25 files changed, 320 insertions, 91 deletions

diff --git a/arch/i386/kernel/acpi/sleep.c b/arch/i386/kernel/acpi/sleep.c
index 4ee83577bf6..c42b5ab49de 100644
--- a/arch/i386/kernel/acpi/sleep.c
+++ b/arch/i386/kernel/acpi/sleep.c
@@ -14,7 +14,7 @@
 
 /* address in low memory of the wakeup routine. */
 unsigned long acpi_wakeup_address = 0;
-unsigned long acpi_video_flags;
+unsigned long acpi_realmode_flags;
 extern char wakeup_start, wakeup_end;
 
 extern unsigned long FASTCALL(acpi_copy_wakeup_routine(unsigned long));
@@ -68,9 +68,11 @@ static int __init acpi_sleep_setup(char *str)
 {
 	while ((str != NULL) && (*str != '\0')) {
 		if (strncmp(str, "s3_bios", 7) == 0)
-			acpi_video_flags = 1;
+			acpi_realmode_flags |= 1;
 		if (strncmp(str, "s3_mode", 7) == 0)
-			acpi_video_flags |= 2;
+			acpi_realmode_flags |= 2;
+		if (strncmp(str, "s3_beep", 7) == 0)
+			acpi_realmode_flags |= 4;
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
@@ -80,9 +82,11 @@ static int __init acpi_sleep_setup(char *str)
 
 __setup("acpi_sleep=", acpi_sleep_setup);
 
+/* Ouch, we want to delete this. We already have better version in userspace, in
+   s2ram from suspend.sf.net project */
 static __init int reset_videomode_after_s3(struct dmi_system_id *d)
 {
-	acpi_video_flags |= 2;
+	acpi_realmode_flags |= 2;
 	return 0;
 }
 
diff --git a/arch/i386/kernel/acpi/wakeup.S b/arch/i386/kernel/acpi/wakeup.S
index a2295a34b2c..ed0a0f2c159 100644
--- a/arch/i386/kernel/acpi/wakeup.S
+++ b/arch/i386/kernel/acpi/wakeup.S
@@ -13,6 +13,21 @@
 # cs = 0x1234, eip = 0x05
 # 
 
+#define BEEP \
+	inb	$97, %al; 	\
+	outb	%al, $0x80; 	\
+	movb	$3, %al; 	\
+	outb	%al, $97; 	\
+	outb	%al, $0x80; 	\
+	movb	$-74, %al; 	\
+	outb	%al, $67; 	\
+	outb	%al, $0x80; 	\
+	movb	$-119, %al; 	\
+	outb	%al, $66; 	\
+	outb	%al, $0x80; 	\
+	movb	$15, %al; 	\
+	outb	%al, $66;
+
 ALIGN
 	.align	4096
 ENTRY(wakeup_start)
@@ -31,6 +46,11 @@ wakeup_code:
 	movw	%cs, %ax
 	movw	%ax, %ds					# Make ds:0 point to wakeup_start
 	movw	%ax, %ss
+
+	testl   $4, realmode_flags - wakeup_code
+	jz      1f
+	BEEP
+1:
 	mov	$(wakeup_stack - wakeup_code), %sp		# Private stack is needed for ASUS board
 	movw	$0x0e00 + 'S', %fs:(0x12)
 
@@ -41,7 +61,7 @@ wakeup_code:
 	cmpl	$0x12345678, %eax
 	jne	bogus_real_magic
 
-	testl	$1, video_flags - wakeup_code
+	testl	$1, realmode_flags - wakeup_code
 	jz	1f
 	lcall   $0xc000,$3
 	movw	%cs, %ax
@@ -49,7 +69,7 @@ wakeup_code:
 	movw	%ax, %ss
 1:
 
-	testl	$2, video_flags - wakeup_code
+	testl	$2, realmode_flags - wakeup_code
 	jz	1f
 	mov	video_mode - wakeup_code, %ax
 	call	mode_set
@@ -88,7 +108,11 @@ wakeup_code:
 	cmpl	$0x12345678, %eax
 	jne	bogus_real_magic
 
-	ljmpl	$__KERNEL_CS,$wakeup_pmode_return
+	testl   $8, realmode_flags - wakeup_code
+	jz      1f
+	BEEP
+1:
+	ljmpl	$__KERNEL_CS, $wakeup_pmode_return
 
 real_save_gdt:	.word 0
 		.long 0
@@ -97,7 +121,8 @@ real_save_cr3:	.long 0
 real_save_cr4:	.long 0
 real_magic:	.long 0
 video_mode:	.long 0
-video_flags:	.long 0
+realmode_flags:	.long 0
+beep_flags:	.long 0
 real_efer_save_restore:	.long 0
 real_save_efer_edx: 	.long 0
 real_save_efer_eax: 	.long 0
@@ -260,8 +285,8 @@ ENTRY(acpi_copy_wakeup_routine)
 
 	movl	saved_videomode, %edx
 	movl	%edx, video_mode - wakeup_start (%eax)
-	movl	acpi_video_flags, %edx
-	movl	%edx, video_flags - wakeup_start (%eax)
+	movl	acpi_realmode_flags, %edx
+	movl	%edx, realmode_flags - wakeup_start (%eax)
 	movl	$0x12345678, real_magic - wakeup_start (%eax)
 	movl	$0x12345678, saved_magic
 	popl	%ebx
diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index 4112afe712b..47001d50a08 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -222,6 +222,7 @@
 #include <linux/capability.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
+#include <linux/freezer.h>
 #include <linux/smp.h>
 #include <linux/dmi.h>
 #include <linux/suspend.h>
@@ -2311,7 +2312,6 @@ static int __init apm_init(void)
 		remove_proc_entry("apm", NULL);
 		return err;
 	}
-	kapmd_task->flags |= PF_NOFREEZE;
 	wake_up_process(kapmd_task);
 
 	if (num_online_cpus() > 1 && !smp ) {
diff --git a/arch/i386/kernel/asm-offsets.c b/arch/i386/kernel/asm-offsets.c
index 27a776c9044..7288ac88d74 100644
--- a/arch/i386/kernel/asm-offsets.c
+++ b/arch/i386/kernel/asm-offsets.c
@@ -17,6 +17,13 @@
 #include <asm/thread_info.h>
 #include <asm/elf.h>
 
+#include <xen/interface/xen.h>
+
+#ifdef CONFIG_LGUEST_GUEST
+#include <linux/lguest.h>
+#include "../../../drivers/lguest/lg.h"
+#endif
+
 #define DEFINE(sym, val) \
         asm volatile("\n->" #sym " %0 " #val : : "i" (val))
 
@@ -59,6 +66,7 @@ void foo(void)
 	OFFSET(TI_addr_limit, thread_info, addr_limit);
 	OFFSET(TI_restart_block, thread_info, restart_block);
 	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+	OFFSET(TI_cpu, thread_info, cpu);
 	BLANK();
 
 	OFFSET(GDS_size, Xgt_desc_struct, size);
@@ -115,4 +123,25 @@ void foo(void)
 	OFFSET(PARAVIRT_iret, paravirt_ops, iret);
 	OFFSET(PARAVIRT_read_cr0, paravirt_ops, read_cr0);
 #endif
+
+#ifdef CONFIG_XEN
+	BLANK();
+	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
+	OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
+#endif
+
+#ifdef CONFIG_LGUEST_GUEST
+	BLANK();
+	OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
+	OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc);
+	OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc);
+	OFFSET(LGUEST_PAGES_host_cr3, lguest_pages, state.host_cr3);
+	OFFSET(LGUEST_PAGES_host_sp, lguest_pages, state.host_sp);
+	OFFSET(LGUEST_PAGES_guest_gdt_desc, lguest_pages,state.guest_gdt_desc);
+	OFFSET(LGUEST_PAGES_guest_idt_desc, lguest_pages,state.guest_idt_desc);
+	OFFSET(LGUEST_PAGES_guest_gdt, lguest_pages, state.guest_gdt);
+	OFFSET(LGUEST_PAGES_regs_trapnum, lguest_pages, regs.trapnum);
+	OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode);
+	OFFSET(LGUEST_PAGES_regs, lguest_pages, regs);
+#endif
 }
diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c
index 7ba7c3abd3a..1203dc5ab87 100644
--- a/arch/i386/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/i386/kernel/cpu/mcheck/therm_throt.c
@@ -134,19 +134,21 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb,
 	int err;
 
 	sys_dev = get_cpu_sysdev(cpu);
-	mutex_lock(&therm_cpu_lock);
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
+		mutex_lock(&therm_cpu_lock);
 		err = thermal_throttle_add_dev(sys_dev);
+		mutex_unlock(&therm_cpu_lock);
 		WARN_ON(err);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
+		mutex_lock(&therm_cpu_lock);
 		thermal_throttle_remove_dev(sys_dev);
+		mutex_unlock(&therm_cpu_lock);
 		break;
 	}
-	mutex_unlock(&therm_cpu_lock);
 	return NOTIFY_OK;
 }
 
diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c
index a1808022ea1..2452c6fbe99 100644
--- a/arch/i386/kernel/efi.c
+++ b/arch/i386/kernel/efi.c
@@ -278,7 +278,7 @@ void efi_memmap_walk(efi_freemem_callback_t callback, void *arg)
 	struct range {
 		unsigned long start;
 		unsigned long end;
-	} prev, curr;
+	} uninitialized_var(prev), curr;
 	efi_memory_desc_t *md;
 	unsigned long start, end;
 	void *p;
diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index 3c3c220488c..a714d6b4350 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -409,8 +409,6 @@ restore_nocheck_notrace:
 1:	INTERRUPT_RETURN
 .section .fixup,"ax"
 iret_exc:
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushl $0			# no error code
 	pushl $do_iret_error
 	jmp error_code
@@ -1023,6 +1021,91 @@ ENTRY(kernel_thread_helper)
 	CFI_ENDPROC
 ENDPROC(kernel_thread_helper)
 
+#ifdef CONFIG_XEN
+ENTRY(xen_hypervisor_callback)
+	CFI_STARTPROC
+	pushl $0
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	TRACE_IRQS_OFF
+
+	/* Check to see if we got the event in the critical
+	   region in xen_iret_direct, after we've reenabled
+	   events and checked for pending events.  This simulates
+	   iret instruction's behaviour where it delivers a
+	   pending interrupt when enabling interrupts. */
+	movl PT_EIP(%esp),%eax
+	cmpl $xen_iret_start_crit,%eax
+	jb   1f
+	cmpl $xen_iret_end_crit,%eax
+	jae  1f
+
+	call xen_iret_crit_fixup
+
+1:	mov %esp, %eax
+	call xen_evtchn_do_upcall
+	jmp  ret_from_intr
+	CFI_ENDPROC
+ENDPROC(xen_hypervisor_callback)
+
+# Hypervisor uses this for application faults while it executes.
+# We get here for two reasons:
+#  1. Fault while reloading DS, ES, FS or GS
+#  2. Fault while executing IRET
+# Category 1 we fix up by reattempting the load, and zeroing the segment
+# register if the load fails.
+# Category 2 we fix up by jumping to do_iret_error. We cannot use the
+# normal Linux return path in this case because if we use the IRET hypercall
+# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+# We distinguish between categories by maintaining a status value in EAX.
+ENTRY(xen_failsafe_callback)
+	CFI_STARTPROC
+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	movl $1,%eax
+1:	mov 4(%esp),%ds
+2:	mov 8(%esp),%es
+3:	mov 12(%esp),%fs
+4:	mov 16(%esp),%gs
+	testl %eax,%eax
+	popl %eax
+	CFI_ADJUST_CFA_OFFSET -4
+	lea 16(%esp),%esp
+	CFI_ADJUST_CFA_OFFSET -16
+	jz 5f
+	addl $16,%esp
+	jmp iret_exc		# EAX != 0 => Category 2 (Bad IRET)
+5:	pushl $0		# EAX == 0 => Category 1 (Bad segment)
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	jmp ret_from_exception
+	CFI_ENDPROC
+
+.section .fixup,"ax"
+6:	xorl %eax,%eax
+	movl %eax,4(%esp)
+	jmp 1b
+7:	xorl %eax,%eax
+	movl %eax,8(%esp)
+	jmp 2b
+8:	xorl %eax,%eax
+	movl %eax,12(%esp)
+	jmp 3b
+9:	xorl %eax,%eax
+	movl %eax,16(%esp)
+	jmp 4b
+.previous
+.section __ex_table,"a"
+	.align 4
+	.long 1b,6b
+	.long 2b,7b
+	.long 3b,8b
+	.long 4b,9b
+.previous
+ENDPROC(xen_failsafe_callback)
+
+#endif	/* CONFIG_XEN */
+
 .section .rodata,"a"
 #include "syscall_table.S"
 
diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index 82714668d43..7c52b222207 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -510,7 +510,8 @@ ENTRY(_stext)
 /*
  * BSS section
  */
-.section ".bss.page_aligned","w"
+.section ".bss.page_aligned","wa"
+	.align PAGE_SIZE_asm
 ENTRY(swapper_pg_dir)
 	.fill 1024,4,0
 ENTRY(swapper_pg_pmd)
@@ -538,6 +539,8 @@ fault_msg:
 	.ascii "Int %d: CR2 %p  err %p  EIP %p  CS %p  flags %p\n"
 	.asciz "Stack: %p %p %p %p %p %p %p %p\n"
 
+#include "../xen/xen-head.S"
+
 /*
  * The IDT and GDT 'descriptors' are a strange 48-bit object
  * only used by the lidt and lgdt instructions. They are not
diff --git a/arch/i386/kernel/init_task.c b/arch/i386/kernel/init_task.c
index cff95d10a4d..d26fc063a76 100644
--- a/arch/i386/kernel/init_task.c
+++ b/arch/i386/kernel/init_task.c
@@ -42,5 +42,5 @@ EXPORT_SYMBOL(init_task);
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
  * no more per-task TSS's.
  */ 
-DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_internodealigned_in_smp = INIT_TSS;
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
 
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 7f8b7af2b95..21db8f56c9a 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -667,6 +667,7 @@ static int balanced_irq(void *unused)
 		set_pending_irq(i, cpumask_of_cpu(0));
 	}
 
+	set_freezable();
 	for ( ; ; ) {
 		time_remaining = schedule_timeout_interruptible(time_remaining);
 		try_to_freeze();
diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
index d2daf672f4a..ba44d40b066 100644
--- a/arch/i386/kernel/irq.c
+++ b/arch/i386/kernel/irq.c
@@ -21,7 +21,7 @@
 #include <asm/apic.h>
 #include <asm/uaccess.h>
 
-DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_internodealigned_in_smp;
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
 DEFINE_PER_CPU(struct pt_regs *, irq_regs);
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index fba121f7973..03b7f5584d7 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -295,7 +295,7 @@ static unsigned int
 	last_irq_sums [NR_CPUS],
 	alert_counter [NR_CPUS];
 
-void touch_nmi_watchdog (void)
+void touch_nmi_watchdog(void)
 {
 	if (nmi_watchdog > 0) {
 		unsigned cpu;
@@ -304,8 +304,10 @@ void touch_nmi_watchdog (void)
 		 * Just reset the alert counters, (other CPUs might be
 		 * spinning on locks we hold):
 		 */
-		for_each_present_cpu (cpu)
-			alert_counter[cpu] = 0;
+		for_each_present_cpu(cpu) {
+			if (alert_counter[cpu])
+				alert_counter[cpu] = 0;
+		}
 	}
 
 	/*
diff --git a/arch/i386/kernel/paravirt.c b/arch/i386/kernel/paravirt.c
index faab09abca5..53f07a8275e 100644
--- a/arch/i386/kernel/paravirt.c
+++ b/arch/i386/kernel/paravirt.c
@@ -228,6 +228,41 @@ static int __init print_banner(void)
 }
 core_initcall(print_banner);
 
+static struct resource reserve_ioports = {
+	.start = 0,
+	.end = IO_SPACE_LIMIT,
+	.name = "paravirt-ioport",
+	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
+};
+
+static struct resource reserve_iomem = {
+	.start = 0,
+	.end = -1,
+	.name = "paravirt-iomem",
+	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
+};
+
+/*
+ * Reserve the whole legacy IO space to prevent any legacy drivers
+ * from wasting time probing for their hardware.  This is a fairly
+ * brute-force approach to disabling all non-virtual drivers.
+ *
+ * Note that this must be called very early to have any effect.
+ */
+int paravirt_disable_iospace(void)
+{
+	int ret;
+
+	ret = request_resource(&ioport_resource, &reserve_ioports);
+	if (ret == 0) {
+		ret = request_resource(&iomem_resource, &reserve_iomem);
+		if (ret)
+			release_resource(&reserve_ioports);
+	}
+
+	return ret;
+}
+
 struct paravirt_ops paravirt_ops = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -267,7 +302,7 @@ struct paravirt_ops paravirt_ops = {
 	.write_msr = native_write_msr_safe,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
-	.get_scheduled_cycles = native_read_tsc,
+	.sched_clock = native_sched_clock,
 	.get_cpu_khz = native_calculate_cpu_khz,
 	.load_tr_desc = native_load_tr_desc,
 	.set_ldt = native_set_ldt,
diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c
index 0c0ceec5de0..0c8f00e69c4 100644
--- a/arch/i386/kernel/ptrace.c
+++ b/arch/i386/kernel/ptrace.c
@@ -164,14 +164,22 @@ static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_
 		u32 *desc;
 		unsigned long base;
 
-		down(&child->mm->context.sem);
-		desc = child->mm->context.ldt + (seg & ~7);
-		base = (desc[0] >> 16) | ((desc[1] & 0xff) << 16) | (desc[1] & 0xff000000);
+		seg &= ~7UL;
 
-		/* 16-bit code segment? */
-		if (!((desc[1] >> 22) & 1))
-			addr &= 0xffff;
-		addr += base;
+		down(&child->mm->context.sem);
+		if (unlikely((seg >> 3) >= child->mm->context.size))
+			addr = -1L; /* bogus selector, access would fault */
+		else {
+			desc = child->mm->context.ldt + seg;
+			base = ((desc[0] >> 16) |
+				((desc[1] & 0xff) << 16) |
+				(desc[1] & 0xff000000));
+
+			/* 16-bit code segment? */
+			if (!((desc[1] >> 22) & 1))
+				addr &= 0xffff;
+			addr += base;
+		}
 		up(&child->mm->context.sem);
 	}
 	return addr;
@@ -358,17 +366,9 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 	switch (request) {
 	/* when I and D space are separate, these will need to be fixed. */
 	case PTRACE_PEEKTEXT: /* read word at location addr. */ 
-	case PTRACE_PEEKDATA: {
-		unsigned long tmp;
-		int copied;
-
-		copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
-		ret = -EIO;
-		if (copied != sizeof(tmp))
-			break;
-		ret = put_user(tmp, datap);
+	case PTRACE_PEEKDATA:
+		ret = generic_ptrace_peekdata(child, addr, data);
 		break;
-	}
 
 	/* read the word at location addr in the USER area. */
 	case PTRACE_PEEKUSR: {
@@ -395,10 +395,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 	/* when I and D space are separate, this will have to be fixed. */
 	case PTRACE_POKETEXT: /* write the word at location addr. */
 	case PTRACE_POKEDATA:
-		ret = 0;
-		if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
-			break;
-		ret = -EIO;
+		ret = generic_ptrace_pokedata(child, addr, data);
 		break;
 
 	case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index 2d61e65eeb5..74871d066c2 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -601,6 +601,8 @@ void __init setup_arch(char **cmdline_p)
 	 * NOTE: at this point the bootmem allocator is fully available.
 	 */
 
+	paravirt_post_allocator_init();
+
 	dmi_scan_machine();
 
 #ifdef CONFIG_X86_GENERICARCH
diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c
index 6299c080f6e..2d35d850202 100644
--- a/arch/i386/kernel/smp.c
+++ b/arch/i386/kernel/smp.c
@@ -22,6 +22,7 @@
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
 #include <mach_apic.h>
 
 /*
@@ -249,13 +250,13 @@ static unsigned long flush_va;
 static DEFINE_SPINLOCK(tlbstate_lock);
 
 /*
- * We cannot call mmdrop() because we are in interrupt context, 
+ * We cannot call mmdrop() because we are in interrupt context,
  * instead update mm->cpu_vm_mask.
  *
  * We need to reload %cr3 since the page tables may be going
  * away from under us..
  */
-static inline void leave_mm (unsigned long cpu)
+void leave_mm(unsigned long cpu)
 {
 	if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
 		BUG();
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 0b2954534b8..5910d3fac56 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -148,7 +148,7 @@ void __init smp_alloc_memory(void)
  * a given CPU
  */
 
-static void __cpuinit smp_store_cpu_info(int id)
+void __cpuinit smp_store_cpu_info(int id)
 {
 	struct cpuinfo_x86 *c = cpu_data + id;
 
@@ -308,8 +308,7 @@ cpumask_t cpu_coregroup_map(int cpu)
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
 
-static inline void
-set_cpu_sibling_map(int cpu)
+void set_cpu_sibling_map(int cpu)
 {
 	int i;
 	struct cpuinfo_x86 *c = cpu_data;
@@ -1144,8 +1143,7 @@ void __init native_smp_prepare_boot_cpu(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void
-remove_siblinginfo(int cpu)
+void remove_siblinginfo(int cpu)
 {
 	int sibling;
 	struct cpuinfo_x86 *c = cpu_data;
diff --git a/arch/i386/kernel/smpcommon.c b/arch/i386/kernel/smpcommon.c
index 1868ae18eb4..bbfe85a0f69 100644
--- a/arch/i386/kernel/smpcommon.c
+++ b/arch/i386/kernel/smpcommon.c
@@ -47,7 +47,7 @@ int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
 EXPORT_SYMBOL(smp_call_function);
 
 /**
- * smp_call_function_single - Run a function on another CPU
+ * smp_call_function_single - Run a function on a specific CPU
  * @cpu: The target CPU.  Cannot be the calling CPU.
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
@@ -66,9 +66,11 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 	int ret;
 	int me = get_cpu();
 	if (cpu == me) {
-		WARN_ON(1);
+		local_irq_disable();
+		func(info);
+		local_irq_enable();
 		put_cpu();
-		return -EBUSY;
+		return 0;
 	}
 
 	ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, wait);
diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index bf6adce5226..8344c70adf6 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -323,3 +323,4 @@ ENTRY(sys_call_table)
 	.long sys_signalfd
 	.long sys_timerfd
 	.long sys_eventfd
+	.long sys_fallocate
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 28bd1c5163e..3e7753c78b9 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -41,6 +41,10 @@
 #include <linux/mca.h>
 #endif
 
+#if defined(CONFIG_EDAC)
+#include <linux/edac.h>
+#endif
+
 #include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/io.h>
@@ -433,6 +437,7 @@ void die(const char * str, struct pt_regs * regs, long err)
 
 	bust_spinlocks(0);
 	die.lock_owner = -1;
+	add_taint(TAINT_DIE);
 	spin_unlock_irqrestore(&die.lock, flags);
 
 	if (!regs)
@@ -517,10 +522,12 @@ fastcall void do_##name(struct pt_regs * regs, long error_code) \
 	do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \
 }
 
-#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
+#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr, irq) \
 fastcall void do_##name(struct pt_regs * regs, long error_code) \
 { \
 	siginfo_t info; \
+	if (irq) \
+		local_irq_enable(); \
 	info.si_signo = signr; \
 	info.si_errno = 0; \
 	info.si_code = sicode; \
@@ -560,13 +567,13 @@ DO_VM86_ERROR( 3, SIGTRAP, "int3", int3)
 #endif
 DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow)
 DO_VM86_ERROR( 5, SIGSEGV, "bounds", bounds)
-DO_ERROR_INFO( 6, SIGILL,  "invalid opcode", invalid_op, ILL_ILLOPN, regs->eip)
+DO_ERROR_INFO( 6, SIGILL,  "invalid opcode", invalid_op, ILL_ILLOPN, regs->eip, 0)
 DO_ERROR( 9, SIGFPE,  "coprocessor segment overrun", coprocessor_segment_overrun)
 DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
 DO_ERROR(11, SIGBUS,  "segment not present", segment_not_present)
 DO_ERROR(12, SIGBUS,  "stack segment", stack_segment)
-DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
-DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0)
+DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0, 0)
+DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0, 1)
 
 fastcall void __kprobes do_general_protection(struct pt_regs * regs,
 					      long error_code)
@@ -635,6 +642,14 @@ mem_parity_error(unsigned char reason, struct pt_regs * regs)
 	printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x on "
 		"CPU %d.\n", reason, smp_processor_id());
 	printk(KERN_EMERG "You have some hardware problem, likely on the PCI bus.\n");
+
+#if defined(CONFIG_EDAC)
+	if(edac_handler_set()) {
+		edac_atomic_assert_error();
+		return;
+	}
+#endif
+
 	if (panic_on_unrecovered_nmi)
                 panic("NMI: Not continuing");
 
@@ -1053,6 +1068,7 @@ asmlinkage void math_state_restore(void)
 	thread->status |= TS_USEDFPU;	/* So we fnsave on switch_to() */
 	tsk->fpu_counter++;
 }
+EXPORT_SYMBOL_GPL(math_state_restore);
 
 #ifndef CONFIG_MATH_EMULATION
 
diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c
index ea63a30ca3e..debd7dbb415 100644
--- a/arch/i386/kernel/tsc.c
+++ b/arch/i386/kernel/tsc.c
@@ -27,6 +27,7 @@ static int tsc_enabled;
  * an extra value to store the TSC freq
  */
 unsigned int tsc_khz;
+EXPORT_SYMBOL_GPL(tsc_khz);
 
 int tsc_disable;
 
@@ -58,10 +59,11 @@ __setup("notsc", tsc_setup);
  */
 static int tsc_unstable;
 
-static inline int check_tsc_unstable(void)
+int check_tsc_unstable(void)
 {
 	return tsc_unstable;
 }
+EXPORT_SYMBOL_GPL(check_tsc_unstable);
 
 /* Accellerators for sched_clock()
  * convert from cycles(64bits) => nanoseconds (64bits)
@@ -84,7 +86,7 @@ static inline int check_tsc_unstable(void)
  *
  *			-johnstul@us.ibm.com "math is hard, lets go shopping!"
  */
-static unsigned long cyc2ns_scale __read_mostly;
+unsigned long cyc2ns_scale __read_mostly;
 
 #define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
 
@@ -93,15 +95,10 @@ static inline void set_cyc2ns_scale(unsigned long cpu_khz)
 	cyc2ns_scale = (1000000 << CYC2NS_SCALE_FACTOR)/cpu_khz;
 }
 
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
-{
-	return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR;
-}
-
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
-unsigned long long sched_clock(void)
+unsigned long long native_sched_clock(void)
 {
 	unsigned long long this_offset;
 
@@ -118,12 +115,24 @@ unsigned long long sched_clock(void)
 		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
 
 	/* read the Time Stamp Counter: */
-	get_scheduled_cycles(this_offset);
+	rdtscll(this_offset);
 
 	/* return the value in ns */
 	return cycles_2_ns(this_offset);
 }
 
+/* We need to define a real function for sched_clock, to override the
+   weak default version */
+#ifdef CONFIG_PARAVIRT
+unsigned long long sched_clock(void)
+{
+	return paravirt_sched_clock();
+}
+#else
+unsigned long long sched_clock(void)
+	__attribute__((alias("native_sched_clock")));
+#endif
+
 unsigned long native_calculate_cpu_khz(void)
 {
 	unsigned long long start, end;
diff --git a/arch/i386/kernel/vmi.c b/arch/i386/kernel/vmi.c
index c12720d7cbc..72042bb7ec9 100644
--- a/arch/i386/kernel/vmi.c
+++ b/arch/i386/kernel/vmi.c
@@ -362,7 +362,7 @@ static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)
 }
 #endif
 
-static void vmi_allocate_pt(u32 pfn)
+static void vmi_allocate_pt(struct mm_struct *mm, u32 pfn)
 {
 	vmi_set_page_type(pfn, VMI_PAGE_L1);
 	vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
@@ -891,7 +891,7 @@ static inline int __init activate_vmi(void)
 		paravirt_ops.setup_boot_clock = vmi_time_bsp_init;
 		paravirt_ops.setup_secondary_clock = vmi_time_ap_init;
 #endif
-		paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles;
+		paravirt_ops.sched_clock = vmi_sched_clock;
  		paravirt_ops.get_cpu_khz = vmi_cpu_khz;
 
 		/* We have true wallclock functions; disable CMOS clock sync */
diff --git a/arch/i386/kernel/vmiclock.c b/arch/i386/kernel/vmiclock.c
index 26a37f8a876..f9b845f4e69 100644
--- a/arch/i386/kernel/vmiclock.c
+++ b/arch/i386/kernel/vmiclock.c
@@ -64,10 +64,10 @@ int vmi_set_wallclock(unsigned long now)
 	return 0;
 }
 
-/* paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles */
-unsigned long long vmi_get_sched_cycles(void)
+/* paravirt_ops.sched_clock = vmi_sched_clock */
+unsigned long long vmi_sched_clock(void)
 {
-	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE);
+	return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE));
 }
 
 /* paravirt_ops.get_cpu_khz = vmi_cpu_khz */
diff --git a/arch/i386/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S
index aa87b06c7c8..7d72cce0052 100644
--- a/arch/i386/kernel/vmlinux.lds.S
+++ b/arch/i386/kernel/vmlinux.lds.S
@@ -60,7 +60,9 @@ SECTIONS
   	__stop___ex_table = .;
   }
 
-  BUG_TABLE
+  NOTES :text :note
+
+  BUG_TABLE :text
 
   . = ALIGN(4);
   .tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) {
@@ -88,6 +90,7 @@ SECTIONS
 
   . = ALIGN(4096);
   .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
+	*(.data.page_aligned)
 	*(.data.idt)
   }
 
@@ -180,6 +183,7 @@ SECTIONS
   .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
 	__per_cpu_start = .;
 	*(.data.percpu)
+	*(.data.percpu.shared_aligned)
 	__per_cpu_end = .;
   }
   . = ALIGN(4096);
@@ -206,6 +210,4 @@ SECTIONS
   STABS_DEBUG
 
   DWARF_DEBUG
-
-  NOTES
 }
diff --git a/arch/i386/kernel/vsyscall-note.S b/arch/i386/kernel/vsyscall-note.S
index d4b5be4f3d5..271f16a8ca0 100644
--- a/arch/i386/kernel/vsyscall-note.S
+++ b/arch/i386/kernel/vsyscall-note.S
@@ -3,23 +3,40 @@
  * Here we can supply some information useful to userland.
  */
 
-#include <linux/uts.h>
 #include <linux/version.h>
+#include <linux/elfnote.h>
 
-#define ASM_ELF_NOTE_BEGIN(name, flags, vendor, type)			      \
-	.section name, flags;						      \
-	.balign 4;							      \
-	.long 1f - 0f;		/* name length */			      \
-	.long 3f - 2f;		/* data length */			      \
-	.long type;		/* note type */				      \
-0:	.asciz vendor;		/* vendor name */			      \
-1:	.balign 4;							      \
-2:
+/* Ideally this would use UTS_NAME, but using a quoted string here
+   doesn't work. Remember to change this when changing the
+   kernel's name. */
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
 
-#define ASM_ELF_NOTE_END						      \
-3:	.balign 4;		/* pad out section */			      \
-	.previous
+#ifdef CONFIG_XEN
 
-	ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0)
-	.long LINUX_VERSION_CODE
-	ASM_ELF_NOTE_END
+/*
+ * Add a special note telling glibc's dynamic linker a fake hardware
+ * flavor that it will use to choose the search path for libraries in the
+ * same way it uses real hardware capabilities like "mmx".
+ * We supply "nosegneg" as the fake capability, to indicate that we
+ * do not like negative offsets in instructions using segment overrides,
+ * since we implement those inefficiently.  This makes it possible to
+ * install libraries optimized to avoid those access patterns in someplace
+ * like /lib/i686/tls/nosegneg.  Note that an /etc/ld.so.conf.d/file
+ * corresponding to the bits here is needed to make ldconfig work right.
+ * It should contain:
+ *	hwcap 1 nosegneg
+ * to match the mapping of bit to name that we give here.
+ */
+
+/* Bit used for the pseudo-hwcap for non-negative segments.  We use
+   bit 1 to avoid bugs in some versions of glibc when bit 0 is
+   used; the choice is otherwise arbitrary. */
+#define VDSO_NOTE_NONEGSEG_BIT	1
+
+ELFNOTE_START(GNU, 2, "a")
+	.long 1, 1<<VDSO_NOTE_NONEGSEG_BIT		/* ncaps, mask */
+	.byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg"	/* bit, name */
+ELFNOTE_END
+#endif