25 files changed, 362 insertions, 124 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5e618c3b4720..77807d4769c9 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -82,6 +82,7 @@ obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
 obj-$(CONFIG_KVM_GUEST)         += kvm.o
 obj-$(CONFIG_KVM_CLOCK)         += kvmclock.o
 obj-$(CONFIG_PARAVIRT)          += paravirt.o paravirt_patch_$(BITS).o
+obj-$(CONFIG_PARAVIRT_CLOCK)    += pvclock.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)   += pcspeaker.o
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index c49ebcc6c41e..33c5216fd3e1 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 5910020c3f24..0633cfd0dc29 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 af4a867a097c..777a7ff075de 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 46d4034d9f37..206791eb46e3 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/entry_32.S b/arch/x86/kernel/entry_32.S
index 2a609dc3271c..c778e4fa55a2 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -248,6 +248,7 @@ ENTRY(resume_userspace)
         DISABLE_INTERRUPTS(CLBR_ANY)    # make sure we don't miss an interrupt
                                         # setting need_resched or sigpending
                                         # between sampling and the iret
+        TRACE_IRQS_OFF
         movl TI_flags(%ebp), %ecx
         andl $_TIF_WORK_MASK, %ecx      # is there any work to be done on
                                         # int/exception return?
diff --git a/arch/x86/kernel/geode_32.c b/arch/x86/kernel/geode_32.c
index e8edd63ab000..9b08e852fd1a 100644
--- a/arch/x86/kernel/geode_32.c
+++ b/arch/x86/kernel/geode_32.c
@@ -166,6 +166,8 @@ int geode_has_vsa2(void)
         static int has_vsa2 = -1;
 
         if (has_vsa2 == -1) {
+                u16 val;
+
                 /*
                  * The VSA has virtual registers that we can query for a
                  * signature.
@@ -173,7 +175,8 @@ int geode_has_vsa2(void)
                 outw(VSA_VR_UNLOCK, VSA_VRC_INDEX);
                 outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX);
 
-                has_vsa2 = (inw(VSA_VRC_DATA) == VSA_SIG);
+                val = inw(VSA_VRC_DATA);
+                has_vsa2 = (val == AMD_VSA_SIG || val == GSW_VSA_SIG);
         }
 
         return has_vsa2;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index b2cc73768a9d..f7357cc0162c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -189,7 +189,7 @@ default_entry:
          * this stage.
          */
 
-#define KPMDS ((0x100000000-__PAGE_OFFSET) >> 30) /* Number of kernel PMDs */
+#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
 
         xorl %ebx,%ebx                          /* %ebx is kept at zero */
 
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e03cc952f233..95e80e5033c3 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;
 
@@ -148,7 +162,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
         int ret;
 
         if (!cpu_has_fxsr)
-                return -ENODEV;
+                return -EIO;
 
         ret = init_fpu(target);
         if (ret)
@@ -165,7 +179,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
         int ret;
 
         if (!cpu_has_fxsr)
-                return -ENODEV;
+                return -EIO;
 
         ret = init_fpu(target);
         if (ret)
@@ -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 3d01e47777db..a4f93b4120c1 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/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index a40d54fc1fdd..4dc8600d9d20 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2130,14 +2130,10 @@ static inline void __init check_timer(void)
 {
         int apic1, pin1, apic2, pin2;
         int vector;
-        unsigned int ver;
         unsigned long flags;
 
         local_irq_save(flags);
 
-        ver = apic_read(APIC_LVR);
-        ver = GET_APIC_VERSION(ver);
-
         /*
          * get/set the timer IRQ vector:
          */
@@ -2150,15 +2146,11 @@ static inline void __init check_timer(void)
          * mode for the 8259A whenever interrupts are routed
          * through I/O APICs.  Also IRQ0 has to be enabled in
          * the 8259A which implies the virtual wire has to be
-         * disabled in the local APIC.  Finally timer interrupts
-         * need to be acknowledged manually in the 8259A for
-         * timer_interrupt() and for the i82489DX when using
-         * the NMI watchdog.
+         * disabled in the local APIC.
          */
         apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
         init_8259A(1);
-        timer_ack = !cpu_has_tsc;
-        timer_ack |= (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
+        timer_ack = 1;
         if (timer_over_8254 > 0)
                 enable_8259A_irq(0);
 
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 4bc1be5d5472..87edf1ceb1df 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -18,6 +18,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/kvm_para.h>
+#include <asm/pvclock.h>
 #include <asm/arch_hooks.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
@@ -36,83 +37,47 @@ static int parse_no_kvmclock(char *arg)
 early_param("no-kvmclock", parse_no_kvmclock);
 
 /* The hypervisor will put information about time periodically here */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock);
-#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock);
+static struct pvclock_wall_clock wall_clock;
 
-static inline u64 kvm_get_delta(u64 last_tsc)
-{
-        int cpu = smp_processor_id();
-        u64 delta = native_read_tsc() - last_tsc;
-        return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE;
-}
-
-static struct kvm_wall_clock wall_clock;
-static cycle_t kvm_clock_read(void);
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * 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;
+        struct pvclock_vcpu_time_info *vcpu_time;
         struct timespec ts;
-        int version, nsec;
         int low, high;
 
         low = (int)__pa(&wall_clock);
         high = ((u64)__pa(&wall_clock) >> 32);
+        native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
 
-        delta = kvm_clock_read();
+        vcpu_time = &get_cpu_var(hv_clock);
+        pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
+        put_cpu_var(hv_clock);
 
-        native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
-        do {
-                version = wall_clock.wc_version;
-                rmb();
-                wc_sec = wall_clock.wc_sec;
-                wc_nsec = wall_clock.wc_nsec;
-                rmb();
-        } while ((wall_clock.wc_version != version) || (version & 1));
-
-        delta = kvm_clock_read() - delta;
-        delta += wc_nsec;
-        nsec = do_div(delta, NSEC_PER_SEC);
-        set_normalized_timespec(&ts, wc_sec + delta, nsec);
-        /*
-         * Of all mechanisms of time adjustment I've tested, this one
-         * was the champion!
-         */
-        return ts.tv_sec + 1;
+        return ts.tv_sec;
 }
 
-int kvm_set_wallclock(unsigned long now)
+static int kvm_set_wallclock(unsigned long now)
 {
-        return 0;
+        return -1;
 }
 
-/*
- * This is our read_clock function. The host puts an tsc timestamp each time
- * it updates a new time. Without the tsc adjustment, we can have a situation
- * in which a vcpu starts to run earlier (smaller system_time), but probes
- * time later (compared to another vcpu), leading to backwards time
- */
 static cycle_t kvm_clock_read(void)
 {
-        u64 last_tsc, now;
-        int cpu;
+        struct pvclock_vcpu_time_info *src;
+        cycle_t ret;
 
-        preempt_disable();
-        cpu = smp_processor_id();
-
-        last_tsc = get_clock(cpu, tsc_timestamp);
-        now = get_clock(cpu, system_time);
-
-        now += kvm_get_delta(last_tsc);
-        preempt_enable();
-
-        return now;
+        src = &get_cpu_var(hv_clock);
+        ret = pvclock_clocksource_read(src);
+        put_cpu_var(hv_clock);
+        return ret;
 }
+
 static struct clocksource kvm_clock = {
         .name = "kvm-clock",
         .read = kvm_clock_read,
@@ -123,13 +88,14 @@ static struct clocksource kvm_clock = {
         .flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static int kvm_register_clock(void)
+static int kvm_register_clock(char *txt)
 {
         int cpu = smp_processor_id();
         int low, high;
         low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
         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);
 }
 
@@ -140,12 +106,20 @@ static void kvm_setup_secondary_clock(void)
          * Now that the first cpu already had this clocksource initialized,
          * we shouldn't fail.
          */
-        WARN_ON(kvm_register_clock());
+        WARN_ON(kvm_register_clock("secondary cpu clock"));
         /* ok, done with our trickery, call native */
         setup_secondary_APIC_clock();
 }
 #endif
 
+#ifdef CONFIG_SMP
+void __init kvm_smp_prepare_boot_cpu(void)
+{
+        WARN_ON(kvm_register_clock("primary cpu clock"));
+        native_smp_prepare_boot_cpu();
+}
+#endif
+
 /*
  * After the clock is registered, the host will keep writing to the
  * registered memory location. If the guest happens to shutdown, this memory
@@ -174,7 +148,7 @@ void __init kvmclock_init(void)
                 return;
 
         if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
-                if (kvm_register_clock())
+                if (kvm_register_clock("boot clock"))
                         return;
                 pv_time_ops.get_wallclock = kvm_get_wallclock;
                 pv_time_ops.set_wallclock = kvm_set_wallclock;
@@ -182,6 +156,9 @@ void __init kvmclock_init(void)
 #ifdef CONFIG_X86_LOCAL_APIC
                 pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
 #endif
+#ifdef CONFIG_SMP
+                smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+#endif
                 machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
                 machine_ops.crash_shutdown  = kvm_crash_shutdown;
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index 3cad17fe026b..07c0f828f488 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -155,6 +155,7 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable)
         wrmsr(msr, value, dummy);
         return 0;
 }
+EXPORT_SYMBOL_GPL(geode_mfgpt_toggle_event);
 
 int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable)
 {
@@ -222,6 +223,7 @@ int geode_mfgpt_alloc_timer(int timer, int domain)
         /* No timers available - too bad */
         return -1;
 }
+EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer);
 
 
 #ifdef CONFIG_GEODE_MFGPT_TIMER
diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index 11b14bbaa61e..84160f74eeb0 100644
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -26,7 +26,6 @@
 
 #include <asm/smp.h>
 #include <asm/nmi.h>
-#include <asm/timer.h>
 
 #include "mach_traps.h"
 
@@ -82,7 +81,7 @@ int __init check_nmi_watchdog(void)
 
         prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
         if (!prev_nmi_count)
-                goto error;
+                return -1;
 
         printk(KERN_INFO "Testing NMI watchdog ... ");
 
@@ -119,7 +118,7 @@ int __init check_nmi_watchdog(void)
         if (!atomic_read(&nmi_active)) {
                 kfree(prev_nmi_count);
                 atomic_set(&nmi_active, -1);
-                goto error;
+                return -1;
         }
         printk("OK.\n");
 
@@ -130,10 +129,6 @@ int __init check_nmi_watchdog(void)
 
         kfree(prev_nmi_count);
         return 0;
-error:
-        timer_ack = !cpu_has_tsc;
-
-        return -1;
 }
 
 static int __init setup_nmi_watchdog(char *str)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index c5ef1af8e79d..dc00a1331ace 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -378,6 +378,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
         struct page *page;
         unsigned long dma_mask = 0;
         dma_addr_t bus;
+        int noretry = 0;
 
         /* ignore region specifiers */
         gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
@@ -397,20 +398,25 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
         if (dev->dma_mask == NULL)
                 return NULL;
 
-        /* Don't invoke OOM killer */
-        gfp |= __GFP_NORETRY;
+        /* Don't invoke OOM killer or retry in lower 16MB DMA zone */
+        if (gfp & __GFP_DMA)
+                noretry = 1;
 
 #ifdef CONFIG_X86_64
         /* Why <=? Even when the mask is smaller than 4GB it is often
            larger than 16MB and in this case we have a chance of
            finding fitting memory in the next higher zone first. If
            not retry with true GFP_DMA. -AK */
-        if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
+        if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
                 gfp |= GFP_DMA32;
+                if (dma_mask < DMA_32BIT_MASK)
+                        noretry = 1;
+        }
 #endif
 
  again:
-        page = dma_alloc_pages(dev, gfp, get_order(size));
+        page = dma_alloc_pages(dev,
+                noretry ? gfp | __GFP_NORETRY : gfp, get_order(size));
         if (page == NULL)
                 return NULL;
 
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c07455d1695f..aa8ec928caa8 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;
@@ -606,6 +629,12 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
                 pci_write_config_dword(dev, 0x90, ctl);
         }
+
+        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_32.c b/arch/x86/kernel/process_32.c
index f8476dfbb60d..e2db9ac5c61c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -333,6 +333,7 @@ void flush_thread(void)
         /*
          * Forget coprocessor state..
          */
+        tsk->fpu_counter = 0;
         clear_fpu(tsk);
         clear_used_math();
 }
@@ -649,8 +650,11 @@ 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 e2319f39988b..c6eb5c91e5f6 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -294,6 +294,7 @@ void flush_thread(void)
         /*
          * Forget coprocessor state..
          */
+        tsk->fpu_counter = 0;
         clear_fpu(tsk);
         clear_used_math();
 }
@@ -658,8 +659,11 @@ __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/pvclock.c b/arch/x86/kernel/pvclock.c
new file mode 100644
index 000000000000..05fbe9a0325a
--- /dev/null
+++ b/arch/x86/kernel/pvclock.c
@@ -0,0 +1,141 @@
+/*  paravirtual clock -- common code used by kvm/xen
+
+    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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+*/
+
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <asm/pvclock.h>
+
+/*
+ * These are perodically updated
+ *    xen: magic shared_info page
+ *    kvm: gpa registered via msr
+ * and then copied here.
+ */
+struct pvclock_shadow_time {
+        u64 tsc_timestamp;     /* TSC at last update of time vals.  */
+        u64 system_timestamp;  /* Time, in nanosecs, since boot.    */
+        u32 tsc_to_nsec_mul;
+        int tsc_shift;
+        u32 version;
+};
+
+/*
+ * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
+ * yielding a 64-bit result.
+ */
+static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
+{
+        u64 product;
+#ifdef __i386__
+        u32 tmp1, tmp2;
+#endif
+
+        if (shift < 0)
+                delta >>= -shift;
+        else
+                delta <<= shift;
+
+#ifdef __i386__
+        __asm__ (
+                "mul  %5       ; "
+                "mov  %4,%%eax ; "
+                "mov  %%edx,%4 ; "
+                "mul  %5       ; "
+                "xor  %5,%5    ; "
+                "add  %4,%%eax ; "
+                "adc  %5,%%edx ; "
+                : "=A" (product), "=r" (tmp1), "=r" (tmp2)
+                : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
+#elif __x86_64__
+        __asm__ (
+                "mul %%rdx ; shrd $32,%%rdx,%%rax"
+                : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+#else
+#error implement me!
+#endif
+
+        return product;
+}
+
+static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow)
+{
+        u64 delta = native_read_tsc() - shadow->tsc_timestamp;
+        return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
+}
+
+/*
+ * Reads a consistent set of time-base values from hypervisor,
+ * into a shadow data area.
+ */
+static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst,
+                                        struct pvclock_vcpu_time_info *src)
+{
+        do {
+                dst->version = src->version;
+                rmb();          /* fetch version before data */
+                dst->tsc_timestamp     = src->tsc_timestamp;
+                dst->system_timestamp  = src->system_time;
+                dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
+                dst->tsc_shift         = src->tsc_shift;
+                rmb();          /* test version after fetching data */
+        } while ((src->version & 1) || (dst->version != src->version));
+
+        return dst->version;
+}
+
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+{
+        struct pvclock_shadow_time shadow;
+        unsigned version;
+        cycle_t ret, offset;
+
+        do {
+                version = pvclock_get_time_values(&shadow, src);
+                barrier();
+                offset = pvclock_get_nsec_offset(&shadow);
+                ret = shadow.system_timestamp + offset;
+                barrier();
+        } while (version != src->version);
+
+        return ret;
+}
+
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
+                            struct pvclock_vcpu_time_info *vcpu_time,
+                            struct timespec *ts)
+{
+        u32 version;
+        u64 delta;
+        struct timespec now;
+
+        /* get wallclock at system boot */
+        do {
+                version = wall_clock->version;
+                rmb();          /* fetch version before time */
+                now.tv_sec  = wall_clock->sec;
+                now.tv_nsec = wall_clock->nsec;
+                rmb();          /* fetch time before checking version */
+        } while ((wall_clock->version & 1) || (version != wall_clock->version));
+
+        delta = pvclock_clocksource_read(vcpu_time);    /* time since system boot */
+        delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
+
+        now.tv_nsec = do_div(delta, NSEC_PER_SEC);
+        now.tv_sec = delta;
+
+        set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+}
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 9615eee9b775..05191bbc68b8 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -4,6 +4,8 @@
 #include <linux/acpi.h>
 #include <linux/bcd.h>
 #include <linux/mc146818rtc.h>
+#include <linux/platform_device.h>
+#include <linux/pnp.h>
 
 #include <asm/time.h>
 #include <asm/vsyscall.h>
@@ -197,3 +199,35 @@ unsigned long long native_read_tsc(void)
 }
 EXPORT_SYMBOL(native_read_tsc);
 
+
+static struct resource rtc_resources[] = {
+        [0] = {
+                .start  = RTC_PORT(0),
+                .end    = RTC_PORT(1),
+                .flags  = IORESOURCE_IO,
+        },
+        [1] = {
+                .start  = RTC_IRQ,
+                .end    = RTC_IRQ,
+                .flags  = IORESOURCE_IRQ,
+        }
+};
+
+static struct platform_device rtc_device = {
+        .name           = "rtc_cmos",
+        .id             = -1,
+        .resource       = rtc_resources,
+        .num_resources  = ARRAY_SIZE(rtc_resources),
+};
+
+static __init int add_rtc_cmos(void)
+{
+#ifdef CONFIG_PNP
+        if (!pnp_platform_devices)
+                platform_device_register(&rtc_device);
+#else
+        platform_device_register(&rtc_device);
+#endif /* CONFIG_PNP */
+        return 0;
+}
+device_initcall(add_rtc_cmos);
diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c
index 2c5f8b213e86..5a2f8e063887 100644
--- a/arch/x86/kernel/setup_32.c
+++ b/arch/x86/kernel/setup_32.c
@@ -532,10 +532,16 @@ static void __init reserve_crashkernel(void)
                                         (unsigned long)(crash_size >> 20),
                                         (unsigned long)(crash_base >> 20),
                                         (unsigned long)(total_mem >> 20));
+
+                        if (reserve_bootmem(crash_base, crash_size,
+                                        BOOTMEM_EXCLUSIVE) < 0) {
+                                printk(KERN_INFO "crashkernel reservation "
+                                        "failed - memory is in use\n");
+                                return;
+                        }
+
                         crashk_res.start = crash_base;
                         crashk_res.end   = crash_base + crash_size - 1;
-                        reserve_bootmem(crash_base, crash_size,
-                                        BOOTMEM_DEFAULT);
                 } else
                         printk(KERN_INFO "crashkernel reservation failed - "
                                         "you have to specify a base address\n");
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 38988491c622..3e1cecedde42 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -996,7 +996,6 @@ do_rest:
 #endif
                 cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
                 cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
-                cpu_clear(cpu, cpu_possible_map);
                 cpu_clear(cpu, cpu_present_map);
                 per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
         }
@@ -1190,6 +1189,7 @@ 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 +1206,7 @@ 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 +1246,8 @@ 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/traps_32.c b/arch/x86/kernel/traps_32.c
index bde6f63e15d5..08d752de4eee 100644
--- a/arch/x86/kernel/traps_32.c
+++ b/arch/x86/kernel/traps_32.c
@@ -544,6 +544,7 @@ vm86_trap:
 #define DO_ERROR(trapnr, signr, str, name)                              \
 void do_##name(struct pt_regs *regs, long error_code)                   \
 {                                                                       \
+        trace_hardirqs_fixup();                                         \
         if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr)  \
                                                 == NOTIFY_STOP)         \
                 return;                                                 \
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index e4790728b224..65b70637ad97 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -14,7 +14,10 @@
 
 #include "mach_timer.h"
 
-static int tsc_enabled;
+/* native_sched_clock() is called before tsc_init(), so
+   we must start with the TSC soft disabled to prevent
+   erroneous rdtsc usage on !cpu_has_tsc processors */
+static int tsc_disabled = -1;
 
 /*
  * On some systems the TSC frequency does not
@@ -28,8 +31,8 @@ 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 +123,7 @@ 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 +325,6 @@ 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 +338,7 @@ 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;
 }
@@ -403,7 +405,7 @@ void __init tsc_init(void)
 {
         int cpu;
 
-        if (!cpu_has_tsc)
+        if (!cpu_has_tsc || tsc_disabled > 0)
                 return;
 
         cpu_khz = calculate_cpu_khz();
@@ -414,6 +416,9 @@ void __init tsc_init(void)
                 return;
         }
 
+        /* now allow native_sched_clock() to use rdtsc */
+        tsc_disabled = 0;
+
         printk("Detected %lu.%03lu MHz processor.\n",
                                 (unsigned long)cpu_khz / 1000,
                                 (unsigned long)cpu_khz % 1000);
@@ -441,8 +446,6 @@ 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 fcc16e58609e..1784b8077a12 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);
 }