Merge branch 'x86-core-v2-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

This merges in:

  x86/build, x86/microcode, x86/spinlocks, x86/memory-corruption-check,
  x86/early-printk, x86/xsave, x86/quirks, x86/setup, x86/signal,
  core/signal, x86/urgent, x86/xen

* 'x86-core-v2-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (142 commits)
  x86: make processor type select depend on CONFIG_EMBEDDED
  x86: extend processor type select help text
  x86, amd-iommu: propagate PCI device enabling error
  warnings: fix arch/x86/kernel/io_apic_64.c
  warnings: fix arch/x86/kernel/early_printk.c
  x86, fpu: check __clear_user() return value
  x86: memory corruption check - cleanup
  x86: ioperm user_regset
  xen: do not reserve 2 pages of padding between hypervisor and fixmap.
  xen: use spin_lock_nest_lock when pinning a pagetable
  x86: xsave: set FP, SSE bits in the xsave header in the user sigcontext
  x86: xsave: fix error condition in save_i387_xstate()
  x86: SB450: deprioritize DMI quirks
  x86: SB450: skip IRQ0 override if it is not routed to INT2 of IOAPIC
  x86: replace a magic number with a named constant in the VESA boot code
  x86 setup: remove IMAGE_OFFSET
  x86 setup: remove DEF_INITSEG and DEF_SETUPSEG
  Revert "x86: fix ghost EDD devices in /sys again"
  x86 setup: fix ghost entries under /sys/firmware/edd take 3
  x86: signal: remove indent in restore_sigcontext()
  ...

25 files changed, 395 insertions, 172 deletions

diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
index 8786e01e0db8..969570167e9e 100644
--- a/include/asm-generic/siginfo.h
+++ b/include/asm-generic/siginfo.h
@@ -199,6 +199,8 @@ typedef struct siginfo {
  */
 #define TRAP_BRKPT	(__SI_FAULT|1)	/* process breakpoint */
 #define TRAP_TRACE	(__SI_FAULT|2)	/* process trace trap */
+#define TRAP_BRANCH     (__SI_FAULT|3)  /* process taken branch trap */
+#define TRAP_HWBKPT     (__SI_FAULT|4)  /* hardware breakpoint/watchpoint */
 #define NSIGTRAP	2
 
 /*
diff --git a/include/asm-parisc/siginfo.h b/include/asm-parisc/siginfo.h
index d4909f55fe35..d7034728f377 100644
--- a/include/asm-parisc/siginfo.h
+++ b/include/asm-parisc/siginfo.h
@@ -3,11 +3,6 @@
 
 #include <asm-generic/siginfo.h>
 
-/*
- * SIGTRAP si_codes
- */
-#define TRAP_BRANCH	(__SI_FAULT|3)	/* process taken branch trap */
-#define TRAP_HWBKPT	(__SI_FAULT|4)	/* hardware breakpoint or watchpoint */
 #undef NSIGTRAP
 #define NSIGTRAP	4
 
diff --git a/include/asm-x86/bios_ebda.h b/include/asm-x86/bios_ebda.h
index ec42ed874591..79b4b88505d7 100644
--- a/include/asm-x86/bios_ebda.h
+++ b/include/asm-x86/bios_ebda.h
@@ -16,4 +16,21 @@ static inline unsigned int get_bios_ebda(void)
 
 void reserve_ebda_region(void);
 
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+/*
+ * This is obviously not a great place for this, but we want to be
+ * able to scatter it around anywhere in the kernel.
+ */
+void check_for_bios_corruption(void);
+void start_periodic_check_for_corruption(void);
+#else
+static inline void check_for_bios_corruption(void)
+{
+}
+
+static inline void start_periodic_check_for_corruption(void)
+{
+}
+#endif
+
 #endif /* ASM_X86__BIOS_EBDA_H */
diff --git a/include/asm-x86/boot.h b/include/asm-x86/boot.h
index 825de5dc867c..1d63bd5d5946 100644
--- a/include/asm-x86/boot.h
+++ b/include/asm-x86/boot.h
@@ -2,9 +2,7 @@
 #define ASM_X86__BOOT_H
 
 /* Don't touch these, unless you really know what you're doing. */
-#define DEF_INITSEG	0x9000
 #define DEF_SYSSEG	0x1000
-#define DEF_SETUPSEG	0x9020
 #define DEF_SYSSIZE	0x7F00
 
 /* Internal svga startup constants */
diff --git a/include/asm-x86/desc.h b/include/asm-x86/desc.h
index b73fea54def2..ebc307817e98 100644
--- a/include/asm-x86/desc.h
+++ b/include/asm-x86/desc.h
@@ -24,6 +24,11 @@ static inline void fill_ldt(struct desc_struct *desc,
 	desc->d = info->seg_32bit;
 	desc->g = info->limit_in_pages;
 	desc->base2 = (info->base_addr & 0xff000000) >> 24;
+	/*
+	 * Don't allow setting of the lm bit. It is useless anyway
+	 * because 64bit system calls require __USER_CS:
+	 */
+	desc->l = 0;
 }
 
 extern struct desc_ptr idt_descr;
@@ -97,7 +102,15 @@ static inline int desc_empty(const void *ptr)
 	native_write_gdt_entry(dt, entry, desc, type)
 #define write_idt_entry(dt, entry, g)		\
 	native_write_idt_entry(dt, entry, g)
-#endif
+
+static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
+{
+}
+
+static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
+{
+}
+#endif	/* CONFIG_PARAVIRT */
 
 static inline void native_write_idt_entry(gate_desc *idt, int entry,
 					  const gate_desc *gate)
diff --git a/include/asm-x86/microcode.h b/include/asm-x86/microcode.h
new file mode 100644
index 000000000000..62c793bb70ca
--- /dev/null
+++ b/include/asm-x86/microcode.h
@@ -0,0 +1,47 @@
+#ifndef ASM_X86__MICROCODE_H
+#define ASM_X86__MICROCODE_H
+
+struct cpu_signature {
+	unsigned int sig;
+	unsigned int pf;
+	unsigned int rev;
+};
+
+struct device;
+
+struct microcode_ops {
+	int  (*request_microcode_user) (int cpu, const void __user *buf, size_t size);
+	int  (*request_microcode_fw) (int cpu, struct device *device);
+
+	void (*apply_microcode) (int cpu);
+
+	int  (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
+	void (*microcode_fini_cpu) (int cpu);
+};
+
+struct ucode_cpu_info {
+	struct cpu_signature cpu_sig;
+	int valid;
+	void *mc;
+};
+extern struct ucode_cpu_info ucode_cpu_info[];
+
+#ifdef CONFIG_MICROCODE_INTEL
+extern struct microcode_ops * __init init_intel_microcode(void);
+#else
+static inline struct microcode_ops * __init init_intel_microcode(void)
+{
+	return NULL;
+}
+#endif /* CONFIG_MICROCODE_INTEL */
+
+#ifdef CONFIG_MICROCODE_AMD
+extern struct microcode_ops * __init init_amd_microcode(void);
+#else
+static inline struct microcode_ops * __init init_amd_microcode(void)
+{
+	return NULL;
+}
+#endif
+
+#endif /* ASM_X86__MICROCODE_H */
diff --git a/include/asm-x86/mmzone_64.h b/include/asm-x86/mmzone_64.h
index 626b03a14875..6480f3333b2a 100644
--- a/include/asm-x86/mmzone_64.h
+++ b/include/asm-x86/mmzone_64.h
@@ -7,7 +7,7 @@
 
 #ifdef CONFIG_NUMA
 
-#define VIRTUAL_BUG_ON(x)
+#include <linux/mmdebug.h>
 
 #include <asm/smp.h>
 
@@ -29,7 +29,6 @@ static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
 {
 	unsigned nid;
 	VIRTUAL_BUG_ON(!memnodemap);
-	VIRTUAL_BUG_ON((addr >> memnode_shift) >= memnodemapsize);
 	nid = memnodemap[addr >> memnode_shift];
 	VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]);
 	return nid;
diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
index 72f7305682c6..9c5a737a9af9 100644
--- a/include/asm-x86/page_32.h
+++ b/include/asm-x86/page_32.h
@@ -73,7 +73,12 @@ typedef struct page *pgtable_t;
 #endif
 
 #ifndef __ASSEMBLY__
+#define __phys_addr_const(x)	((x) - PAGE_OFFSET)
+#ifdef CONFIG_DEBUG_VIRTUAL
+extern unsigned long __phys_addr(unsigned long);
+#else
 #define __phys_addr(x)		((x) - PAGE_OFFSET)
+#endif
 #define __phys_reloc_hide(x)	RELOC_HIDE((x), 0)
 
 #ifdef CONFIG_FLATMEM
diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
index d7d358a43996..8d6ae2f760d0 100644
--- a/include/asm-x86/paravirt.h
+++ b/include/asm-x86/paravirt.h
@@ -124,6 +124,9 @@ struct pv_cpu_ops {
 				int entrynum, const void *desc, int size);
 	void (*write_idt_entry)(gate_desc *,
 				int entrynum, const gate_desc *gate);
+	void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
+	void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
+
 	void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
 
 	void (*set_iopl_mask)(unsigned mask);
@@ -325,6 +328,7 @@ struct pv_lock_ops {
 	int (*spin_is_locked)(struct raw_spinlock *lock);
 	int (*spin_is_contended)(struct raw_spinlock *lock);
 	void (*spin_lock)(struct raw_spinlock *lock);
+	void (*spin_lock_flags)(struct raw_spinlock *lock, unsigned long flags);
 	int (*spin_trylock)(struct raw_spinlock *lock);
 	void (*spin_unlock)(struct raw_spinlock *lock);
 };
@@ -830,6 +834,16 @@ do {							\
 	(aux) = __aux;					\
 } while (0)
 
+static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
+{
+	PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
+}
+
+static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
+{
+	PVOP_VCALL2(pv_cpu_ops.free_ldt, ldt, entries);
+}
+
 static inline void load_TR_desc(void)
 {
 	PVOP_VCALL0(pv_cpu_ops.load_tr_desc);
@@ -1394,6 +1408,12 @@ static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
 	PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
 }
 
+static __always_inline void __raw_spin_lock_flags(struct raw_spinlock *lock,
+						  unsigned long flags)
+{
+	PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags);
+}
+
 static __always_inline int __raw_spin_trylock(struct raw_spinlock *lock)
 {
 	return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index c7d35464a4bb..ee7cbb30773a 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -586,41 +586,6 @@ static inline void clear_in_cr4(unsigned long mask)
 	write_cr4(cr4);
 }
 
-struct microcode_header {
-	unsigned int		hdrver;
-	unsigned int		rev;
-	unsigned int		date;
-	unsigned int		sig;
-	unsigned int		cksum;
-	unsigned int		ldrver;
-	unsigned int		pf;
-	unsigned int		datasize;
-	unsigned int		totalsize;
-	unsigned int		reserved[3];
-};
-
-struct microcode {
-	struct microcode_header	hdr;
-	unsigned int		bits[0];
-};
-
-typedef struct microcode	microcode_t;
-typedef struct microcode_header	microcode_header_t;
-
-/* microcode format is extended from prescott processors */
-struct extended_signature {
-	unsigned int		sig;
-	unsigned int		pf;
-	unsigned int		cksum;
-};
-
-struct extended_sigtable {
-	unsigned int		count;
-	unsigned int		cksum;
-	unsigned int		reserved[3];
-	struct extended_signature sigs[0];
-};
-
 typedef struct {
 	unsigned long		seg;
 } mm_segment_t;
diff --git a/include/asm-x86/ptrace.h b/include/asm-x86/ptrace.h
index d64a61097165..ac578f11c1c5 100644
--- a/include/asm-x86/ptrace.h
+++ b/include/asm-x86/ptrace.h
@@ -177,11 +177,11 @@ convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
 
 #ifdef CONFIG_X86_32
 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
-			 int error_code);
-#else
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+			 int error_code, int si_code);
 #endif
 
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
 extern long syscall_trace_enter(struct pt_regs *);
 extern void syscall_trace_leave(struct pt_regs *);
 
diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h
index 29324c103341..6df2615f9138 100644
--- a/include/asm-x86/smp.h
+++ b/include/asm-x86/smp.h
@@ -50,12 +50,16 @@ extern struct {
 struct smp_ops {
 	void (*smp_prepare_boot_cpu)(void);
 	void (*smp_prepare_cpus)(unsigned max_cpus);
-	int (*cpu_up)(unsigned cpu);
 	void (*smp_cpus_done)(unsigned max_cpus);
 
 	void (*smp_send_stop)(void);
 	void (*smp_send_reschedule)(int cpu);
 
+	int (*cpu_up)(unsigned cpu);
+	int (*cpu_disable)(void);
+	void (*cpu_die)(unsigned int cpu);
+	void (*play_dead)(void);
+
 	void (*send_call_func_ipi)(cpumask_t mask);
 	void (*send_call_func_single_ipi)(int cpu);
 };
@@ -94,6 +98,21 @@ static inline int __cpu_up(unsigned int cpu)
 	return smp_ops.cpu_up(cpu);
 }
 
+static inline int __cpu_disable(void)
+{
+	return smp_ops.cpu_disable();
+}
+
+static inline void __cpu_die(unsigned int cpu)
+{
+	smp_ops.cpu_die(cpu);
+}
+
+static inline void play_dead(void)
+{
+	smp_ops.play_dead();
+}
+
 static inline void smp_send_reschedule(int cpu)
 {
 	smp_ops.smp_send_reschedule(cpu);
@@ -109,16 +128,19 @@ static inline void arch_send_call_function_ipi(cpumask_t mask)
 	smp_ops.send_call_func_ipi(mask);
 }
 
+void cpu_disable_common(void);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void native_smp_cpus_done(unsigned int max_cpus);
 int native_cpu_up(unsigned int cpunum);
+int native_cpu_disable(void);
+void native_cpu_die(unsigned int cpu);
+void native_play_dead(void);
+void play_dead_common(void);
+
 void native_send_call_func_ipi(cpumask_t mask);
 void native_send_call_func_single_ipi(int cpu);
 
-extern int __cpu_disable(void);
-extern void __cpu_die(unsigned int cpu);
-
 void smp_store_cpu_info(int id);
 #define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
 
@@ -205,9 +227,5 @@ static inline int hard_smp_processor_id(void)
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
-#ifdef CONFIG_HOTPLUG_CPU
-extern void cpu_uninit(void);
-#endif
-
 #endif /* __ASSEMBLY__ */
 #endif /* ASM_X86__SMP_H */
diff --git a/include/asm-x86/spinlock.h b/include/asm-x86/spinlock.h
index 93adae338ac6..157ff7fab97a 100644
--- a/include/asm-x86/spinlock.h
+++ b/include/asm-x86/spinlock.h
@@ -21,8 +21,10 @@
 
 #ifdef CONFIG_X86_32
 # define LOCK_PTR_REG "a"
+# define REG_PTR_MODE "k"
 #else
 # define LOCK_PTR_REG "D"
+# define REG_PTR_MODE "q"
 #endif
 
 #if defined(CONFIG_X86_32) && \
@@ -54,19 +56,7 @@
  * much between them in performance though, especially as locks are out of line.
  */
 #if (NR_CPUS < 256)
-static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
-{
-	int tmp = ACCESS_ONCE(lock->slock);
-
-	return (((tmp >> 8) & 0xff) != (tmp & 0xff));
-}
-
-static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
-{
-	int tmp = ACCESS_ONCE(lock->slock);
-
-	return (((tmp >> 8) - tmp) & 0xff) > 1;
-}
+#define TICKET_SHIFT 8
 
 static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 {
@@ -89,19 +79,17 @@ static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 
 static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
 {
-	int tmp;
-	short new;
+	int tmp, new;
 
-	asm volatile("movw %2,%w0\n\t"
+	asm volatile("movzwl %2, %0\n\t"
 		     "cmpb %h0,%b0\n\t"
+		     "leal 0x100(%" REG_PTR_MODE "0), %1\n\t"
 		     "jne 1f\n\t"
-		     "movw %w0,%w1\n\t"
-		     "incb %h1\n\t"
 		     LOCK_PREFIX "cmpxchgw %w1,%2\n\t"
 		     "1:"
 		     "sete %b1\n\t"
 		     "movzbl %b1,%0\n\t"
-		     : "=&a" (tmp), "=Q" (new), "+m" (lock->slock)
+		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
 		     :
 		     : "memory", "cc");
 
@@ -116,19 +104,7 @@ static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 		     : "memory", "cc");
 }
 #else
-static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
-{
-	int tmp = ACCESS_ONCE(lock->slock);
-
-	return (((tmp >> 16) & 0xffff) != (tmp & 0xffff));
-}
-
-static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
-{
-	int tmp = ACCESS_ONCE(lock->slock);
-
-	return (((tmp >> 16) - tmp) & 0xffff) > 1;
-}
+#define TICKET_SHIFT 16
 
 static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 {
@@ -146,7 +122,7 @@ static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 		     /* don't need lfence here, because loads are in-order */
 		     "jmp 1b\n"
 		     "2:"
-		     : "+Q" (inc), "+m" (lock->slock), "=r" (tmp)
+		     : "+r" (inc), "+m" (lock->slock), "=&r" (tmp)
 		     :
 		     : "memory", "cc");
 }
@@ -160,13 +136,13 @@ static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
 		     "movl %0,%1\n\t"
 		     "roll $16, %0\n\t"
 		     "cmpl %0,%1\n\t"
+		     "leal 0x00010000(%" REG_PTR_MODE "0), %1\n\t"
 		     "jne 1f\n\t"
-		     "addl $0x00010000, %1\n\t"
 		     LOCK_PREFIX "cmpxchgl %1,%2\n\t"
 		     "1:"
 		     "sete %b1\n\t"
 		     "movzbl %b1,%0\n\t"
-		     : "=&a" (tmp), "=r" (new), "+m" (lock->slock)
+		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
 		     :
 		     : "memory", "cc");
 
@@ -182,7 +158,19 @@ static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 }
 #endif
 
-#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
+static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
+{
+	int tmp = ACCESS_ONCE(lock->slock);
+
+	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1 << TICKET_SHIFT) - 1));
+}
+
+static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
+{
+	int tmp = ACCESS_ONCE(lock->slock);
+
+	return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
+}
 
 #ifdef CONFIG_PARAVIRT
 /*
@@ -272,6 +260,13 @@ static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
 {
 	__ticket_spin_unlock(lock);
 }
+
+static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
+						  unsigned long flags)
+{
+	__raw_spin_lock(lock);
+}
+
 #endif	/* CONFIG_PARAVIRT */
 
 static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
diff --git a/include/asm-x86/tlbflush.h b/include/asm-x86/tlbflush.h
index ef68b76dc3c5..3cdd08b5bdb7 100644
--- a/include/asm-x86/tlbflush.h
+++ b/include/asm-x86/tlbflush.h
@@ -119,6 +119,10 @@ static inline void native_flush_tlb_others(const cpumask_t *cpumask,
 {
 }
 
+static inline void reset_lazy_tlbstate(void)
+{
+}
+
 #else  /* SMP */
 
 #include <asm/smp.h>
@@ -151,6 +155,12 @@ struct tlb_state {
 	char __cacheline_padding[L1_CACHE_BYTES-8];
 };
 DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
+
+void reset_lazy_tlbstate(void);
+#else
+static inline void reset_lazy_tlbstate(void)
+{
+}
 #endif
 
 #endif	/* SMP */
diff --git a/include/asm-x86/traps.h b/include/asm-x86/traps.h
index 2ccebc6fb0b0..7a692baa51ae 100644
--- a/include/asm-x86/traps.h
+++ b/include/asm-x86/traps.h
@@ -1,6 +1,8 @@
 #ifndef ASM_X86__TRAPS_H
 #define ASM_X86__TRAPS_H
 
+#include <asm/debugreg.h>
+
 /* Common in X86_32 and X86_64 */
 asmlinkage void divide_error(void);
 asmlinkage void debug(void);
@@ -36,6 +38,16 @@ void do_invalid_op(struct pt_regs *, long);
 void do_general_protection(struct pt_regs *, long);
 void do_nmi(struct pt_regs *, long);
 
+static inline int get_si_code(unsigned long condition)
+{
+	if (condition & DR_STEP)
+		return TRAP_TRACE;
+	else if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3))
+		return TRAP_HWBKPT;
+	else
+		return TRAP_BRKPT;
+}
+
 extern int panic_on_unrecovered_nmi;
 extern int kstack_depth_to_print;
 
diff --git a/include/asm-x86/xen/hypervisor.h b/include/asm-x86/xen/hypervisor.h
index 0ef3a88b869d..445a24759560 100644
--- a/include/asm-x86/xen/hypervisor.h
+++ b/include/asm-x86/xen/hypervisor.h
@@ -54,7 +54,6 @@
 /* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
-#define is_initial_xendomain() (xen_start_info->flags & SIF_INITDOMAIN)
 
 /* arch/i386/mach-xen/evtchn.c */
 /* Force a proper event-channel callback from Xen. */
@@ -67,6 +66,17 @@ u64 jiffies_to_st(unsigned long jiffies);
 #define MULTI_UVMFLAGS_INDEX 3
 #define MULTI_UVMDOMID_INDEX 4
 
-#define is_running_on_xen()	(xen_start_info ? 1 : 0)
+enum xen_domain_type {
+	XEN_NATIVE,
+	XEN_PV_DOMAIN,
+	XEN_HVM_DOMAIN,
+};
+
+extern enum xen_domain_type xen_domain_type;
+
+#define xen_domain()		(xen_domain_type != XEN_NATIVE)
+#define xen_pv_domain()		(xen_domain_type == XEN_PV_DOMAIN)
+#define xen_initial_domain()	(xen_pv_domain() && xen_start_info->flags & SIF_INITDOMAIN)
+#define xen_hvm_domain()	(xen_domain_type == XEN_HVM_DOMAIN)
 
 #endif /* ASM_X86__XEN__HYPERVISOR_H */
diff --git a/include/linux/elf.h b/include/linux/elf.h
index edc3dac3f02f..0b61ca41a044 100644
--- a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -360,6 +360,7 @@ typedef struct elf64_shdr {
 #define NT_PPC_SPE	0x101		/* PowerPC SPE/EVR registers */
 #define NT_PPC_VSX	0x102		/* PowerPC VSX registers */
 #define NT_386_TLS	0x200		/* i386 TLS slots (struct user_desc) */
+#define NT_386_IOPERM	0x201		/* x86 io permission bitmap (1=deny) */
 
 
 /* Note header in a PT_NOTE section */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2651f805ba6d..75d81f157d2e 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -182,7 +182,7 @@ extern int vsscanf(const char *, const char *, va_list)
 
 extern int get_option(char **str, int *pint);
 extern char *get_options(const char *str, int nints, int *ints);
-extern unsigned long long memparse(char *ptr, char **retptr);
+extern unsigned long long memparse(const char *ptr, char **retptr);
 
 extern int core_kernel_text(unsigned long addr);
 extern int __kernel_text_address(unsigned long addr);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 72a15dc26bbf..c61ba10768ea 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -7,6 +7,7 @@
 
 #include <linux/gfp.h>
 #include <linux/list.h>
+#include <linux/mmdebug.h>
 #include <linux/mmzone.h>
 #include <linux/rbtree.h>
 #include <linux/prio_tree.h>
@@ -219,12 +220,6 @@ struct inode;
  */
 #include <linux/page-flags.h>
 
-#ifdef CONFIG_DEBUG_VM
-#define VM_BUG_ON(cond) BUG_ON(cond)
-#else
-#define VM_BUG_ON(condition) do { } while(0)
-#endif
-
 /*
  * Methods to modify the page usage count.
  *
@@ -919,7 +914,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 }
 #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
 
-#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+#if USE_SPLIT_PTLOCKS
 /*
  * We tuck a spinlock to guard each pagetable page into its struct page,
  * at page->private, with BUILD_BUG_ON to make sure that this will not
@@ -932,14 +927,14 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 } while (0)
 #define pte_lock_deinit(page)	((page)->mapping = NULL)
 #define pte_lockptr(mm, pmd)	({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
-#else
+#else	/* !USE_SPLIT_PTLOCKS */
 /*
  * We use mm->page_table_lock to guard all pagetable pages of the mm.
  */
 #define pte_lock_init(page)	do {} while (0)
 #define pte_lock_deinit(page)	do {} while (0)
 #define pte_lockptr(mm, pmd)	({(void)(pmd); &(mm)->page_table_lock;})
-#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+#endif /* USE_SPLIT_PTLOCKS */
 
 static inline void pgtable_page_ctor(struct page *page)
 {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bf334138c7c1..9d49fa36bbef 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -21,11 +21,13 @@
 
 struct address_space;
 
-#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+#define USE_SPLIT_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
+
+#if USE_SPLIT_PTLOCKS
 typedef atomic_long_t mm_counter_t;
-#else  /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+#else  /* !USE_SPLIT_PTLOCKS */
 typedef unsigned long mm_counter_t;
-#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+#endif /* !USE_SPLIT_PTLOCKS */
 
 /*
  * Each physical page in the system has a struct page associated with
@@ -65,7 +67,7 @@ struct page {
 						 * see PAGE_MAPPING_ANON below.
 						 */
 	    };
-#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+#if USE_SPLIT_PTLOCKS
 	    spinlock_t ptl;
 #endif
 	    struct kmem_cache *slab;	/* SLUB: Pointer to slab */
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
new file mode 100644
index 000000000000..8a5509877192
--- /dev/null
+++ b/include/linux/mmdebug.h
@@ -0,0 +1,18 @@
+#ifndef LINUX_MM_DEBUG_H
+#define LINUX_MM_DEBUG_H 1
+
+#include <linux/autoconf.h>
+
+#ifdef CONFIG_DEBUG_VM
+#define VM_BUG_ON(cond) BUG_ON(cond)
+#else
+#define VM_BUG_ON(cond) do { } while (0)
+#endif
+
+#ifdef CONFIG_DEBUG_VIRTUAL
+#define VIRTUAL_BUG_ON(cond) BUG_ON(cond)
+#else
+#define VIRTUAL_BUG_ON(cond) do { } while (0)
+#endif
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5d0819ee442a..c226c7b82946 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -352,7 +352,7 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 extern void arch_unmap_area(struct mm_struct *, unsigned long);
 extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 
-#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+#if USE_SPLIT_PTLOCKS
 /*
  * The mm counters are not protected by its page_table_lock,
  * so must be incremented atomically.
@@ -363,7 +363,7 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 #define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
 #define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
 
-#else  /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+#else  /* !USE_SPLIT_PTLOCKS */
 /*
  * The mm counters are protected by its page_table_lock,
  * so can be incremented directly.
@@ -374,7 +374,7 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 #define inc_mm_counter(mm, member) (mm)->_##member++
 #define dec_mm_counter(mm, member) (mm)->_##member--
 
-#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+#endif /* !USE_SPLIT_PTLOCKS */
 
 #define get_mm_rss(mm)					\
 	(get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h
new file mode 100644
index 000000000000..5b88e36c9103
--- /dev/null
+++ b/include/linux/usb/ehci_def.h
@@ -0,0 +1,160 @@
+/*
+ * Copyright (c) 2001-2002 by David Brownell
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software Foundation,
+ * Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef __LINUX_USB_EHCI_DEF_H
+#define __LINUX_USB_EHCI_DEF_H
+
+/* EHCI register interface, corresponds to EHCI Revision 0.95 specification */
+
+/* Section 2.2 Host Controller Capability Registers */
+struct ehci_caps {
+	/* these fields are specified as 8 and 16 bit registers,
+	 * but some hosts can't perform 8 or 16 bit PCI accesses.
+	 */
+	u32		hc_capbase;
+#define HC_LENGTH(p)		(((p)>>00)&0x00ff)	/* bits 7:0 */
+#define HC_VERSION(p)		(((p)>>16)&0xffff)	/* bits 31:16 */
+	u32		hcs_params;     /* HCSPARAMS - offset 0x4 */
+#define HCS_DEBUG_PORT(p)	(((p)>>20)&0xf)	/* bits 23:20, debug port? */
+#define HCS_INDICATOR(p)	((p)&(1 << 16))	/* true: has port indicators */
+#define HCS_N_CC(p)		(((p)>>12)&0xf)	/* bits 15:12, #companion HCs */
+#define HCS_N_PCC(p)		(((p)>>8)&0xf)	/* bits 11:8, ports per CC */
+#define HCS_PORTROUTED(p)	((p)&(1 << 7))	/* true: port routing */
+#define HCS_PPC(p)		((p)&(1 << 4))	/* true: port power control */
+#define HCS_N_PORTS(p)		(((p)>>0)&0xf)	/* bits 3:0, ports on HC */
+
+	u32		hcc_params;      /* HCCPARAMS - offset 0x8 */
+#define HCC_EXT_CAPS(p)		(((p)>>8)&0xff)	/* for pci extended caps */
+#define HCC_ISOC_CACHE(p)       ((p)&(1 << 7))  /* true: can cache isoc frame */
+#define HCC_ISOC_THRES(p)       (((p)>>4)&0x7)  /* bits 6:4, uframes cached */
+#define HCC_CANPARK(p)		((p)&(1 << 2))  /* true: can park on async qh */
+#define HCC_PGM_FRAMELISTLEN(p) ((p)&(1 << 1))  /* true: periodic_size changes*/
+#define HCC_64BIT_ADDR(p)       ((p)&(1))       /* true: can use 64-bit addr */
+	u8		portroute [8];	 /* nibbles for routing - offset 0xC */
+} __attribute__ ((packed));
+
+
+/* Section 2.3 Host Controller Operational Registers */
+struct ehci_regs {
+
+	/* USBCMD: offset 0x00 */
+	u32		command;
+/* 23:16 is r/w intr rate, in microframes; default "8" == 1/msec */
+#define CMD_PARK	(1<<11)		/* enable "park" on async qh */
+#define CMD_PARK_CNT(c)	(((c)>>8)&3)	/* how many transfers to park for */
+#define CMD_LRESET	(1<<7)		/* partial reset (no ports, etc) */
+#define CMD_IAAD	(1<<6)		/* "doorbell" interrupt async advance */
+#define CMD_ASE		(1<<5)		/* async schedule enable */
+#define CMD_PSE		(1<<4)		/* periodic schedule enable */
+/* 3:2 is periodic frame list size */
+#define CMD_RESET	(1<<1)		/* reset HC not bus */
+#define CMD_RUN		(1<<0)		/* start/stop HC */
+
+	/* USBSTS: offset 0x04 */
+	u32		status;
+#define STS_ASS		(1<<15)		/* Async Schedule Status */
+#define STS_PSS		(1<<14)		/* Periodic Schedule Status */
+#define STS_RECL	(1<<13)		/* Reclamation */
+#define STS_HALT	(1<<12)		/* Not running (any reason) */
+/* some bits reserved */
+	/* these STS_* flags are also intr_enable bits (USBINTR) */
+#define STS_IAA		(1<<5)		/* Interrupted on async advance */
+#define STS_FATAL	(1<<4)		/* such as some PCI access errors */
+#define STS_FLR		(1<<3)		/* frame list rolled over */
+#define STS_PCD		(1<<2)		/* port change detect */
+#define STS_ERR		(1<<1)		/* "error" completion (overflow, ...) */
+#define STS_INT		(1<<0)		/* "normal" completion (short, ...) */
+
+	/* USBINTR: offset 0x08 */
+	u32		intr_enable;
+
+	/* FRINDEX: offset 0x0C */
+	u32		frame_index;	/* current microframe number */
+	/* CTRLDSSEGMENT: offset 0x10 */
+	u32		segment;	/* address bits 63:32 if needed */
+	/* PERIODICLISTBASE: offset 0x14 */
+	u32		frame_list;	/* points to periodic list */
+	/* ASYNCLISTADDR: offset 0x18 */
+	u32		async_next;	/* address of next async queue head */
+
+	u32		reserved [9];
+
+	/* CONFIGFLAG: offset 0x40 */
+	u32		configured_flag;
+#define FLAG_CF		(1<<0)		/* true: we'll support "high speed" */
+
+	/* PORTSC: offset 0x44 */
+	u32		port_status [0];	/* up to N_PORTS */
+/* 31:23 reserved */
+#define PORT_WKOC_E	(1<<22)		/* wake on overcurrent (enable) */
+#define PORT_WKDISC_E	(1<<21)		/* wake on disconnect (enable) */
+#define PORT_WKCONN_E	(1<<20)		/* wake on connect (enable) */
+/* 19:16 for port testing */
+#define PORT_LED_OFF	(0<<14)
+#define PORT_LED_AMBER	(1<<14)
+#define PORT_LED_GREEN	(2<<14)
+#define PORT_LED_MASK	(3<<14)
+#define PORT_OWNER	(1<<13)		/* true: companion hc owns this port */
+#define PORT_POWER	(1<<12)		/* true: has power (see PPC) */
+#define PORT_USB11(x) (((x)&(3<<10)) == (1<<10))	/* USB 1.1 device */
+/* 11:10 for detecting lowspeed devices (reset vs release ownership) */
+/* 9 reserved */
+#define PORT_RESET	(1<<8)		/* reset port */
+#define PORT_SUSPEND	(1<<7)		/* suspend port */
+#define PORT_RESUME	(1<<6)		/* resume it */
+#define PORT_OCC	(1<<5)		/* over current change */
+#define PORT_OC		(1<<4)		/* over current active */
+#define PORT_PEC	(1<<3)		/* port enable change */
+#define PORT_PE		(1<<2)		/* port enable */
+#define PORT_CSC	(1<<1)		/* connect status change */
+#define PORT_CONNECT	(1<<0)		/* device connected */
+#define PORT_RWC_BITS   (PORT_CSC | PORT_PEC | PORT_OCC)
+} __attribute__ ((packed));
+
+#define USBMODE		0x68		/* USB Device mode */
+#define USBMODE_SDIS	(1<<3)		/* Stream disable */
+#define USBMODE_BE	(1<<2)		/* BE/LE endianness select */
+#define USBMODE_CM_HC	(3<<0)		/* host controller mode */
+#define USBMODE_CM_IDLE	(0<<0)		/* idle state */
+
+/* Appendix C, Debug port ... intended for use with special "debug devices"
+ * that can help if there's no serial console.  (nonstandard enumeration.)
+ */
+struct ehci_dbg_port {
+	u32	control;
+#define DBGP_OWNER	(1<<30)
+#define DBGP_ENABLED	(1<<28)
+#define DBGP_DONE	(1<<16)
+#define DBGP_INUSE	(1<<10)
+#define DBGP_ERRCODE(x)	(((x)>>7)&0x07)
+#	define DBGP_ERR_BAD	1
+#	define DBGP_ERR_SIGNAL	2
+#define DBGP_ERROR	(1<<6)
+#define DBGP_GO		(1<<5)
+#define DBGP_OUT	(1<<4)
+#define DBGP_LEN(x)	(((x)>>0)&0x0f)
+	u32	pids;
+#define DBGP_PID_GET(x)		(((x)>>16)&0xff)
+#define DBGP_PID_SET(data, tok)	(((data)<<8)|(tok))
+	u32	data03;
+	u32	data47;
+	u32	address;
+#define DBGP_EPADDR(dev, ep)	(((dev)<<8)|(ep))
+} __attribute__ ((packed));
+
+#endif /* __LINUX_USB_EHCI_DEF_H */
diff --git a/include/xen/balloon.h b/include/xen/balloon.h
deleted file mode 100644
index fe43b0f3c86a..000000000000
--- a/include/xen/balloon.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/******************************************************************************
- * balloon.h
- *
- * Xen balloon driver - enables returning/claiming memory to/from Xen.
- *
- * Copyright (c) 2003, B Dragovic
- * Copyright (c) 2003-2004, M Williamson, K Fraser
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation; or, when distributed
- * separately from the Linux kernel or incorporated into other
- * software packages, subject to the following license:
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this source file (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy, modify,
- * merge, publish, distribute, sublicense, and/or sell copies of the Software,
- * and to permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- */
-
-#ifndef __XEN_BALLOON_H__
-#define __XEN_BALLOON_H__
-
-#include <linux/spinlock.h>
-
-#if 0
-/*
- * Inform the balloon driver that it should allow some slop for device-driver
- * memory activities.
- */
-void balloon_update_driver_allowance(long delta);
-
-/* Allocate/free a set of empty pages in low memory (i.e., no RAM mapped). */
-struct page **alloc_empty_pages_and_pagevec(int nr_pages);
-void free_empty_pages_and_pagevec(struct page **pagevec, int nr_pages);
-
-void balloon_release_driver_page(struct page *page);
-
-/*
- * Prevent the balloon driver from changing the memory reservation during
- * a driver critical region.
- */
-extern spinlock_t balloon_lock;
-#define balloon_lock(__flags)   spin_lock_irqsave(&balloon_lock, __flags)
-#define balloon_unlock(__flags) spin_unlock_irqrestore(&balloon_lock, __flags)
-#endif
-
-#endif /* __XEN_BALLOON_H__ */
diff --git a/include/xen/events.h b/include/xen/events.h
index 4680ff3fbc91..0d5f1adc0363 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -46,6 +46,8 @@ extern void xen_irq_resume(void);
 
 /* Clear an irq's pending state, in preparation for polling on it */
 void xen_clear_irq_pending(int irq);
+void xen_set_irq_pending(int irq);
+bool xen_test_irq_pending(int irq);
 
 /* Poll waiting for an irq to become pending.  In the usual case, the
    irq will be disabled so it won't deliver an interrupt. */