Merge branch 'linus' into x86/irq

28 files changed, 240 insertions, 90 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 671591fcc61d..ff1a7b49a460 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
@@ -765,8 +772,13 @@ 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/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
index 22fab6c4be15..7da00b799cda 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
@@ -12,11 +12,6 @@ ENTRY(_start)
 
 SECTIONS
 {
-        . = HEADER_OFFSET;
-        .header : {
-                 *(.header)
-        }
-
         . = 0;
         .text : {
                  *(.text*)
@@ -50,6 +45,11 @@ SECTIONS
                 __bss_end = .;
         }
 
+        . = HEADER_OFFSET;
+        .header : {
+                *(.header)
+        }
+
         . = ALIGN(16);
         _end = .;
 
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 0c7f64b99e17..159a1c76d2bd 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/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..eb9ddd8efb82 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 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 76769ccb1425..0774b231a28b 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..08a30986d472 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/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 0c37f16b6950..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);
@@ -385,30 +386,37 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
         if (dma_alloc_from_coherent_mem(dev, size, dma_handle, &memory))
                 return memory;
 
-        if (!dev)
+        if (!dev) {
                 dev = &fallback_dev;
+                gfp |= GFP_DMA;
+        }
         dma_mask = dev->coherent_dma_mask;
         if (dma_mask == 0)
-                dma_mask = DMA_32BIT_MASK;
+                dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
 
         /* Device not DMA able */
         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)
+        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.c b/arch/x86/kernel/process.c
index 67e9b4a1e89d..ba370dc8685b 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 f8476dfbb60d..6d5483356e74 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 e2319f39988b..ac54ff56df80 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/ptrace.c b/arch/x86/kernel/ptrace.c
index fb03ef380f0e..a7835f282936 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1303,6 +1303,9 @@ static const struct user_regset_view user_x86_64_view = {
 #define genregs32_get           genregs_get
 #define genregs32_set           genregs_set
 
+#define user_i387_ia32_struct   user_i387_struct
+#define user32_fxsr_struct      user_fxsr_struct
+
 #endif  /* CONFIG_X86_64 */
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
@@ -1315,13 +1318,13 @@ static const struct user_regset x86_32_regsets[] = {
         },
         [REGSET_FP] = {
                 .core_note_type = NT_PRFPREG,
-                .n = sizeof(struct user_i387_struct) / sizeof(u32),
+                .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
                 .size = sizeof(u32), .align = sizeof(u32),
                 .active = fpregs_active, .get = fpregs_get, .set = fpregs_set
         },
         [REGSET_XFP] = {
                 .core_note_type = NT_PRXFPREG,
-                .n = sizeof(struct user_i387_struct) / sizeof(u32),
+                .n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
                 .size = sizeof(u32), .align = sizeof(u32),
                 .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
         },
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.c b/arch/x86/kernel/setup.c
index c0c68c18a788..6f80b852a196 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -12,6 +12,7 @@
 #include <asm/mpspec.h>
 #include <asm/apicdef.h>
 
+#ifdef CONFIG_X86_LOCAL_APIC
 unsigned int num_processors;
 unsigned disabled_cpus __cpuinitdata;
 /* Processor that is doing the boot up */
@@ -23,8 +24,9 @@ EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid);
 
 /* Bitmask of physically existing CPUs */
 physid_mask_t phys_cpu_present_map;
+#endif
 
-#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_SMP)
+#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP)
 /*
  * Copy data used in early init routines from the initial arrays to the
  * per cpu data areas.  These arrays then become expendable and the
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index f2fc8feb727d..6dff1286ad8a 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -951,7 +951,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
 {
         if (c->x86 == 0x6 && c->x86_model >= 0xf)
-                set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability);
+                set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 }
 
 static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 8f75893a6467..0cb7aadc87cd 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -231,7 +231,8 @@ native_smp_call_function_mask(cpumask_t mask,
         wmb();
 
         /* Send a message to other CPUs */
-        if (cpus_equal(mask, allbutself))
+        if (cpus_equal(mask, allbutself) &&
+            cpus_equal(cpu_online_map, cpu_callout_map))
                 send_IPI_allbutself(CALL_FUNCTION_VECTOR);
         else
                 send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6b087ab6cd8f..56078d61c793 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -86,6 +86,7 @@ void *x86_bios_cpu_apicid_early_ptr;
 
 #ifdef CONFIG_X86_32
 u8 apicid_2_node[MAX_APICID];
+static int low_mappings;
 #endif
 
 /* State of each CPU */
@@ -326,6 +327,12 @@ static void __cpuinit start_secondary(void *unused)
                 enable_8259A_irq(0);
         }
 
+#ifdef CONFIG_X86_32
+        while (low_mappings)
+                cpu_relax();
+        __flush_tlb_all();
+#endif
+
         /* This must be done before setting cpu_online_map */
         set_cpu_sibling_map(raw_smp_processor_id());
         wmb();
@@ -1040,14 +1047,20 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 #ifdef CONFIG_X86_32
         /* init low mem mapping */
         clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY,
-                        min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+                min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
         flush_tlb_all();
-#endif
+        low_mappings = 1;
+
+        err = do_boot_cpu(apicid, cpu);
 
+        zap_low_mappings();
+        low_mappings = 0;
+#else
         err = do_boot_cpu(apicid, cpu);
-        if (err < 0) {
+#endif
+        if (err) {
                 Dprintk("do_boot_cpu failed %d\n", err);
-                return err;
+                return -EIO;
         }
 
         /*
@@ -1177,6 +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;
@@ -1193,7 +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();
@@ -1233,6 +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.
@@ -1259,9 +1275,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
         setup_ioapic_dest();
 #endif
         check_nmi_watchdog();
-#ifdef CONFIG_X86_32
-        zap_low_mappings();
-#endif
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
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..068759db63dd 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 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);
 }
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 58882f9f2637..f6c05d0410fb 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -2,6 +2,7 @@
    All C exports should go in the respective C files. */
 
 #include <linux/module.h>
+#include <net/checksum.h>
 #include <linux/smp.h>
 
 #include <asm/processor.h>
@@ -29,6 +30,8 @@ EXPORT_SYMBOL(__copy_from_user_inatomic);
 EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(clear_page);
 
+EXPORT_SYMBOL(csum_partial);
+
 /*
  * Export string functions. We normally rely on gcc builtin for most of these,
  * but gcc sometimes decides not to inline them.