Merge branch 'linus' into x86/gart

35 files changed, 293 insertions, 138 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fe361ae..52e18e6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,17 +26,10 @@ config X86
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
 
-config DEFCONFIG_LIST
+config ARCH_DEFCONFIG
 	string
-	depends on X86_32
-	option defconfig_list
-	default "arch/x86/configs/i386_defconfig"
-
-config DEFCONFIG_LIST
-	string
-	depends on X86_64
-	option defconfig_list
-	default "arch/x86/configs/x86_64_defconfig"
+	default "arch/x86/configs/i386_defconfig" if X86_32
+	default "arch/x86/configs/x86_64_defconfig" if X86_64
 
 
 config GENERIC_LOCKBREAK
@@ -1515,13 +1508,13 @@ config PCI_GOMMCONFIG
 config PCI_GODIRECT
 	bool "Direct"
 
-config PCI_GOANY
-	bool "Any"
-
 config PCI_GOOLPC
 	bool "OLPC"
 	depends on OLPC
 
+config PCI_GOANY
+	bool "Any"
+
 endchoice
 
 config PCI_BIOS
@@ -1538,9 +1531,8 @@ config PCI_MMCONFIG
 	depends on X86_32 && PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY)
 
 config PCI_OLPC
-	bool
-	depends on PCI && PCI_GOOLPC
-	default y
+	def_bool y
+	depends on PCI && OLPC && (PCI_GOOLPC || PCI_GOANY)
 
 config PCI_DOMAINS
 	def_bool y
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index ac1e31b..1836337 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -6,15 +6,19 @@ config TRACE_IRQFLAGS_SUPPORT
 source "lib/Kconfig.debug"
 
 config NONPROMISC_DEVMEM
-	bool "Disable promiscuous /dev/mem"
+	bool "Filter access to /dev/mem"
 	help
-	  The /dev/mem file by default only allows userspace access to PCI
-	  space and the BIOS code and data regions. This is sufficient for
-	  dosemu and X and all common users of /dev/mem. With this config
-	  option, you allow userspace access to all of memory, including
-	  kernel and userspace memory. Accidental access to this is
-	  obviously disasterous, but specific access can be used by people
-	  debugging the kernel.
+	  If this option is left off, you allow userspace access to all
+	  of memory, including kernel and userspace memory. Accidental
+	  access to this is obviously disastrous, but specific access can
+	  be used by people debugging the kernel.
+
+	  If this option is switched on, the /dev/mem file only allows
+	  userspace access to PCI space and the BIOS code and data regions.
+	  This is sufficient for dosemu and X and all common users of
+	  /dev/mem.
+
+	  If in doubt, say Y.
 
 config EARLY_PRINTK
 	bool "Early printk" if EMBEDDED
diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c
index c1d00c02..50e47cd 100644
--- a/arch/x86/boot/printf.c
+++ b/arch/x86/boot/printf.c
@@ -56,7 +56,7 @@ static char *number(char *str, long num, int base, int size, int precision,
 	if (type & LEFT)
 		type &= ~ZEROPAD;
 	if (base < 2 || base > 36)
-		return 0;
+		return NULL;
 	c = (type & ZEROPAD) ? '0' : ' ';
 	sign = 0;
 	if (type & SIGN) {
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index c49ebcc..33c5216 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -242,12 +242,19 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
 
 static void __cpuinit acpi_register_lapic(int id, u8 enabled)
 {
+	unsigned int ver = 0;
+
 	if (!enabled) {
 		++disabled_cpus;
 		return;
 	}
 
-	generic_processor_info(id, 0);
+#ifdef CONFIG_X86_32
+	if (boot_cpu_physical_apicid != -1U)
+		ver = apic_version[boot_cpu_physical_apicid];
+#endif
+
+	generic_processor_info(id, ver);
 }
 
 static int __init
@@ -767,8 +774,13 @@ static void __init acpi_register_lapic_address(unsigned long address)
 	mp_lapic_addr = address;
 
 	set_fixmap_nocache(FIX_APIC_BASE, address);
-	if (boot_cpu_physical_apicid == -1U)
+	if (boot_cpu_physical_apicid == -1U) {
 		boot_cpu_physical_apicid  = GET_APIC_ID(read_apic_id());
+#ifdef CONFIG_X86_32
+		apic_version[boot_cpu_physical_apicid] =
+			 GET_APIC_VERSION(apic_read(APIC_LVR));
+#endif
+	}
 }
 
 static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 5910020..0633cfd 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -534,7 +534,7 @@ int setup_profiling_timer(unsigned int multiplier)
  */
 void clear_local_APIC(void)
 {
-	int maxlvt = lapic_get_maxlvt();
+	int maxlvt;
 	u32 v;
 
 	/* APIC hasn't been mapped yet */
diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c
index af4a867..777a7ff 100644
--- a/arch/x86/kernel/cpu/cpufreq/longrun.c
+++ b/arch/x86/kernel/cpu/cpufreq/longrun.c
@@ -245,7 +245,7 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq,
 	if ((ecx > 95) || (ecx == 0) || (eax < ebx))
 		return -EIO;
 
-	edx = (eax - ebx) / (100 - ecx);
+	edx = ((eax - ebx) * 100) / (100 - ecx);
 	*low_freq = edx * 1000; /* back to kHz */
 
 	dprintk("low frequency is %u kHz\n", *low_freq);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 46d4034..206791e 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1127,12 +1127,23 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		 * an UP version, and is deprecated by AMD.
 		 */
 		if (num_online_cpus() != 1) {
-			printk(KERN_ERR PFX "MP systems not supported by PSB BIOS structure\n");
+#ifndef CONFIG_ACPI_PROCESSOR
+			printk(KERN_ERR PFX "ACPI Processor support is required "
+			       "for SMP systems but is absent. Please load the "
+			       "ACPI Processor module before starting this "
+			       "driver.\n");
+#else
+			printk(KERN_ERR PFX "Your BIOS does not provide ACPI "
+			       "_PSS objects in a way that Linux understands. "
+			       "Please report this to the Linux ACPI maintainers"
+			       " and complain to your BIOS vendor.\n");
+#endif
 			kfree(data);
 			return -ENODEV;
 		}
 		if (pol->cpu != 0) {
-			printk(KERN_ERR PFX "No _PSS objects for CPU other than CPU0\n");
+			printk(KERN_ERR PFX "No ACPI _PSS objects for CPU other than "
+			       "CPU0. Complain to your BIOS vendor.\n");
 			kfree(data);
 			return -ENODEV;
 		}
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e03cc95..eb9ddd8 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -56,6 +56,11 @@ void __cpuinit mxcsr_feature_mask_init(void)
 
 void __init init_thread_xstate(void)
 {
+	if (!HAVE_HWFP) {
+		xstate_size = sizeof(struct i387_soft_struct);
+		return;
+	}
+
 	if (cpu_has_fxsr)
 		xstate_size = sizeof(struct i387_fxsave_struct);
 #ifdef CONFIG_X86_32
@@ -94,7 +99,7 @@ void __cpuinit fpu_init(void)
 int init_fpu(struct task_struct *tsk)
 {
 	if (tsk_used_math(tsk)) {
-		if (tsk == current)
+		if (HAVE_HWFP && tsk == current)
 			unlazy_fpu(tsk);
 		return 0;
 	}
@@ -109,6 +114,15 @@ int init_fpu(struct task_struct *tsk)
 			return -ENOMEM;
 	}
 
+#ifdef CONFIG_X86_32
+	if (!HAVE_HWFP) {
+		memset(tsk->thread.xstate, 0, xstate_size);
+		finit();
+		set_stopped_child_used_math(tsk);
+		return 0;
+	}
+#endif
+
 	if (cpu_has_fxsr) {
 		struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
 
@@ -330,13 +344,13 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
 	struct user_i387_ia32_struct env;
 	int ret;
 
-	if (!HAVE_HWFP)
-		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
-
 	ret = init_fpu(target);
 	if (ret)
 		return ret;
 
+	if (!HAVE_HWFP)
+		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
+
 	if (!cpu_has_fxsr) {
 		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 					   &target->thread.xstate->fsave, 0,
@@ -360,15 +374,15 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	struct user_i387_ia32_struct env;
 	int ret;
 
-	if (!HAVE_HWFP)
-		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
-
 	ret = init_fpu(target);
 	if (ret)
 		return ret;
 
 	set_stopped_child_used_math(target);
 
+	if (!HAVE_HWFP)
+		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
+
 	if (!cpu_has_fxsr) {
 		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 					  &target->thread.xstate->fsave, 0, -1);
@@ -474,18 +488,18 @@ static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf)
 int restore_i387_ia32(struct _fpstate_ia32 __user *buf)
 {
 	int err;
+	struct task_struct *tsk = current;
 
-	if (HAVE_HWFP) {
-		struct task_struct *tsk = current;
-
+	if (HAVE_HWFP)
 		clear_fpu(tsk);
 
-		if (!used_math()) {
-			err = init_fpu(tsk);
-			if (err)
-				return err;
-		}
+	if (!used_math()) {
+		err = init_fpu(tsk);
+		if (err)
+			return err;
+	}
 
+	if (HAVE_HWFP) {
 		if (cpu_has_fxsr)
 			err = restore_i387_fxsave(buf);
 		else
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
index 3d01e47..a4f93b4 100644
--- a/arch/x86/kernel/init_task.c
+++ b/arch/x86/kernel/init_task.c
@@ -11,7 +11,6 @@
 #include <asm/desc.h>
 
 static struct fs_struct init_fs = INIT_FS;
-static struct files_struct init_files = INIT_FILES;
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
 struct mm_struct init_mm = INIT_MM(init_mm);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 4bc1be5..08a3098 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -53,7 +53,7 @@ static cycle_t kvm_clock_read(void);
  * have elapsed since the hypervisor wrote the data. So we try to account for
  * that with system time
  */
-unsigned long kvm_get_wallclock(void)
+static unsigned long kvm_get_wallclock(void)
 {
 	u32 wc_sec, wc_nsec;
 	u64 delta;
@@ -86,7 +86,7 @@ unsigned long kvm_get_wallclock(void)
 	return ts.tv_sec + 1;
 }
 
-int kvm_set_wallclock(unsigned long now)
+static int kvm_set_wallclock(unsigned long now)
 {
 	return 0;
 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 1f99b62..3710097 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -26,6 +26,7 @@
 #include <linux/kdebug.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
+#include <linux/sysdev.h>
 #include <asm/atomic.h>
 #include <asm/io.h>
 #include <asm/mtrr.h>
@@ -548,6 +549,28 @@ static __init unsigned read_aperture(struct pci_dev *dev, u32 *size)
 	return aper_base;
 }
 
+static int gart_resume(struct sys_device *dev)
+{
+	return 0;
+}
+
+static int gart_suspend(struct sys_device *dev, pm_message_t state)
+{
+	return -EINVAL;
+}
+
+static struct sysdev_class gart_sysdev_class = {
+	.name = "gart",
+	.suspend = gart_suspend,
+	.resume = gart_resume,
+
+};
+
+static struct sys_device device_gart = {
+	.id	= 0,
+	.cls	= &gart_sysdev_class,
+};
+
 /*
  * Private Northbridge GATT initialization in case we cannot use the
  * AGP driver for some reason.
@@ -558,7 +581,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 	unsigned aper_base, new_aper_base;
 	struct pci_dev *dev;
 	void *gatt;
-	int i;
+	int i, error;
 
 	printk(KERN_INFO "PCI-DMA: Disabling AGP.\n");
 	aper_size = aper_base = info->aper_size = 0;
@@ -595,6 +618,12 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 		dev = k8_northbridges[i];
 		enable_gart_translation(dev, __pa(gatt));
 	}
+
+	error = sysdev_class_register(&gart_sysdev_class);
+	if (!error)
+		error = sysdev_register(&device_gart);
+	if (error)
+		panic("Could not register gart_sysdev -- would corrupt data on next suspend");
 	flush_gart();
 
 	printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n",
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 67e9b4a..ba370dc 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -99,15 +99,6 @@ static void mwait_idle(void)
 		local_irq_enable();
 }
 
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
-	if (force_mwait)
-		return 1;
-	/* Any C1 states supported? */
-	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
 /*
  * On SMP it's slightly faster (but much more power-consuming!)
  * to poll the ->work.need_resched flag instead of waiting for the
@@ -119,6 +110,33 @@ static void poll_idle(void)
 	cpu_relax();
 }
 
+/*
+ * mwait selection logic:
+ *
+ * It depends on the CPU. For AMD CPUs that support MWAIT this is
+ * wrong. Family 0x10 and 0x11 CPUs will enter C1 on HLT. Powersavings
+ * then depend on a clock divisor and current Pstate of the core. If
+ * all cores of a processor are in halt state (C1) the processor can
+ * enter the C1E (C1 enhanced) state. If mwait is used this will never
+ * happen.
+ *
+ * idle=mwait overrides this decision and forces the usage of mwait.
+ */
+static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
+{
+	if (force_mwait)
+		return 1;
+
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		switch(c->x86) {
+		case 0x10:
+		case 0x11:
+			return 0;
+		}
+	}
+	return 1;
+}
+
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
 	static int selected;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index f8476df..6d54833 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -649,8 +649,11 @@ struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct
 	/* If the task has used fpu the last 5 timeslices, just do a full
 	 * restore of the math state immediately to avoid the trap; the
 	 * chances of needing FPU soon are obviously high now
+	 *
+	 * tsk_used_math() checks prevent calling math_state_restore(),
+	 * which can sleep in the case of !tsk_used_math()
 	 */
-	if (next_p->fpu_counter > 5)
+	if (tsk_used_math(next_p) && next_p->fpu_counter > 5)
 		math_state_restore();
 
 	/*
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e2319f3..ac54ff5 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -658,8 +658,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/* If the task has used fpu the last 5 timeslices, just do a full
 	 * restore of the math state immediately to avoid the trap; the
 	 * chances of needing FPU soon are obviously high now
+	 *
+	 * tsk_used_math() checks prevent calling math_state_restore(),
+	 * which can sleep in the case of !tsk_used_math()
 	 */
-	if (next_p->fpu_counter>5)
+	if (tsk_used_math(next_p) && next_p->fpu_counter > 5)
 		math_state_restore();
 	return prev_p;
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3898849..56078d6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1190,6 +1190,7 @@ static void __init smp_cpu_index_default(void)
  */
 void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
+	preempt_disable();
 	nmi_watchdog_default();
 	smp_cpu_index_default();
 	current_cpu_data = boot_cpu_data;
@@ -1206,7 +1207,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	if (smp_sanity_check(max_cpus) < 0) {
 		printk(KERN_INFO "SMP disabled\n");
 		disable_smp();
-		return;
+		goto out;
 	}
 
 	preempt_disable();
@@ -1246,6 +1247,8 @@ 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();
+out:
+	preempt_enable();
 }
 /*
  * Early setup to make printk work.
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index e479072..068759d 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -14,7 +14,7 @@
 
 #include "mach_timer.h"
 
-static int tsc_enabled;
+static int tsc_disabled;
 
 /*
  * On some systems the TSC frequency does not
@@ -28,8 +28,8 @@ EXPORT_SYMBOL_GPL(tsc_khz);
 static int __init tsc_setup(char *str)
 {
 	printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, "
-				"cannot disable TSC completely.\n");
-	mark_tsc_unstable("user disabled TSC");
+	       "cannot disable TSC completely.\n");
+	tsc_disabled = 1;
 	return 1;
 }
 #else
@@ -120,7 +120,7 @@ unsigned long long native_sched_clock(void)
 	 *   very important for it to be as fast as the platform
 	 *   can achive it. )
 	 */
-	if (unlikely(!tsc_enabled && !tsc_unstable))
+	if (unlikely(tsc_disabled))
 		/* No locking but a rare wrong value is not a big deal: */
 		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
 
@@ -322,7 +322,6 @@ void mark_tsc_unstable(char *reason)
 {
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
-		tsc_enabled = 0;
 		printk("Marking TSC unstable due to: %s.\n", reason);
 		/* Can be called before registration */
 		if (clocksource_tsc.mult)
@@ -336,7 +335,7 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d)
 {
 	printk(KERN_NOTICE "%s detected: marking TSC unstable.\n",
-		       d->ident);
+	       d->ident);
 	tsc_unstable = 1;
 	return 0;
 }
@@ -403,14 +402,22 @@ void __init tsc_init(void)
 {
 	int cpu;
 
-	if (!cpu_has_tsc)
+	if (!cpu_has_tsc || tsc_disabled) {
+		/* Disable the TSC in case of !cpu_has_tsc */
+		tsc_disabled = 1;
 		return;
+	}
 
 	cpu_khz = calculate_cpu_khz();
 	tsc_khz = cpu_khz;
 
 	if (!cpu_khz) {
 		mark_tsc_unstable("could not calculate TSC khz");
+		/*
+		 * We need to disable the TSC completely in this case
+		 * to prevent sched_clock() from using it.
+		 */
+		tsc_disabled = 1;
 		return;
 	}
 
@@ -441,8 +448,6 @@ void __init tsc_init(void)
 	if (check_tsc_unstable()) {
 		clocksource_tsc.rating = 0;
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
-	} else
-		tsc_enabled = 1;
-
+	}
 	clocksource_register(&clocksource_tsc);
 }
diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c
index fcc16e5..1784b80 100644
--- a/arch/x86/kernel/tsc_64.c
+++ b/arch/x86/kernel/tsc_64.c
@@ -227,14 +227,14 @@ void __init tsc_calibrate(void)
 	/* hpet or pmtimer available ? */
 	if (!hpet && !pm1 && !pm2) {
 		printk(KERN_INFO "TSC calibrated against PIT\n");
-		return;
+		goto out;
 	}
 
 	/* Check, whether the sampling was disturbed by an SMI */
 	if (tsc1 == ULONG_MAX || tsc2 == ULONG_MAX) {
 		printk(KERN_WARNING "TSC calibration disturbed by SMI, "
 		       "using PIT calibration result\n");
-		return;
+		goto out;
 	}
 
 	tsc2 = (tsc2 - tsc1) * 1000000L;
@@ -255,6 +255,7 @@ void __init tsc_calibrate(void)
 
 	tsc_khz = tsc2 / tsc1;
 
+out:
 	for_each_possible_cpu(cpu)
 		set_cyc2ns_scale(tsc_khz, cpu);
 }
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 3324d90..7c077a9 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -216,7 +216,7 @@ int pit_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
 
-	if (pit && vcpu->vcpu_id == 0)
+	if (pit && vcpu->vcpu_id == 0 && pit->pit_state.inject_pending)
 		return atomic_read(&pit->pit_state.pit_timer.pending);
 
 	return 0;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 36809d7..c297c50 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -957,7 +957,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *lapic = vcpu->arch.apic;
 
-	if (lapic)
+	if (lapic && apic_enabled(lapic) && apic_lvt_enabled(lapic, APIC_LVTT))
 		return atomic_read(&lapic->timer.pending);
 
 	return 0;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 36c5406..7246b60 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1996,7 +1996,7 @@ static struct shrinker mmu_shrinker = {
 	.seeks = DEFAULT_SEEKS * 10,
 };
 
-void mmu_destroy_caches(void)
+static void mmu_destroy_caches(void)
 {
 	if (pte_chain_cache)
 		kmem_cache_destroy(pte_chain_cache);
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index f2a696d..8a96320 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -677,8 +677,9 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 	c->use_modrm_ea = 1;
 
 	if (c->modrm_mod == 3) {
-		c->modrm_val = *(unsigned long *)
-			decode_register(c->modrm_rm, c->regs, c->d & ByteOp);
+		c->modrm_ptr = decode_register(c->modrm_rm,
+					       c->regs, c->d & ByteOp);
+		c->modrm_val = *(unsigned long *)c->modrm_ptr;
 		return rc;
 	}
 
@@ -1005,6 +1006,7 @@ done_prefixes:
 		if ((c->d & ModRM) && c->modrm_mod == 3) {
 			c->src.type = OP_REG;
 			c->src.val = c->modrm_val;
+			c->src.ptr = c->modrm_ptr;
 			break;
 		}
 		c->src.type = OP_MEM;
@@ -1049,6 +1051,7 @@ done_prefixes:
 		if ((c->d & ModRM) && c->modrm_mod == 3) {
 			c->dst.type = OP_REG;
 			c->dst.val = c->dst.orig_val = c->modrm_val;
+			c->dst.ptr = c->modrm_ptr;
 			break;
 		}
 		c->dst.type = OP_MEM;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index af65b2d..5c7e2fd 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -582,8 +582,9 @@ static void __init lguest_init_IRQ(void)
 		int vector = FIRST_EXTERNAL_VECTOR + i;
 		if (vector != SYSCALL_VECTOR) {
 			set_intr_gate(vector, interrupt[i]);
-			set_irq_chip_and_handler(i, &lguest_irq_controller,
-						 handle_level_irq);
+			set_irq_chip_and_handler_name(i, &lguest_irq_controller,
+						      handle_level_irq,
+						      "level");
 		}
 	}
 	/* This call is required to set up for 4k stacks, where we have
diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay_32.c
index 4535e6d..d710f2d 100644
--- a/arch/x86/lib/delay_32.c
+++ b/arch/x86/lib/delay_32.c
@@ -44,13 +44,36 @@ static void delay_loop(unsigned long loops)
 static void delay_tsc(unsigned long loops)
 {
 	unsigned long bclock, now;
+	int cpu;
 
-	preempt_disable();		/* TSC's are per-cpu */
+	preempt_disable();
+	cpu = smp_processor_id();
 	rdtscl(bclock);
-	do {
-		rep_nop();
+	for (;;) {
 		rdtscl(now);
-	} while ((now-bclock) < loops);
+		if ((now - bclock) >= loops)
+			break;
+
+		/* Allow RT tasks to run */
+		preempt_enable();
+		rep_nop();
+		preempt_disable();
+
+		/*
+		 * It is possible that we moved to another CPU, and
+		 * since TSC's are per-cpu we need to calculate
+		 * that. The delay must guarantee that we wait "at
+		 * least" the amount of time. Being moved to another
+		 * CPU could make the wait longer but we just need to
+		 * make sure we waited long enough. Rebalance the
+		 * counter for this CPU.
+		 */
+		if (unlikely(cpu != smp_processor_id())) {
+			loops -= (now - bclock);
+			cpu = smp_processor_id();
+			rdtscl(bclock);
+		}
+	}
 	preempt_enable();
 }
 
diff --git a/arch/x86/lib/delay_64.c b/arch/x86/lib/delay_64.c
index bbc6105..4c441be 100644
--- a/arch/x86/lib/delay_64.c
+++ b/arch/x86/lib/delay_64.c
@@ -31,14 +31,36 @@ int __devinit read_current_timer(unsigned long *timer_value)
 void __delay(unsigned long loops)
 {
 	unsigned bclock, now;
+	int cpu;
 
-	preempt_disable();		/* TSC's are pre-cpu */
+	preempt_disable();
+	cpu = smp_processor_id();
 	rdtscl(bclock);
-	do {
-		rep_nop(); 
+	for (;;) {
 		rdtscl(now);
+		if ((now - bclock) >= loops)
+			break;
+
+		/* Allow RT tasks to run */
+		preempt_enable();
+		rep_nop();
+		preempt_disable();
+
+		/*
+		 * It is possible that we moved to another CPU, and
+		 * since TSC's are per-cpu we need to calculate
+		 * that. The delay must guarantee that we wait "at
+		 * least" the amount of time. Being moved to another
+		 * CPU could make the wait longer but we just need to
+		 * make sure we waited long enough. Rebalance the
+		 * counter for this CPU.
+		 */
+		if (unlikely(cpu != smp_processor_id())) {
+			loops -= (now - bclock);
+			cpu = smp_processor_id();
+			rdtscl(bclock);
+		}
 	}
-	while ((now-bclock) < loops);
 	preempt_enable();
 }
 EXPORT_SYMBOL(__delay);
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 6e38d87..c7b06fe 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -30,6 +30,7 @@
 #include <asm/uaccess.h>
 #include <asm/desc.h>
 #include <asm/user.h>
+#include <asm/i387.h>
 
 #include "fpu_system.h"
 #include "fpu_emu.h"
@@ -146,6 +147,13 @@ asmlinkage void math_emulate(long arg)
 	unsigned long code_limit = 0;	/* Initialized to stop compiler warnings */
 	struct desc_struct code_descriptor;
 
+	if (!used_math()) {
+		if (init_fpu(current)) {
+			do_group_exit(SIGKILL);
+			return;
+		}
+	}
+
 #ifdef RE_ENTRANT_CHECKING
 	if (emulating) {
 		printk("ERROR: wm-FPU-emu is not RE-ENTRANT!\n");
@@ -153,11 +161,6 @@ asmlinkage void math_emulate(long arg)
 	RE_ENTRANT_CHECK_ON;
 #endif /* RE_ENTRANT_CHECKING */
 
-	if (!used_math()) {
-		finit();
-		set_used_math();
-	}
-
 	SETUP_DATA_AREA(arg);
 
 	FPU_ORIG_EIP = FPU_EIP;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 32ba13b..156e6d7 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -206,7 +206,7 @@ void __init cleanup_highmap(void)
 	pmd_t *last_pmd = pmd + PTRS_PER_PMD;
 
 	for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
-		if (!pmd_present(*pmd))
+		if (pmd_none(*pmd))
 			continue;
 		if (vaddr < (unsigned long) _text || vaddr > end)
 			set_pmd(pmd, __pmd(0));
@@ -506,7 +506,7 @@ early_param("memtest", parse_memtest);
 
 static void __init early_memtest(unsigned long start, unsigned long end)
 {
-	unsigned long t_start, t_size;
+	u64 t_start, t_size;
 	unsigned pattern;
 
 	if (!memtest_pattern)
@@ -525,7 +525,7 @@ static void __init early_memtest(unsigned long start, unsigned long end)
 			if (t_start + t_size > end)
 				t_size = end - t_start;
 
-			printk(KERN_CONT "\n  %016lx - %016lx pattern %d",
+			printk(KERN_CONT "\n  %016llx - %016llx pattern %d",
 				t_start, t_start + t_size, pattern);
 
 			memtest(t_start, t_size, pattern);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 71bb315..2b2bb3f 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -593,10 +593,11 @@ void __init early_iounmap(void *addr, unsigned long size)
 	unsigned long offset;
 	unsigned int nrpages;
 	enum fixed_addresses idx;
-	unsigned int nesting;
+	int nesting;
 
 	nesting = --early_ioremap_nested;
-	WARN_ON(nesting < 0);
+	if (WARN_ON(nesting < 0))
+		return;
 
 	if (early_ioremap_debug) {
 		printk(KERN_INFO "early_iounmap(%p, %08lx) [%d]\n", addr,
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index bcb1a8e..06b7a1c 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -28,13 +28,13 @@
 #ifdef CONFIG_X86_PAT
 int __read_mostly pat_wc_enabled = 1;
 
-void __init pat_disable(char *reason)
+void __cpuinit pat_disable(char *reason)
 {
 	pat_wc_enabled = 0;
 	printk(KERN_INFO "%s\n", reason);
 }
 
-static int nopat(char *str)
+static int __init nopat(char *str)
 {
 	pat_disable("PAT support disabled.");
 	return 0;
@@ -151,32 +151,33 @@ static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot,
 	unsigned long pat_type;
 	u8 mtrr_type;
 
-	mtrr_type = mtrr_type_lookup(start, end);
-	if (mtrr_type == 0xFF) {		/* MTRR not enabled */
-		*ret_prot = prot;
-		return 0;
-	}
-	if (mtrr_type == 0xFE) {		/* MTRR match error */
-		*ret_prot = _PAGE_CACHE_UC;
-		return -1;
-	}
-	if (mtrr_type != MTRR_TYPE_UNCACHABLE &&
-	    mtrr_type != MTRR_TYPE_WRBACK &&
-	    mtrr_type != MTRR_TYPE_WRCOMB) {	/* MTRR type unhandled */
-		*ret_prot = _PAGE_CACHE_UC;
-		return -1;
-	}
-
 	pat_type = prot & _PAGE_CACHE_MASK;
 	prot &= (~_PAGE_CACHE_MASK);
 
-	/* Currently doing intersection by hand. Optimize it later. */
+	/*
+	 * We return the PAT request directly for types where PAT takes
+	 * precedence with respect to MTRR and for UC_MINUS.
+	 * Consistency checks with other PAT requests is done later
+	 * while going through memtype list.
+	 */
 	if (pat_type == _PAGE_CACHE_WC) {
 		*ret_prot = prot | _PAGE_CACHE_WC;
+		return 0;
 	} else if (pat_type == _PAGE_CACHE_UC_MINUS) {
 		*ret_prot = prot | _PAGE_CACHE_UC_MINUS;
-	} else if (pat_type == _PAGE_CACHE_UC ||
-	           mtrr_type == MTRR_TYPE_UNCACHABLE) {
+		return 0;
+	} else if (pat_type == _PAGE_CACHE_UC) {
+		*ret_prot = prot | _PAGE_CACHE_UC;
+		return 0;
+	}
+
+	/*
+	 * Look for MTRR hint to get the effective type in case where PAT
+	 * request is for WB.
+	 */
+	mtrr_type = mtrr_type_lookup(start, end);
+
+	if (mtrr_type == MTRR_TYPE_UNCACHABLE) {
 		*ret_prot = prot | _PAGE_CACHE_UC;
 	} else if (mtrr_type == MTRR_TYPE_WRCOMB) {
 		*ret_prot = prot | _PAGE_CACHE_WC;
@@ -233,14 +234,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 	if (req_type == -1) {
 		/*
-		 * Special case where caller wants to inherit from mtrr or
-		 * existing pat mapping, defaulting to UC_MINUS in case of
-		 * no match.
+		 * Call mtrr_lookup to get the type hint. This is an
+		 * optimization for /dev/mem mmap'ers into WB memory (BIOS
+		 * tools and ACPI tools). Use WB request for WB memory and use
+		 * UC_MINUS otherwise.
 		 */
 		u8 mtrr_type = mtrr_type_lookup(start, end);
-		if (mtrr_type == 0xFE) { /* MTRR match error */
-			err = -1;
-		}
 
 		if (mtrr_type == MTRR_TYPE_WRBACK) {
 			req_type = _PAGE_CACHE_WB;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 8545c8a..6e64aaf 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -302,18 +302,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL385 G2",
+		.ident = "HP ProLiant DL360",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"),
 		},
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL585 G2",
+		.ident = "HP ProLiant DL380",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"),
 		},
 	},
 #ifdef __i386__
diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c
index e70b9c5..b821f44 100644
--- a/arch/x86/pci/init.c
+++ b/arch/x86/pci/init.c
@@ -15,7 +15,8 @@ static __init int pci_access_init(void)
 	pci_mmcfg_early_init();
 
 #ifdef CONFIG_PCI_OLPC
-	pci_olpc_init();
+	if (!pci_olpc_init())
+		return 0;	/* skip additional checks if it's an XO */
 #endif
 #ifdef CONFIG_PCI_BIOS
 	pci_pcbios_init();
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 0908fca..ca8df9c 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -621,6 +621,13 @@ static __init int via_router_probe(struct irq_router *r,
 			 */
 			device = PCI_DEVICE_ID_VIA_8235;
 			break;
+		case PCI_DEVICE_ID_VIA_8237:
+			/**
+			 * Asus a7v600 bios wrongly reports 8237
+			 * as 586-compatible
+			 */
+			device = PCI_DEVICE_ID_VIA_8237;
+			break;
 		}
 	}
 
diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c
index 5e76365..e11e9e8 100644
--- a/arch/x86/pci/olpc.c
+++ b/arch/x86/pci/olpc.c
@@ -302,12 +302,13 @@ static struct pci_raw_ops pci_olpc_conf = {
 	.write = pci_olpc_write,
 };
 
-void __init pci_olpc_init(void)
+int __init pci_olpc_init(void)
 {
 	if (!machine_is_olpc() || olpc_has_vsa())
-		return;
+		return -ENODEV;
 
 	printk(KERN_INFO "PCI: Using configuration type OLPC\n");
 	raw_pci_ops = &pci_olpc_conf;
 	is_lx = is_geode_lx();
+	return 0;
 }
diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h
index f3972b1..720c4c5 100644
--- a/arch/x86/pci/pci.h
+++ b/arch/x86/pci/pci.h
@@ -101,7 +101,7 @@ extern struct pci_raw_ops pci_direct_conf1;
 extern int pci_direct_probe(void);
 extern void pci_direct_init(int type);
 extern void pci_pcbios_init(void);
-extern void pci_olpc_init(void);
+extern int pci_olpc_init(void);
 
 /* pci-mmconfig.c */
 
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 23476c2..efa2ba7 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -106,9 +106,9 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 		do_realtime((struct timespec *)tv);
 		tv->tv_usec /= 1000;
 		if (unlikely(tz != NULL)) {
-			/* This relies on gcc inlining the memcpy. We'll notice
-			   if it ever fails to do so. */
-			memcpy(tz, &gtod->sys_tz, sizeof(struct timezone));
+			/* Avoid memcpy. Some old compilers fail to inline it */
+			tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
+			tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
 		}
 		return 0;
 	}
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 126766d..3525ef5 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -60,7 +60,7 @@ xmaddr_t arbitrary_virt_to_machine(unsigned long address)
 {
 	unsigned int level;
 	pte_t *pte = lookup_address(address, &level);
-	unsigned offset = address & PAGE_MASK;
+	unsigned offset = address & ~PAGE_MASK;
 
 	BUG_ON(pte == NULL);