17 files changed, 217 insertions, 98 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 9a5ed58..488be46 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1613,6 +1613,10 @@ static int __init parse_acpi(char *arg)
 	/* "acpi=noirq" disables ACPI interrupt routing */
 	else if (strcmp(arg, "noirq") == 0) {
 		acpi_noirq_set();
+	}
+	/* "acpi=copy_dsdt" copys DSDT */
+	else if (strcmp(arg, "copy_dsdt") == 0) {
+		acpi_gbl_copy_dsdt_locally = 1;
 	} else {
 		/* Core will printk when we return error. */
 		return -EINVAL;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c1c00d0..68e4a6f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1084,6 +1084,20 @@ static void clear_all_debug_regs(void)
 	}
 }
 
+#ifdef CONFIG_KGDB
+/*
+ * Restore debug regs if using kgdbwait and you have a kernel debugger
+ * connection established.
+ */
+static void dbg_restore_debug_regs(void)
+{
+	if (unlikely(kgdb_connected && arch_kgdb_ops.correct_hw_break))
+		arch_kgdb_ops.correct_hw_break();
+}
+#else /* ! CONFIG_KGDB */
+#define dbg_restore_debug_regs()
+#endif /* ! CONFIG_KGDB */
+
 /*
  * cpu_init() initializes state that is per-CPU. Some data is already
  * initialized (naturally) in the bootstrap process, such as the GDT
@@ -1107,9 +1121,9 @@ void __cpuinit cpu_init(void)
 	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
-	if (cpu != 0 && percpu_read(node_number) == 0 &&
-	    cpu_to_node(cpu) != NUMA_NO_NODE)
-		percpu_write(node_number, cpu_to_node(cpu));
+	if (cpu != 0 && percpu_read(numa_node) == 0 &&
+	    early_cpu_to_node(cpu) != NUMA_NO_NODE)
+		set_numa_node(early_cpu_to_node(cpu));
 #endif
 
 	me = current;
@@ -1174,18 +1188,8 @@ void __cpuinit cpu_init(void)
 	load_TR_desc();
 	load_LDT(&init_mm.context);
 
-#ifdef CONFIG_KGDB
-	/*
-	 * If the kgdb is connected no debug regs should be altered.  This
-	 * is only applicable when KGDB and a KGDB I/O module are built
-	 * into the kernel and you are using early debugging with
-	 * kgdbwait. KGDB will control the kernel HW breakpoint registers.
-	 */
-	if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
-		arch_kgdb_ops.correct_hw_break();
-	else
-#endif
-		clear_all_debug_regs();
+	clear_all_debug_regs();
+	dbg_restore_debug_regs();
 
 	fpu_init();
 
@@ -1239,6 +1243,7 @@ void __cpuinit cpu_init(void)
 #endif
 
 	clear_all_debug_regs();
+	dbg_restore_debug_regs();
 
 	/*
 	 * Force FPU initialization:
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 81c499e..e1a0a3b 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -190,7 +190,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
 		mutex_unlock(&therm_cpu_lock);
 		break;
 	}
-	return err ? NOTIFY_BAD : NOTIFY_OK;
+	return notifier_from_errno(err);
 }
 
 static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata =
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 8b862d59..1b7b31a 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -170,7 +170,7 @@ static int __cpuinit cpuid_class_cpu_callback(struct notifier_block *nfb,
 		cpuid_device_destroy(cpu);
 		break;
 	}
-	return err ? NOTIFY_BAD : NOTIFY_OK;
+	return notifier_from_errno(err);
 }
 
 static struct notifier_block __refdata cpuid_class_cpu_notifier =
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index b9c830c..fa99bae 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -41,6 +41,14 @@ static void early_vga_write(struct console *con, const char *str, unsigned n)
 				writew(0x720, VGABASE + 2*(max_xpos*j + i));
 			current_ypos = max_ypos-1;
 		}
+#ifdef CONFIG_KGDB_KDB
+		if (c == '\b') {
+			if (current_xpos > 0)
+				current_xpos--;
+		} else if (c == '\r') {
+			current_xpos = 0;
+		} else
+#endif
 		if (c == '\n') {
 			current_xpos = 0;
 			current_ypos++;
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 23b4ecd..a198b7c 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -36,6 +36,7 @@
 unsigned long				hpet_address;
 u8					hpet_blockid; /* OS timer block num */
 u8					hpet_msi_disable;
+u8					hpet_readback_cmp;
 
 #ifdef CONFIG_PCI_MSI
 static unsigned long			hpet_num_timers;
@@ -395,19 +396,23 @@ static int hpet_next_event(unsigned long delta,
 	 * at that point and we would wait for the next hpet interrupt
 	 * forever. We found out that reading the CMP register back
 	 * forces the transfer so we can rely on the comparison with
-	 * the counter register below. If the read back from the
-	 * compare register does not match the value we programmed
-	 * then we might have a real hardware problem. We can not do
-	 * much about it here, but at least alert the user/admin with
-	 * a prominent warning.
-	 * An erratum on some chipsets (ICH9,..), results in comparator read
-	 * immediately following a write returning old value. Workaround
-	 * for this is to read this value second time, when first
-	 * read returns old value.
+	 * the counter register below.
+	 *
+	 * That works fine on those ATI chipsets, but on newer Intel
+	 * chipsets (ICH9...) this triggers due to an erratum: Reading
+	 * the comparator immediately following a write is returning
+	 * the old value.
+	 *
+	 * We restrict the read back to the affected ATI chipsets (set
+	 * by quirks) and also run it with hpet=verbose for debugging
+	 * purposes.
 	 */
-	if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) {
-		WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt,
-		  KERN_WARNING "hpet: compare register read back failed.\n");
+	if (hpet_readback_cmp || hpet_verbose) {
+		u32 cmp = hpet_readl(HPET_Tn_CMP(timer));
+
+		if (cmp != cnt)
+			printk_once(KERN_WARNING
+			    "hpet: compare register read back failed.\n");
 	}
 
 	return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index b2258ca..4f4af75 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -47,20 +47,8 @@
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
 #include <asm/system.h>
-
 #include <asm/apic.h>
 
-/*
- * Put the error code here just in case the user cares:
- */
-static int gdb_x86errcode;
-
-/*
- * Likewise, the vector number here (since GDB only gets the signal
- * number through the usual means, and that's not very specific):
- */
-static int gdb_x86vector = -1;
-
 /**
  *	pt_regs_to_gdb_regs - Convert ptrace regs to GDB regs
  *	@gdb_regs: A pointer to hold the registers in the order GDB wants.
@@ -211,6 +199,8 @@ static struct hw_breakpoint {
 	struct perf_event	**pev;
 } breakinfo[4];
 
+static unsigned long early_dr7;
+
 static void kgdb_correct_hw_break(void)
 {
 	int breakno;
@@ -222,6 +212,14 @@ static void kgdb_correct_hw_break(void)
 		int cpu = raw_smp_processor_id();
 		if (!breakinfo[breakno].enabled)
 			continue;
+		if (dbg_is_early) {
+			set_debugreg(breakinfo[breakno].addr, breakno);
+			early_dr7 |= encode_dr7(breakno,
+						breakinfo[breakno].len,
+						breakinfo[breakno].type);
+			set_debugreg(early_dr7, 7);
+			continue;
+		}
 		bp = *per_cpu_ptr(breakinfo[breakno].pev, cpu);
 		info = counter_arch_bp(bp);
 		if (bp->attr.disabled != 1)
@@ -236,7 +234,8 @@ static void kgdb_correct_hw_break(void)
 		if (!val)
 			bp->attr.disabled = 0;
 	}
-	hw_breakpoint_restore();
+	if (!dbg_is_early)
+		hw_breakpoint_restore();
 }
 
 static int hw_break_reserve_slot(int breakno)
@@ -245,6 +244,9 @@ static int hw_break_reserve_slot(int breakno)
 	int cnt = 0;
 	struct perf_event **pevent;
 
+	if (dbg_is_early)
+		return 0;
+
 	for_each_online_cpu(cpu) {
 		cnt++;
 		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
@@ -270,6 +272,9 @@ static int hw_break_release_slot(int breakno)
 	struct perf_event **pevent;
 	int cpu;
 
+	if (dbg_is_early)
+		return 0;
+
 	for_each_online_cpu(cpu) {
 		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
 		if (dbg_release_bp_slot(*pevent))
@@ -314,7 +319,11 @@ static void kgdb_remove_all_hw_break(void)
 		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
 		if (bp->attr.disabled == 1)
 			continue;
-		arch_uninstall_hw_breakpoint(bp);
+		if (dbg_is_early)
+			early_dr7 &= ~encode_dr7(i, breakinfo[i].len,
+						 breakinfo[i].type);
+		else
+			arch_uninstall_hw_breakpoint(bp);
 		bp->attr.disabled = 1;
 	}
 }
@@ -391,6 +400,11 @@ void kgdb_disable_hw_debug(struct pt_regs *regs)
 	for (i = 0; i < 4; i++) {
 		if (!breakinfo[i].enabled)
 			continue;
+		if (dbg_is_early) {
+			early_dr7 &= ~encode_dr7(i, breakinfo[i].len,
+						 breakinfo[i].type);
+			continue;
+		}
 		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
 		if (bp->attr.disabled == 1)
 			continue;
@@ -399,23 +413,6 @@ void kgdb_disable_hw_debug(struct pt_regs *regs)
 	}
 }
 
-/**
- *	kgdb_post_primary_code - Save error vector/code numbers.
- *	@regs: Original pt_regs.
- *	@e_vector: Original error vector.
- *	@err_code: Original error code.
- *
- *	This is needed on architectures which support SMP and KGDB.
- *	This function is called after all the slave cpus have been put
- *	to a know spin state and the primary CPU has control over KGDB.
- */
-void kgdb_post_primary_code(struct pt_regs *regs, int e_vector, int err_code)
-{
-	/* primary processor is completely in the debugger */
-	gdb_x86vector = e_vector;
-	gdb_x86errcode = err_code;
-}
-
 #ifdef CONFIG_SMP
 /**
  *	kgdb_roundup_cpus - Get other CPUs into a holding pattern
@@ -567,7 +564,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 			return NOTIFY_DONE;
 	}
 
-	if (kgdb_handle_exception(args->trapnr, args->signr, args->err, regs))
+	if (kgdb_handle_exception(args->trapnr, args->signr, cmd, regs))
 		return NOTIFY_DONE;
 
 	/* Must touch watchdog before return to normal operation */
@@ -575,6 +572,26 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 	return NOTIFY_STOP;
 }
 
+#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
+int kgdb_ll_trap(int cmd, const char *str,
+		 struct pt_regs *regs, long err, int trap, int sig)
+{
+	struct die_args args = {
+		.regs	= regs,
+		.str	= str,
+		.err	= err,
+		.trapnr	= trap,
+		.signr	= sig,
+
+	};
+
+	if (!kgdb_io_module_registered)
+		return NOTIFY_DONE;
+
+	return __kgdb_notify(&args, cmd);
+}
+#endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
+
 static int
 kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
 {
@@ -605,14 +622,15 @@ static struct notifier_block kgdb_notifier = {
  */
 int kgdb_arch_init(void)
 {
+	return register_die_notifier(&kgdb_notifier);
+}
+
+void kgdb_arch_late(void)
+{
 	int i, cpu;
-	int ret;
 	struct perf_event_attr attr;
 	struct perf_event **pevent;
 
-	ret = register_die_notifier(&kgdb_notifier);
-	if (ret != 0)
-		return ret;
 	/*
 	 * Pre-allocate the hw breakpoint structions in the non-atomic
 	 * portion of kgdb because this operation requires mutexs to
@@ -624,12 +642,15 @@ int kgdb_arch_init(void)
 	attr.bp_type = HW_BREAKPOINT_W;
 	attr.disabled = 1;
 	for (i = 0; i < 4; i++) {
+		if (breakinfo[i].pev)
+			continue;
 		breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL);
 		if (IS_ERR(breakinfo[i].pev)) {
-			printk(KERN_ERR "kgdb: Could not allocate hw breakpoints\n");
+			printk(KERN_ERR "kgdb: Could not allocate hw"
+			       "breakpoints\nDisabling the kernel debugger\n");
 			breakinfo[i].pev = NULL;
 			kgdb_arch_exit();
-			return -1;
+			return;
 		}
 		for_each_online_cpu(cpu) {
 			pevent = per_cpu_ptr(breakinfo[i].pev, cpu);
@@ -640,7 +661,6 @@ int kgdb_arch_init(void)
 			}
 		}
 	}
-	return ret;
 }
 
 /**
@@ -690,6 +710,11 @@ unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs)
 	return instruction_pointer(regs);
 }
 
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
+{
+	regs->ip = ip;
+}
+
 struct kgdb_arch arch_kgdb_ops = {
 	/* Breakpoint instruction: */
 	.gdb_bpt_instr		= { 0xcc },
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index feaeb0d..eb9b76c 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -29,6 +29,8 @@
 #define KVM_SCALE 22
 
 static int kvmclock = 1;
+static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
 
 static int parse_no_kvmclock(char *arg)
 {
@@ -54,7 +56,8 @@ static unsigned long kvm_get_wallclock(void)
 
 	low = (int)__pa_symbol(&wall_clock);
 	high = ((u64)__pa_symbol(&wall_clock) >> 32);
-	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
+
+	native_write_msr(msr_kvm_wall_clock, low, high);
 
 	vcpu_time = &get_cpu_var(hv_clock);
 	pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
@@ -130,7 +133,8 @@ static int kvm_register_clock(char *txt)
 	high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
 	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
 	       cpu, high, low, txt);
-	return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
+
+	return native_write_msr_safe(msr_kvm_system_time, low, high);
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -165,14 +169,14 @@ static void __init kvm_smp_prepare_boot_cpu(void)
 #ifdef CONFIG_KEXEC
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
-	native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+	native_write_msr(msr_kvm_system_time, 0, 0);
 	native_machine_crash_shutdown(regs);
 }
 #endif
 
 static void kvm_shutdown(void)
 {
-	native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+	native_write_msr(msr_kvm_system_time, 0, 0);
 	native_machine_shutdown();
 }
 
@@ -181,27 +185,37 @@ void __init kvmclock_init(void)
 	if (!kvm_para_available())
 		return;
 
-	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
-		if (kvm_register_clock("boot clock"))
-			return;
-		pv_time_ops.sched_clock = kvm_clock_read;
-		x86_platform.calibrate_tsc = kvm_get_tsc_khz;
-		x86_platform.get_wallclock = kvm_get_wallclock;
-		x86_platform.set_wallclock = kvm_set_wallclock;
+	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
+		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
+	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
+		return;
+
+	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+		msr_kvm_system_time, msr_kvm_wall_clock);
+
+	if (kvm_register_clock("boot clock"))
+		return;
+	pv_time_ops.sched_clock = kvm_clock_read;
+	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
-		x86_cpuinit.setup_percpu_clockev =
-			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;
+	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 #endif
-		machine_ops.shutdown  = kvm_shutdown;
+	machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
-		machine_ops.crash_shutdown  = kvm_crash_shutdown;
+	machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif
-		kvm_get_preset_lpj();
-		clocksource_register(&kvm_clock);
-		pv_info.paravirt_enabled = 1;
-		pv_info.name = "KVM";
-	}
+	kvm_get_preset_lpj();
+	clocksource_register(&kvm_clock);
+	pv_info.paravirt_enabled = 1;
+	pv_info.name = "KVM";
+
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
+		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 }
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 2cd8c54..fa6551d 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -260,6 +260,7 @@ static void microcode_dev_exit(void)
 }
 
 MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
+MODULE_ALIAS("devname:cpu/microcode");
 #else
 #define microcode_dev_init()	0
 #define microcode_dev_exit()	do { } while (0)
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 4d4468e..7bf2dc4 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -230,7 +230,7 @@ static int __cpuinit msr_class_cpu_callback(struct notifier_block *nfb,
 		msr_device_destroy(cpu);
 		break;
 	}
-	return err ? NOTIFY_BAD : NOTIFY_OK;
+	return notifier_from_errno(err);
 }
 
 static struct notifier_block __refdata msr_class_cpu_notifier = {
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 7d2829d..a5bc528 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -31,8 +31,6 @@ static struct dma_map_ops swiotlb_dma_ops = {
 	.free_coherent = swiotlb_free_coherent,
 	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
 	.sync_single_for_device = swiotlb_sync_single_for_device,
-	.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
-	.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
 	.sync_sg_for_device = swiotlb_sync_sg_for_device,
 	.map_sg = swiotlb_map_sg_attrs,
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 03801f2..239427c 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -31,8 +31,16 @@ struct pvclock_shadow_time {
 	u32 tsc_to_nsec_mul;
 	int tsc_shift;
 	u32 version;
+	u8  flags;
 };
 
+static u8 valid_flags __read_mostly = 0;
+
+void pvclock_set_flags(u8 flags)
+{
+	valid_flags = flags;
+}
+
 /*
  * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
  * yielding a 64-bit result.
@@ -91,6 +99,7 @@ static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst,
 		dst->system_timestamp  = src->system_time;
 		dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
 		dst->tsc_shift         = src->tsc_shift;
+		dst->flags             = src->flags;
 		rmb();		/* test version after fetching data */
 	} while ((src->version & 1) || (dst->version != src->version));
 
@@ -109,11 +118,14 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src)
 	return pv_tsc_khz;
 }
 
+static atomic64_t last_value = ATOMIC64_INIT(0);
+
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 {
 	struct pvclock_shadow_time shadow;
 	unsigned version;
 	cycle_t ret, offset;
+	u64 last;
 
 	do {
 		version = pvclock_get_time_values(&shadow, src);
@@ -123,6 +135,31 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 		barrier();
 	} while (version != src->version);
 
+	if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) &&
+		(shadow.flags & PVCLOCK_TSC_STABLE_BIT))
+		return ret;
+
+	/*
+	 * Assumption here is that last_value, a global accumulator, always goes
+	 * forward. If we are less than that, we should not be much smaller.
+	 * We assume there is an error marging we're inside, and then the correction
+	 * does not sacrifice accuracy.
+	 *
+	 * For reads: global may have changed between test and return,
+	 * but this means someone else updated poked the clock at a later time.
+	 * We just need to make sure we are not seeing a backwards event.
+	 *
+	 * For updates: last_value = ret is not enough, since two vcpus could be
+	 * updating at the same time, and one of them could be slightly behind,
+	 * making the assumption that last_value always go forward fail to hold.
+	 */
+	last = atomic64_read(&last_value);
+	do {
+		if (ret < last)
+			return last;
+		last = atomic64_cmpxchg(&last_value, last, ret);
+	} while (unlikely(last != ret));
+
 	return ret;
 }
 
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 12e9fea..e72d3fc 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -495,10 +495,18 @@ void force_hpet_resume(void)
 /*
  * HPET MSI on some boards (ATI SB700/SB800) has side effect on
  * floppy DMA. Disable HPET MSI on such platforms.
+ * See erratum #27 (Misinterpreted MSI Requests May Result in
+ * Corrupted LPC DMA Data) in AMD Publication #46837,
+ * "SB700 Family Product Errata", Rev. 1.0, March 2010.
+ *
+ * Also force the read back of the CMP register in hpet_next_event()
+ * to work around the problem that the CMP register write seems to be
+ * delayed. See hpet_next_event() for details.
  */
 static void force_disable_hpet_msi(struct pci_dev *unused)
 {
 	hpet_msi_disable = 1;
+	hpet_readback_cmp = 1;
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c4851ef..e802989 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -725,6 +725,7 @@ void __init setup_arch(char **cmdline_p)
 	/* VMI may relocate the fixmap; do this before touching ioremap area */
 	vmi_init();
 
+	early_trap_init();
 	early_cpu_init();
 	early_ioremap_init();
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index ef6370b..a867940 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -265,10 +265,10 @@ void __init setup_per_cpu_areas(void)
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
 	/*
-	 * make sure boot cpu node_number is right, when boot cpu is on the
+	 * make sure boot cpu numa_node is right, when boot cpu is on the
 	 * node that doesn't have mem installed
 	 */
-	per_cpu(node_number, boot_cpu_id) = cpu_to_node(boot_cpu_id);
+	set_cpu_numa_node(boot_cpu_id, early_cpu_to_node(boot_cpu_id));
 #endif
 
 	/* Setup node to cpumask map */
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index cc2c604..c2f1b26 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -46,6 +46,7 @@
 
 /* Global pointer to shared data; NULL means no measured launch. */
 struct tboot *tboot __read_mostly;
+EXPORT_SYMBOL(tboot);
 
 /* timeout for APs (in secs) to enter wait-for-SIPI state during shutdown */
 #define AP_WAIT_TIMEOUT		1
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 02cfb9b..142d70c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -15,6 +15,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
+#include <linux/kgdb.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
@@ -451,6 +452,11 @@ void restart_nmi(void)
 /* May run on IST stack. */
 dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
 {
+#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
+	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
+			== NOTIFY_STOP)
+		return;
+#endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
 #ifdef CONFIG_KPROBES
 	if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
 			== NOTIFY_STOP)
@@ -802,6 +808,16 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 }
 #endif
 
+/* Set of traps needed for early debugging. */
+void __init early_trap_init(void)
+{
+	set_intr_gate_ist(1, &debug, DEBUG_STACK);
+	/* int3 can be called from all */
+	set_system_intr_gate_ist(3, &int3, DEBUG_STACK);
+	set_intr_gate(14, &page_fault);
+	load_idt(&idt_descr);
+}
+
 void __init trap_init(void)
 {
 	int i;
@@ -815,10 +831,7 @@ void __init trap_init(void)
 #endif
 
 	set_intr_gate(0, &divide_error);
-	set_intr_gate_ist(1, &debug, DEBUG_STACK);
 	set_intr_gate_ist(2, &nmi, NMI_STACK);
-	/* int3 can be called from all */
-	set_system_intr_gate_ist(3, &int3, DEBUG_STACK);
 	/* int4 can be called from all */
 	set_system_intr_gate(4, &overflow);
 	set_intr_gate(5, &bounds);
@@ -834,7 +847,6 @@ void __init trap_init(void)
 	set_intr_gate(11, &segment_not_present);
 	set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK);
 	set_intr_gate(13, &general_protection);
-	set_intr_gate(14, &page_fault);
 	set_intr_gate(15, &spurious_interrupt_bug);
 	set_intr_gate(16, &coprocessor_error);
 	set_intr_gate(17, &alignment_check);