(void)
-{
-	x86_quirk_pre_time_init();
-	tsc_init();
-	late_time_init = choose_time_init();
-}

arch/x86/kernel/time_64.c

@@ -1,135 +0,0 @@
-/*
- *  "High Precision Event Timer" based timekeeping.
- *
- *  Copyright (c) 1991,1992,1995  Linus Torvalds
- *  Copyright (c) 1994  Alan Modra
- *  Copyright (c) 1995  Markus Kuhn
- *  Copyright (c) 1996  Ingo Molnar
- *  Copyright (c) 1998  Andrea Arcangeli
- *  Copyright (c) 2002,2006  Vojtech Pavlik
- *  Copyright (c) 2003  Andi Kleen
- *  RTC support code taken from arch/i386/kernel/timers/time_hpet.c
- */
-
-#include <linux/clockchips.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/time.h>
-#include <linux/mca.h>
-#include <linux/nmi.h>
-
-#include <asm/i8253.h>
-#include <asm/hpet.h>
-#include <asm/vgtod.h>
-#include <asm/time.h>
-#include <asm/timer.h>
-
-volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
-
-unsigned long profile_pc(struct pt_regs *regs)
-{
-	unsigned long pc = instruction_pointer(regs);
-
-	/* Assume the lock function has either no stack frame or a copy
-	   of flags from PUSHF
-	   Eflags always has bits 22 and up cleared unlike kernel addresses. */
-	if (!user_mode_vm(regs) && in_lock_functions(pc)) {
-#ifdef CONFIG_FRAME_POINTER
-		return *(unsigned long *)(regs->bp + sizeof(long));
-#else
-		unsigned long *sp = (unsigned long *)regs->sp;
-		if (sp[0] >> 22)
-			return sp[0];
-		if (sp[1] >> 22)
-			return sp[1];
-#endif
-	}
-	return pc;
-}
-EXPORT_SYMBOL(profile_pc);
-
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	inc_irq_stat(irq0_irqs);
-
-	global_clock_event->event_handler(global_clock_event);
-
-#ifdef CONFIG_MCA
-	if (MCA_bus) {
-		u8 irq_v = inb_p(0x61);       /* read the current state */
-		outb_p(irq_v|0x80, 0x61);     /* reset the IRQ */
-	}
-#endif
-
-	return IRQ_HANDLED;
-}
-
-/* calibrate_cpu is used on systems with fixed rate TSCs to determine
- * processor frequency */
-#define TICK_COUNT 100000000
-unsigned long __init calibrate_cpu(void)
-{
-	int tsc_start, tsc_now;
-	int i, no_ctr_free;
-	unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
-	unsigned long flags;
-
-	for (i = 0; i < 4; i++)
-		if (avail_to_resrv_perfctr_nmi_bit(i))
-			break;
-	no_ctr_free = (i == 4);
-	if (no_ctr_free) {
-		WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
-		     "cpu_khz value may be incorrect.\n");
-		i = 3;
-		rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
-		wrmsrl(MSR_K7_EVNTSEL3, 0);
-		rdmsrl(MSR_K7_PERFCTR3, pmc3);
-	} else {
-		reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-		reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-	}
-	local_irq_save(flags);
-	/* start measuring cycles, incrementing from 0 */
-	wrmsrl(MSR_K7_PERFCTR0 + i, 0);
-	wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
-	rdtscl(tsc_start);
-	do {
-		rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
-		tsc_now = get_cycles();
-	} while ((tsc_now - tsc_start) < TICK_COUNT);
-
-	local_irq_restore(flags);
-	if (no_ctr_free) {
-		wrmsrl(MSR_K7_EVNTSEL3, 0);
-		wrmsrl(MSR_K7_PERFCTR3, pmc3);
-		wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
-	} else {
-		release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-		release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-	}
-
-	return pmc_now * tsc_khz / (tsc_now - tsc_start);
-}
-
-static struct irqaction irq0 = {
-	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER,
-	.name		= "timer"
-};
-
-void __init hpet_time_init(void)
-{
-	if (!hpet_enable())
-		setup_pit_timer();
-
-	setup_irq(0, &irq0);
-}
-
-void __init time_init(void)
-{
-	tsc_init();
-
-	late_time_init = choose_time_init();
-}

arch/x86/kernel/traps.c

@@ -59,6 +59,7 @@
 #include <asm/mach_traps.h>
 
 #ifdef CONFIG_X86_64
+#include <asm/x86_init.h>
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
 #else
@@ -972,7 +973,5 @@ void __init trap_init(void)
 	 */
 	cpu_init();
 
-#ifdef CONFIG_X86_32
-	x86_quirk_trap_init();
-#endif
+	x86_init.irqs.trap_init();
 }

arch/x86/kernel/tsc.c

@@ -17,6 +17,8 @@
 #include <asm/time.h>
 #include <asm/delay.h>
 #include <asm/hypervisor.h>
+#include <asm/nmi.h>
+#include <asm/x86_init.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -400,15 +402,9 @@ unsigned long native_calibrate_tsc(void)
 {
 	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags, latch, ms, fast_calibrate, hv_tsc_khz;
+	unsigned long flags, latch, ms, fast_calibrate;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
-	hv_tsc_khz = get_hypervisor_tsc_freq();
-	if (hv_tsc_khz) {
-		printk(KERN_INFO "TSC: Frequency read from the hypervisor\n");
-		return hv_tsc_khz;
-	}
-
 	local_irq_save(flags);
 	fast_calibrate = quick_pit_calibrate();
 	local_irq_restore(flags);
@@ -566,7 +562,7 @@ int recalibrate_cpu_khz(void)
 	unsigned long cpu_khz_old = cpu_khz;
 
 	if (cpu_has_tsc) {
-		tsc_khz = calibrate_tsc();
+		tsc_khz = x86_platform.calibrate_tsc();
 		cpu_khz = tsc_khz;
 		cpu_data(0).loops_per_jiffy =
 			cpufreq_scale(cpu_data(0).loops_per_jiffy,
@@ -860,15 +856,71 @@ static void __init init_tsc_clocksource(void)
 	clocksource_register(&clocksource_tsc);
 }
 
+#ifdef CONFIG_X86_64
+/*
+ * calibrate_cpu is used on systems with fixed rate TSCs to determine
+ * processor frequency
+ */
+#define TICK_COUNT 100000000
+static unsigned long __init calibrate_cpu(void)
+{
+	int tsc_start, tsc_now;
+	int i, no_ctr_free;
+	unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
+	unsigned long flags;
+
+	for (i = 0; i < 4; i++)
+		if (avail_to_resrv_perfctr_nmi_bit(i))
+			break;
+	no_ctr_free = (i == 4);
+	if (no_ctr_free) {
+		WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
+		     "cpu_khz value may be incorrect.\n");
+		i = 3;
+		rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
+		wrmsrl(MSR_K7_EVNTSEL3, 0);
+		rdmsrl(MSR_K7_PERFCTR3, pmc3);
+	} else {
+		reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+		reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+	}
+	local_irq_save(flags);
+	/* start measuring cycles, incrementing from 0 */
+	wrmsrl(MSR_K7_PERFCTR0 + i, 0);
+	wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
+	rdtscl(tsc_start);
+	do {
+		rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
+		tsc_now = get_cycles();
+	} while ((tsc_now - tsc_start) < TICK_COUNT);
+
+	local_irq_restore(flags);
+	if (no_ctr_free) {
+		wrmsrl(MSR_K7_EVNTSEL3, 0);
+		wrmsrl(MSR_K7_PERFCTR3, pmc3);
+		wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
+	} else {
+		release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+		release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+	}
+
+	return pmc_now * tsc_khz / (tsc_now - tsc_start);
+}
+#else
+static inline unsigned long calibrate_cpu(void) { return cpu_khz; }
+#endif
+
 void __init tsc_init(void)
 {
 	u64 lpj;
 	int cpu;
 
+	x86_init.timers.tsc_pre_init();
+
 	if (!cpu_has_tsc)
 		return;
 
-	tsc_khz = calibrate_tsc();
+	tsc_khz = x86_platform.calibrate_tsc();
 	cpu_khz = tsc_khz;
 
 	if (!tsc_khz) {
@@ -876,11 +928,9 @@ void __init tsc_init(void)
 		return;
 	}
 
-#ifdef CONFIG_X86_64
 	if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
 			(boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
 		cpu_khz = calibrate_cpu();
-#endif
 
 	printk("Detected %lu.%03lu MHz processor.\n",
 			(unsigned long)cpu_khz / 1000,

arch/x86/kernel/visws_quirks.c

@@ -30,6 +30,7 @@
 #include <asm/setup.h>
 #include <asm/apic.h>
 #include <asm/e820.h>
+#include <asm/time.h>
 #include <asm/io.h>
 
 #include <linux/kernel_stat.h>
@@ -53,7 +54,7 @@ int is_visws_box(void)
 	return visws_board_type >= 0;
 }
 
-static int __init visws_time_init(void)
+static void __init visws_time_init(void)
 {
 	printk(KERN_INFO "Starting Cobalt Timer system clock\n");
 
@@ -66,21 +67,13 @@ static int __init visws_time_init(void)
 	/* Enable (unmask) the timer interrupt */
 	co_cpu_write(CO_CPU_CTRL, co_cpu_read(CO_CPU_CTRL) & ~CO_CTRL_TIMEMASK);
 
-	/*
-	 * Zero return means the generic timer setup code will set up
-	 * the standard vector:
-	 */
-	return 0;
+	setup_default_timer_irq();
 }
 
-static int __init visws_pre_intr_init(void)
+/* Replaces the default init_ISA_irqs in the generic setup */
+static void __init visws_pre_intr_init(void)
 {
 	init_VISWS_APIC_irqs();
-
-	/*
-	 * We dont want ISA irqs to be set up by the generic code:
-	 */
-	return 1;
 }
 
 /* Quirk for machine specific memory setup. */
@@ -156,12 +149,8 @@ static void visws_machine_power_off(void)
 	outl(PIIX_SPECIAL_STOP, 0xCFC);
 }
 
-static int __init visws_get_smp_config(unsigned int early)
+static void __init visws_get_smp_config(unsigned int early)
 {
-	/*
-	 * Prevent MP-table parsing by the generic code:
-	 */
-	return 1;
 }
 
 /*
@@ -208,7 +197,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 	apic_version[m->apicid] = ver;
 }
 
-static int __init visws_find_smp_config(unsigned int reserve)
+static void __init visws_find_smp_config(unsigned int reserve)
 {
 	struct mpc_cpu *mp = phys_to_virt(CO_CPU_TAB_PHYS);
 	unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS));
@@ -230,21 +219,9 @@ static int __init visws_find_smp_config(unsigned int reserve)
 		MP_processor_info(mp++);
 
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
-
-	return 1;
 }
 
-static int visws_trap_init(void);
-
-static struct x86_quirks visws_x86_quirks __initdata = {
-	.arch_time_init		= visws_time_init,
-	.arch_pre_intr_init	= visws_pre_intr_init,
-	.arch_memory_setup	= visws_memory_setup,
-	.arch_intr_init		= NULL,
-	.arch_trap_init		= visws_trap_init,
-	.mach_get_smp_config	= visws_get_smp_config,
-	.mach_find_smp_config	= visws_find_smp_config,
-};
+static void visws_trap_init(void);
 
 void __init visws_early_detect(void)
 {
@@ -257,11 +234,14 @@ void __init visws_early_detect(void)
 		return;
 
 	/*
-	 * Install special quirks for timer, interrupt and memory setup:
-	 * Fall back to generic behavior for traps:
-	 * Override generic MP-table parsing:
+	 * Override the default platform setup functions
 	 */
-	x86_quirks = &visws_x86_quirks;
+	x86_init.resources.memory_setup = visws_memory_setup;
+	x86_init.mpparse.get_smp_config = visws_get_smp_config;
+	x86_init.mpparse.find_smp_config = visws_find_smp_config;
+	x86_init.irqs.pre_vector_init = visws_pre_intr_init;
+	x86_init.irqs.trap_init = visws_trap_init;
+	x86_init.timers.timer_init = visws_time_init;
 
 	/*
 	 * Install reboot quirks:
@@ -400,12 +380,10 @@ static __init void cobalt_init(void)
 		co_apic_read(CO_APIC_ID));
 }
 
-static int __init visws_trap_init(void)
+static void __init visws_trap_init(void)
 {
 	lithium_init();
 	cobalt_init();
-
-	return 1;
 }
 
 /*

arch/x86/kernel/vmi_32.c

@@ -817,15 +817,15 @@ static inline int __init activate_vmi(void)
 		vmi_timer_ops.set_alarm = vmi_get_function(VMI_CALL_SetAlarm);
 		vmi_timer_ops.cancel_alarm =
 			 vmi_get_function(VMI_CALL_CancelAlarm);
-		pv_time_ops.time_init = vmi_time_init;
-		pv_time_ops.get_wallclock = vmi_get_wallclock;
-		pv_time_ops.set_wallclock = vmi_set_wallclock;
+		x86_init.timers.timer_init = vmi_time_init;
 #ifdef CONFIG_X86_LOCAL_APIC
-		pv_apic_ops.setup_boot_clock = vmi_time_bsp_init;
-		pv_apic_ops.setup_secondary_clock = vmi_time_ap_init;
+		x86_init.timers.setup_percpu_clockev = vmi_time_bsp_init;
+		x86_cpuinit.setup_percpu_clockev = vmi_time_ap_init;
 #endif
 		pv_time_ops.sched_clock = vmi_sched_clock;
-		pv_time_ops.get_tsc_khz = vmi_tsc_khz;
+		x86_platform.calibrate_tsc = vmi_tsc_khz;
+		x86_platform.get_wallclock = vmi_get_wallclock;
+		x86_platform.set_wallclock = vmi_set_wallclock;
 
 		/* We have true wallclock functions; disable CMOS clock sync */
 		no_sync_cmos_clock = 1;

arch/x86/kernel/vmiclock_32.c

@@ -68,7 +68,7 @@ unsigned long long vmi_sched_clock(void)
 	return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE));
 }
 
-/* paravirt_ops.get_tsc_khz = vmi_tsc_khz */
+/* x86_platform.calibrate_tsc = vmi_tsc_khz */
 unsigned long vmi_tsc_khz(void)
 {
 	unsigned long long khz;

arch/x86/kernel/x86_init.c

@@ -0,0 +1,75 @@
+/*
+ * Copyright (C) 2009 Thomas Gleixner <tglx@linutronix.de>
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+#include <linux/init.h>
+
+#include <asm/bios_ebda.h>
+#include <asm/paravirt.h>
+#include <asm/mpspec.h>
+#include <asm/setup.h>
+#include <asm/apic.h>
+#include <asm/e820.h>
+#include <asm/time.h>
+#include <asm/irq.h>
+#include <asm/tsc.h>
+
+void __cpuinit x86_init_noop(void) { }
+void __init x86_init_uint_noop(unsigned int unused) { }
+void __init x86_init_pgd_noop(pgd_t *unused) { }
+
+/*
+ * The platform setup functions are preset with the default functions
+ * for standard PC hardware.
+ */
+struct x86_init_ops x86_init __initdata = {
+
+	.resources = {
+		.probe_roms		= x86_init_noop,
+		.reserve_resources	= reserve_standard_io_resources,
+		.memory_setup		= default_machine_specific_memory_setup,
+	},
+
+	.mpparse = {
+		.mpc_record		= x86_init_uint_noop,
+		.setup_ioapic_ids	= x86_init_noop,
+		.mpc_apic_id		= default_mpc_apic_id,
+		.smp_read_mpc_oem	= default_smp_read_mpc_oem,
+		.mpc_oem_bus_info	= default_mpc_oem_bus_info,
+		.find_smp_config	= default_find_smp_config,
+		.get_smp_config		= default_get_smp_config,
+	},
+
+	.irqs = {
+		.pre_vector_init	= init_ISA_irqs,
+		.intr_init		= native_init_IRQ,
+		.trap_init		= x86_init_noop,
+	},
+
+	.oem = {
+		.arch_setup		= x86_init_noop,
+		.banner			= default_banner,
+	},
+
+	.paging = {
+		.pagetable_setup_start	= native_pagetable_setup_start,
+		.pagetable_setup_done	= native_pagetable_setup_done,
+	},
+
+	.timers = {
+		.setup_percpu_clockev	= setup_boot_APIC_clock,
+		.tsc_pre_init		= x86_init_noop,
+		.timer_init		= hpet_time_init,
+	},
+};
+
+struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
+	.setup_percpu_clockev		= setup_secondary_APIC_clock,
+};
+
+struct x86_platform_ops x86_platform = {
+	.calibrate_tsc			= native_calibrate_tsc,
+	.get_wallclock			= mach_get_cmos_time,
+	.set_wallclock			= mach_set_rtc_mmss,
+};

arch/x86/lguest/boot.c

@@ -1262,7 +1262,6 @@ __init void lguest_init(void)
 	 */
 
 	/* Interrupt-related operations */
-	pv_irq_ops.init_IRQ = lguest_init_IRQ;
 	pv_irq_ops.save_fl = PV_CALLEE_SAVE(save_fl);
 	pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(lg_restore_fl);
 	pv_irq_ops.irq_disable = PV_CALLEE_SAVE(irq_disable);
@@ -1270,7 +1269,6 @@ __init void lguest_init(void)
 	pv_irq_ops.safe_halt = lguest_safe_halt;
 
 	/* Setup operations */
-	pv_init_ops.memory_setup = lguest_memory_setup;
 	pv_init_ops.patch = lguest_patch;
 
 	/* Intercepts of various CPU instructions */
@@ -1320,10 +1318,11 @@ __init void lguest_init(void)
 	set_lguest_basic_apic_ops();
 #endif
 
-	/* Time operations */
-	pv_time_ops.get_wallclock = lguest_get_wallclock;
-	pv_time_ops.time_init = lguest_time_init;
-	pv_time_ops.get_tsc_khz = lguest_tsc_khz;
+	x86_init.resources.memory_setup = lguest_memory_setup;
+	x86_init.irqs.intr_init = lguest_init_IRQ;
+	x86_init.timers.timer_init = lguest_time_init;
+	x86_platform.calibrate_tsc = lguest_tsc_khz;
+	x86_platform.get_wallclock =  lguest_get_wallclock;
 
 	/*
 	 * Now is a good time to look at the implementations of these functions

arch/x86/xen/enlighten.c

@@ -912,19 +912,9 @@ static const struct pv_info xen_info __initdata = {
 
 static const struct pv_init_ops xen_init_ops __initdata = {
 	.patch = xen_patch,
-
-	.banner = xen_banner,
-	.memory_setup = xen_memory_setup,
-	.arch_setup = xen_arch_setup,
-	.post_allocator_init = xen_post_allocator_init,
 };
 
 static const struct pv_time_ops xen_time_ops __initdata = {
-	.time_init = xen_time_init,
-
-	.set_wallclock = xen_set_wallclock,
-	.get_wallclock = xen_get_wallclock,
-	.get_tsc_khz = xen_tsc_khz,
 	.sched_clock = xen_sched_clock,
 };
 
@@ -990,8 +980,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 
 static const struct pv_apic_ops xen_apic_ops __initdata = {
 #ifdef CONFIG_X86_LOCAL_APIC
-	.setup_boot_clock = paravirt_nop,
-	.setup_secondary_clock = paravirt_nop,
 	.startup_ipi_hook = paravirt_nop,
 #endif
 };
@@ -1070,7 +1058,18 @@ asmlinkage void __init xen_start_kernel(void)
 	pv_time_ops = xen_time_ops;
 	pv_cpu_ops = xen_cpu_ops;
 	pv_apic_ops = xen_apic_ops;
-	pv_mmu_ops = xen_mmu_ops;
+
+	x86_init.resources.memory_setup = xen_memory_setup;
+	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;
 
 	/*
 	 * Set up some pagetable state before starting to set any ptes.
@@ -1095,6 +1094,7 @@ asmlinkage void __init xen_start_kernel(void)
 	 */
 	xen_setup_stackprotector();
 
+	xen_init_mmu_ops();
 	xen_init_irq_ops();
 	xen_init_cpuid_mask();
 

arch/x86/xen/irq.c

@@ -1,5 +1,7 @@
 #include <linux/hardirq.h>
 
+#include <asm/x86_init.h>
+
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
 #include <xen/interface/vcpu.h>
@@ -112,8 +114,6 @@ static void xen_halt(void)
 }
 
 static const struct pv_irq_ops xen_irq_ops __initdata = {
-	.init_IRQ = xen_init_IRQ,
-
 	.save_fl = PV_CALLEE_SAVE(xen_save_fl),
 	.restore_fl = PV_CALLEE_SAVE(xen_restore_fl),
 	.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
@@ -129,4 +129,5 @@ static const struct pv_irq_ops xen_irq_ops __initdata = {
 void __init xen_init_irq_ops()
 {
 	pv_irq_ops = xen_irq_ops;
+	x86_init.irqs.intr_init = xen_init_IRQ;
 }

arch/x86/xen/mmu.c

@@ -1229,9 +1229,12 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 }
 
+static void xen_post_allocator_init(void);
+
 static __init void xen_pagetable_setup_done(pgd_t *base)
 {
 	xen_setup_shared_info();
+	xen_post_allocator_init();
 }
 
 static void xen_write_cr2(unsigned long cr2)
@@ -1841,7 +1844,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 }
 
-__init void xen_post_allocator_init(void)
+static __init void xen_post_allocator_init(void)
 {
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
@@ -1875,10 +1878,7 @@ static void xen_leave_lazy_mmu(void)
 	preempt_enable();
 }
 
-const struct pv_mmu_ops xen_mmu_ops __initdata = {
-	.pagetable_setup_start = xen_pagetable_setup_start,
-	.pagetable_setup_done = xen_pagetable_setup_done,
-
+static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.read_cr2 = xen_read_cr2,
 	.write_cr2 = xen_write_cr2,
 
@@ -1954,6 +1954,12 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.set_fixmap = xen_set_fixmap,
 };
 
+void __init xen_init_mmu_ops(void)
+{
+	x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
+	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
+	pv_mmu_ops = xen_mmu_ops;
+}
 
 #ifdef CONFIG_XEN_DEBUG_FS
 

arch/x86/xen/mmu.h

@@ -59,5 +59,5 @@ void  xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 
 unsigned long xen_read_cr2_direct(void);
 
-extern const struct pv_mmu_ops xen_mmu_ops;
+extern void xen_init_mmu_ops(void);
 #endif	/* _XEN_MMU_H */

arch/x86/xen/xen-ops.h

@@ -30,8 +30,6 @@ pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_ident_map_ISA(void);
 void xen_reserve_top(void);
 
-void xen_post_allocator_init(void);
-
 char * __init xen_memory_setup(void);
 void __init xen_arch_setup(void);
 void __init xen_init_IRQ(void);