39 files changed, 253 insertions, 194 deletions

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index b815664fe370..8e99073b9e0f 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -520,6 +520,7 @@ config X86_PTRACE_BTS
         bool "Branch Trace Store"
         default y
         depends on X86_DEBUGCTLMSR
+        depends on BROKEN
         help
           This adds a ptrace interface to the hardware's branch trace store.
 
diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c
index 0be77b39328a..7e8e8b25f5f6 100644
--- a/arch/x86/boot/tty.c
+++ b/arch/x86/boot/tty.c
@@ -74,7 +74,7 @@ static int kbd_pending(void)
 {
         u8 pending;
         asm volatile("int $0x16; setnz %0"
-                     : "=rm" (pending)
+                     : "=qm" (pending)
                      : "a" (0x0100));
         return pending;
 }
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 1a30c0440c6b..ac302a2fa339 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -251,13 +251,6 @@ struct amd_iommu {
         /* Pointer to PCI device of this IOMMU */
         struct pci_dev *dev;
 
-        /*
-         * Capability pointer. There could be more than one IOMMU per PCI
-         * device function if there are more than one AMD IOMMU capability
-         * pointers.
-         */
-        u16 cap_ptr;
-
         /* physical address of MMIO space */
         u64 mmio_phys;
         /* virtual address of MMIO space */
@@ -266,6 +259,13 @@ struct amd_iommu {
         /* capabilities of that IOMMU read from ACPI */
         u32 cap;
 
+        /*
+         * Capability pointer. There could be more than one IOMMU per PCI
+         * device function if there are more than one AMD IOMMU capability
+         * pointers.
+         */
+        u16 cap_ptr;
+
         /* pci domain of this IOMMU */
         u16 pci_seg;
 
@@ -284,19 +284,19 @@ struct amd_iommu {
         /* size of command buffer */
         u32 cmd_buf_size;
 
-        /* event buffer virtual address */
-        u8 *evt_buf;
         /* size of event buffer */
         u32 evt_buf_size;
+        /* event buffer virtual address */
+        u8 *evt_buf;
         /* MSI number for event interrupt */
         u16 evt_msi_num;
 
-        /* if one, we need to send a completion wait command */
-        int need_sync;
-
         /* true if interrupts for this IOMMU are already enabled */
         bool int_enabled;
 
+        /* if one, we need to send a completion wait command */
+        int need_sync;
+
         /* default dma_ops domain for that IOMMU */
         struct dma_ops_domain *default_dom;
 };
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 7f225a4b2a26..097794ff6b79 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -71,15 +71,13 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
 /* Make sure we keep the same behaviour */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-#ifdef CONFIG_X86_32
-        return 0;
-#else
+#ifdef CONFIG_X86_64
         struct dma_mapping_ops *ops = get_dma_ops(dev);
         if (ops->mapping_error)
                 return ops->mapping_error(dev, dma_addr);
 
-        return (dma_addr == bad_dma_address);
 #endif
+        return (dma_addr == bad_dma_address);
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
index 72c5a190bf48..a95008457ea4 100644
--- a/arch/x86/include/asm/ds.h
+++ b/arch/x86/include/asm/ds.h
@@ -23,12 +23,13 @@
 #ifndef _ASM_X86_DS_H
 #define _ASM_X86_DS_H
 
-#ifdef CONFIG_X86_DS
 
 #include <linux/types.h>
 #include <linux/init.h>
 
 
+#ifdef CONFIG_X86_DS
+
 struct task_struct;
 
 /*
@@ -232,7 +233,8 @@ extern void ds_free(struct ds_context *context);
 
 #else /* CONFIG_X86_DS */
 
-#define ds_init_intel(config) do {} while (0)
+struct cpuinfo_x86;
+static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
 
 #endif /* CONFIG_X86_DS */
 #endif /* _ASM_X86_DS_H */
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
index 5b28995d664e..d02d936840a3 100644
--- a/arch/x86/include/asm/pci_64.h
+++ b/arch/x86/include/asm/pci_64.h
@@ -34,8 +34,6 @@ extern void pci_iommu_alloc(void);
  */
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
 
-#if defined(CONFIG_GART_IOMMU) || defined(CONFIG_CALGARY_IOMMU)
-
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
         dma_addr_t ADDR_NAME;
 #define DECLARE_PCI_UNMAP_LEN(LEN_NAME)         \
@@ -49,18 +47,6 @@ extern void pci_iommu_alloc(void);
 #define pci_unmap_len_set(PTR, LEN_NAME, VAL)           \
         (((PTR)->LEN_NAME) = (VAL))
 
-#else
-/* No IOMMU */
-
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
-#define pci_unmap_addr(PTR, ADDR_NAME)          (0)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
-#define pci_unmap_len(PTR, LEN_NAME)            (0)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)   do { } while (0)
-
-#endif
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_PCI_64_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index d1531c8480b7..eefb0594b058 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -271,8 +271,6 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
                               struct user_desc __user *info, int can_allocate);
 
-#define __ARCH_WANT_COMPAT_SYS_PTRACE
-
 #endif /* __KERNEL__ */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 4850e4b02b61..ff386ff50ed7 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -239,7 +239,7 @@ struct pci_bus;
 void set_pci_bus_resources_arch_default(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()                    (boot_cpu_data.x86_max_cores > 1)
+#define mc_capable()    (cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids)
 #define smt_capable()                   (smp_num_siblings > 1)
 #endif
 
diff --git a/arch/x86/include/asm/vmi.h b/arch/x86/include/asm/vmi.h
index b7c0dea119fe..61e08c0a2907 100644
--- a/arch/x86/include/asm/vmi.h
+++ b/arch/x86/include/asm/vmi.h
@@ -223,9 +223,15 @@ struct pci_header {
 } __attribute__((packed));
 
 /* Function prototypes for bootstrapping */
+#ifdef CONFIG_VMI
 extern void vmi_init(void);
+extern void vmi_activate(void);
 extern void vmi_bringup(void);
-extern void vmi_apply_boot_page_allocations(void);
+#else
+static inline void vmi_init(void) {}
+static inline void vmi_activate(void) {}
+static inline void vmi_bringup(void) {}
+#endif
 
 /* State needed to start an application processor in an SMP system. */
 struct vmi_ap_state {
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index e489ff9cb3e2..b62a7667828e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -41,7 +41,7 @@ obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y                           += process.o
 obj-y                           += i387.o xsave.o
 obj-y                           += ptrace.o
-obj-y                           += ds.o
+obj-$(CONFIG_X86_DS)            += ds.o
 obj-$(CONFIG_X86_32)            += tls.o
 obj-$(CONFIG_IA32_EMULATION)    += tls.o
 obj-y                           += step.o
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index e4899e0e8787..0a60d60ed036 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -187,6 +187,8 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
 
         spin_lock_irqsave(&iommu->lock, flags);
         ret = __iommu_queue_command(iommu, cmd);
+        if (!ret)
+                iommu->need_sync = 1;
         spin_unlock_irqrestore(&iommu->lock, flags);
 
         return ret;
@@ -210,10 +212,13 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
         cmd.data[0] = CMD_COMPL_WAIT_INT_MASK;
         CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT);
 
-        iommu->need_sync = 0;
-
         spin_lock_irqsave(&iommu->lock, flags);
 
+        if (!iommu->need_sync)
+                goto out;
+
+        iommu->need_sync = 0;
+
         ret = __iommu_queue_command(iommu, &cmd);
 
         if (ret)
@@ -230,8 +235,9 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
         status &= ~MMIO_STATUS_COM_WAIT_INT_MASK;
         writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET);
 
-        if (unlikely((i == EXIT_LOOP_COUNT) && printk_ratelimit()))
-                printk(KERN_WARNING "AMD IOMMU: Completion wait loop failed\n");
+        if (unlikely(i == EXIT_LOOP_COUNT))
+                panic("AMD IOMMU: Completion wait loop failed\n");
+
 out:
         spin_unlock_irqrestore(&iommu->lock, flags);
 
@@ -254,8 +260,6 @@ static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid)
 
         ret = iommu_queue_command(iommu, &cmd);
 
-        iommu->need_sync = 1;
-
         return ret;
 }
 
@@ -281,8 +285,6 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
 
         ret = iommu_queue_command(iommu, &cmd);
 
-        iommu->need_sync = 1;
-
         return ret;
 }
 
@@ -343,7 +345,7 @@ static int iommu_map(struct protection_domain *dom,
         u64 __pte, *pte, *page;
 
         bus_addr  = PAGE_ALIGN(bus_addr);
-        phys_addr = PAGE_ALIGN(bus_addr);
+        phys_addr = PAGE_ALIGN(phys_addr);
 
         /* only support 512GB address spaces for now */
         if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
@@ -599,7 +601,7 @@ static void dma_ops_free_pagetable(struct dma_ops_domain *dma_dom)
                         continue;
 
                 p2 = IOMMU_PTE_PAGE(p1[i]);
-                for (j = 0; j < 512; ++i) {
+                for (j = 0; j < 512; ++j) {
                         if (!IOMMU_PTE_PRESENT(p2[j]))
                                 continue;
                         p3 = IOMMU_PTE_PAGE(p2[j]);
@@ -762,8 +764,6 @@ static void set_device_domain(struct amd_iommu *iommu,
         write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
         iommu_queue_inv_dev_entry(iommu, devid);
-
-        iommu->need_sync = 1;
 }
 
 /*****************************************************************************
@@ -858,6 +858,9 @@ static int get_device_resources(struct device *dev,
                 print_devid(_bdf, 1);
         }
 
+        if (domain_for_device(_bdf) == NULL)
+                set_device_domain(*iommu, *domain, _bdf);
+
         return 1;
 }
 
@@ -908,7 +911,7 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
         if (address >= dom->aperture_size)
                 return;
 
-        WARN_ON(address & 0xfffULL || address > dom->aperture_size);
+        WARN_ON(address & ~PAGE_MASK || address >= dom->aperture_size);
 
         pte  = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
         pte += IOMMU_PTE_L0_INDEX(address);
@@ -920,8 +923,8 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
 
 /*
  * This function contains common code for mapping of a physically
- * contiguous memory region into DMA address space. It is uses by all
- * mapping functions provided by this IOMMU driver.
+ * contiguous memory region into DMA address space. It is used by all
+ * mapping functions provided with this IOMMU driver.
  * Must be called with the domain lock held.
  */
 static dma_addr_t __map_single(struct device *dev,
@@ -981,7 +984,8 @@ static void __unmap_single(struct amd_iommu *iommu,
         dma_addr_t i, start;
         unsigned int pages;
 
-        if ((dma_addr == 0) || (dma_addr + size > dma_dom->aperture_size))
+        if ((dma_addr == bad_dma_address) ||
+            (dma_addr + size > dma_dom->aperture_size))
                 return;
 
         pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
@@ -1031,8 +1035,7 @@ static dma_addr_t map_single(struct device *dev, phys_addr_t paddr,
         if (addr == bad_dma_address)
                 goto out;
 
-        if (unlikely(iommu->need_sync))
-                iommu_completion_wait(iommu);
+        iommu_completion_wait(iommu);
 
 out:
         spin_unlock_irqrestore(&domain->lock, flags);
@@ -1060,8 +1063,7 @@ static void unmap_single(struct device *dev, dma_addr_t dma_addr,
 
         __unmap_single(iommu, domain->priv, dma_addr, size, dir);
 
-        if (unlikely(iommu->need_sync))
-                iommu_completion_wait(iommu);
+        iommu_completion_wait(iommu);
 
         spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -1127,8 +1129,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
                         goto unmap;
         }
 
-        if (unlikely(iommu->need_sync))
-                iommu_completion_wait(iommu);
+        iommu_completion_wait(iommu);
 
 out:
         spin_unlock_irqrestore(&domain->lock, flags);
@@ -1173,8 +1174,7 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
                 s->dma_address = s->dma_length = 0;
         }
 
-        if (unlikely(iommu->need_sync))
-                iommu_completion_wait(iommu);
+        iommu_completion_wait(iommu);
 
         spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -1225,8 +1225,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
                 goto out;
         }
 
-        if (unlikely(iommu->need_sync))
-                iommu_completion_wait(iommu);
+        iommu_completion_wait(iommu);
 
 out:
         spin_unlock_irqrestore(&domain->lock, flags);
@@ -1257,8 +1256,7 @@ static void free_coherent(struct device *dev, size_t size,
 
         __unmap_single(iommu, domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
 
-        if (unlikely(iommu->need_sync))
-                iommu_completion_wait(iommu);
+        iommu_completion_wait(iommu);
 
         spin_unlock_irqrestore(&domain->lock, flags);
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 30ae2701b3df..c6cc22815d35 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -427,6 +427,10 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
         memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
                         &entry, sizeof(entry));
 
+        /* set head and tail to zero manually */
+        writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+        writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+
         iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
 
         return cmd_buf;
@@ -1074,7 +1078,8 @@ int __init amd_iommu_init(void)
                 goto free;
 
         /* IOMMU rlookup table - find the IOMMU for a specific device */
-        amd_iommu_rlookup_table = (void *)__get_free_pages(GFP_KERNEL,
+        amd_iommu_rlookup_table = (void *)__get_free_pages(
+                        GFP_KERNEL | __GFP_ZERO,
                         get_order(rlookup_table_size));
         if (amd_iommu_rlookup_table == NULL)
                 goto free;
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 04a7f960bbc0..16f94879b525 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -1315,7 +1315,7 @@ void enable_x2apic(void)
         }
 }
 
-void enable_IR_x2apic(void)
+void __init enable_IR_x2apic(void)
 {
 #ifdef CONFIG_INTR_REMAP
         int ret;
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index d3dcd58b87cd..7f05f44b97e9 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -115,9 +115,20 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data)
         u32 i = 0;
 
         if (cpu_family == CPU_HW_PSTATE) {
-                rdmsr(MSR_PSTATE_STATUS, lo, hi);
-                i = lo & HW_PSTATE_MASK;
-                data->currpstate = i;
+                if (data->currpstate == HW_PSTATE_INVALID) {
+                        /* read (initial) hw pstate if not yet set */
+                        rdmsr(MSR_PSTATE_STATUS, lo, hi);
+                        i = lo & HW_PSTATE_MASK;
+
+                        /*
+                         * a workaround for family 11h erratum 311 might cause
+                         * an "out-of-range Pstate if the core is in Pstate-0
+                         */
+                        if (i >= data->numps)
+                                data->currpstate = HW_PSTATE_0;
+                        else
+                                data->currpstate = i;
+                }
                 return 0;
         }
         do {
@@ -1121,6 +1132,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
         }
 
         data->cpu = pol->cpu;
+        data->currpstate = HW_PSTATE_INVALID;
 
         if (powernow_k8_cpu_init_acpi(data)) {
                 /*
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index ab48cfed4d96..65cfb5d7f77f 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -5,6 +5,19 @@
  *  http://www.gnu.org/licenses/gpl.html
  */
 
+
+enum pstate {
+        HW_PSTATE_INVALID = 0xff,
+        HW_PSTATE_0 = 0,
+        HW_PSTATE_1 = 1,
+        HW_PSTATE_2 = 2,
+        HW_PSTATE_3 = 3,
+        HW_PSTATE_4 = 4,
+        HW_PSTATE_5 = 5,
+        HW_PSTATE_6 = 6,
+        HW_PSTATE_7 = 7,
+};
+
 struct powernow_k8_data {
         unsigned int cpu;
 
@@ -23,7 +36,9 @@ struct powernow_k8_data {
         u32 exttype; /* extended interface = 1 */
 
         /* keep track of the current fid / vid or pstate */
-        u32 currvid, currfid, currpstate;
+        u32 currvid;
+        u32 currfid;
+        enum pstate currpstate;
 
         /* the powernow_table includes all frequency and vid/fid pairings:
          * fid are the lower 8 bits of the index, vid are the upper 8 bits.
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 4b031a4ac856..1c838032fd37 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -510,12 +510,9 @@ static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c)
  */
 void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
 {
-        static cpumask_t mce_cpus = CPU_MASK_NONE;
-
         mce_cpu_quirks(c);
 
         if (mce_dont_init ||
-            cpu_test_and_set(smp_processor_id(), mce_cpus) ||
             !mce_available(c))
                 return;
 
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index d1a121443bde..a2d1176c38ee 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -21,8 +21,6 @@
  */
 
 
-#ifdef CONFIG_X86_DS
-
 #include <asm/ds.h>
 
 #include <linux/errno.h>
@@ -211,14 +209,15 @@ static DEFINE_PER_CPU(struct ds_context *, system_context);
 static inline struct ds_context *ds_get_context(struct task_struct *task)
 {
         struct ds_context *context;
+        unsigned long irq;
 
-        spin_lock(&ds_lock);
+        spin_lock_irqsave(&ds_lock, irq);
 
         context = (task ? task->thread.ds_ctx : this_system_context);
         if (context)
                 context->count++;
 
-        spin_unlock(&ds_lock);
+        spin_unlock_irqrestore(&ds_lock, irq);
 
         return context;
 }
@@ -226,55 +225,46 @@ static inline struct ds_context *ds_get_context(struct task_struct *task)
 /*
  * Same as ds_get_context, but allocates the context and it's DS
  * structure, if necessary; returns NULL; if out of memory.
- *
- * pre: requires ds_lock to be held
  */
 static inline struct ds_context *ds_alloc_context(struct task_struct *task)
 {
         struct ds_context **p_context =
                 (task ? &task->thread.ds_ctx : &this_system_context);
         struct ds_context *context = *p_context;
+        unsigned long irq;
 
         if (!context) {
-                spin_unlock(&ds_lock);
-
                 context = kzalloc(sizeof(*context), GFP_KERNEL);
-
-                if (!context) {
-                        spin_lock(&ds_lock);
+                if (!context)
                         return NULL;
-                }
 
                 context->ds = kzalloc(ds_cfg.sizeof_ds, GFP_KERNEL);
                 if (!context->ds) {
                         kfree(context);
-                        spin_lock(&ds_lock);
                         return NULL;
                 }
 
-                spin_lock(&ds_lock);
-                /*
-                 * Check for race - another CPU could have allocated
-                 * it meanwhile:
-                 */
+                spin_lock_irqsave(&ds_lock, irq);
+
                 if (*p_context) {
                         kfree(context->ds);
                         kfree(context);
-                        return *p_context;
-                }
 
-                *p_context = context;
+                        context = *p_context;
+                } else {
+                        *p_context = context;
 
-                context->this = p_context;
-                context->task = task;
+                        context->this = p_context;
+                        context->task = task;
 
-                if (task)
-                        set_tsk_thread_flag(task, TIF_DS_AREA_MSR);
+                        if (task)
+                                set_tsk_thread_flag(task, TIF_DS_AREA_MSR);
 
-                if (!task || (task == current))
-                        wrmsr(MSR_IA32_DS_AREA, (unsigned long)context->ds, 0);
-
-                get_tracer(task);
+                        if (!task || (task == current))
+                                wrmsrl(MSR_IA32_DS_AREA,
+                                       (unsigned long)context->ds);
+                }
+                spin_unlock_irqrestore(&ds_lock, irq);
         }
 
         context->count++;
@@ -288,10 +278,12 @@ static inline struct ds_context *ds_alloc_context(struct task_struct *task)
  */
 static inline void ds_put_context(struct ds_context *context)
 {
+        unsigned long irq;
+
         if (!context)
                 return;
 
-        spin_lock(&ds_lock);
+        spin_lock_irqsave(&ds_lock, irq);
 
         if (--context->count)
                 goto out;
@@ -313,7 +305,7 @@ static inline void ds_put_context(struct ds_context *context)
         kfree(context->ds);
         kfree(context);
  out:
-        spin_unlock(&ds_lock);
+        spin_unlock_irqrestore(&ds_lock, irq);
 }
 
 
@@ -384,6 +376,7 @@ static int ds_request(struct task_struct *task, void *base, size_t size,
         struct ds_context *context;
         unsigned long buffer, adj;
         const unsigned long alignment = (1 << 3);
+        unsigned long irq;
         int error = 0;
 
         if (!ds_cfg.sizeof_ds)
@@ -398,26 +391,27 @@ static int ds_request(struct task_struct *task, void *base, size_t size,
                 return -EOPNOTSUPP;
 
 
-        spin_lock(&ds_lock);
-
-        error = -ENOMEM;
         context = ds_alloc_context(task);
         if (!context)
-                goto out_unlock;
+                return -ENOMEM;
+
+        spin_lock_irqsave(&ds_lock, irq);
 
         error = -EPERM;
         if (!check_tracer(task))
                 goto out_unlock;
 
+        get_tracer(task);
+
         error = -EALREADY;
         if (context->owner[qual] == current)
-                goto out_unlock;
+                goto out_put_tracer;
         error = -EPERM;
         if (context->owner[qual] != NULL)
-                goto out_unlock;
+                goto out_put_tracer;
         context->owner[qual] = current;
 
-        spin_unlock(&ds_lock);
+        spin_unlock_irqrestore(&ds_lock, irq);
 
 
         error = -ENOMEM;
@@ -465,10 +459,17 @@ static int ds_request(struct task_struct *task, void *base, size_t size,
  out_release:
         context->owner[qual] = NULL;
         ds_put_context(context);
+        put_tracer(task);
+        return error;
+
+ out_put_tracer:
+        spin_unlock_irqrestore(&ds_lock, irq);
+        ds_put_context(context);
+        put_tracer(task);
         return error;
 
  out_unlock:
-        spin_unlock(&ds_lock);
+        spin_unlock_irqrestore(&ds_lock, irq);
         ds_put_context(context);
         return error;
 }
@@ -818,13 +819,21 @@ static const struct ds_configuration ds_cfg_var = {
         .sizeof_ds    = sizeof(long) * 12,
         .sizeof_field = sizeof(long),
         .sizeof_rec[ds_bts]   = sizeof(long) * 3,
+#ifdef __i386__
         .sizeof_rec[ds_pebs]  = sizeof(long) * 10
+#else
+        .sizeof_rec[ds_pebs]  = sizeof(long) * 18
+#endif
 };
 static const struct ds_configuration ds_cfg_64 = {
         .sizeof_ds    = 8 * 12,
         .sizeof_field = 8,
         .sizeof_rec[ds_bts]   = 8 * 3,
+#ifdef __i386__
         .sizeof_rec[ds_pebs]  = 8 * 10
+#else
+        .sizeof_rec[ds_pebs]  = 8 * 18
+#endif
 };
 
 static inline void
@@ -878,4 +887,3 @@ void ds_free(struct ds_context *context)
         while (leftovers--)
                 ds_put_context(context);
 }
-#endif /* CONFIG_X86_DS */
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 1f20608d4ca8..b0f61f0dcd0a 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -58,7 +58,7 @@ void __cpuinit mxcsr_feature_mask_init(void)
         stts();
 }
 
-void __init init_thread_xstate(void)
+void __cpuinit init_thread_xstate(void)
 {
         if (!HAVE_HWFP) {
                 xstate_size = sizeof(struct i387_soft_struct);
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index c9513e1ff28d..9043251210fb 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -3608,27 +3608,7 @@ int __init io_apic_get_redir_entries (int ioapic)
 
 int __init probe_nr_irqs(void)
 {
-        int idx;
-        int nr = 0;
-#ifndef CONFIG_XEN
-        int nr_min = 32;
-#else
-        int nr_min = NR_IRQS;
-#endif
-
-        for (idx = 0; idx < nr_ioapics; idx++)
-                nr += io_apic_get_redir_entries(idx) + 1;
-
-        /* double it for hotplug and msi and nmi */
-        nr <<= 1;
-
-        /* something wrong ? */
-        if (nr < nr_min)
-                nr = nr_min;
-        if (WARN_ON(nr > NR_IRQS))
-                nr = NR_IRQS;
-
-        return nr;
+        return NR_IRQS;
 }
 
 /* --------------------------------------------------------------------------
@@ -3775,7 +3755,9 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 void __init setup_ioapic_dest(void)
 {
         int pin, ioapic, irq, irq_entry;
+        struct irq_desc *desc;
         struct irq_cfg *cfg;
+        cpumask_t mask;
 
         if (skip_ioapic_setup == 1)
                 return;
@@ -3792,16 +3774,30 @@ void __init setup_ioapic_dest(void)
                          * cpu is online.
                          */
                         cfg = irq_cfg(irq);
-                        if (!cfg->vector)
+                        if (!cfg->vector) {
                                 setup_IO_APIC_irq(ioapic, pin, irq,
                                                   irq_trigger(irq_entry),
                                                   irq_polarity(irq_entry));
+                                continue;
+
+                        }
+
+                        /*
+                         * Honour affinities which have been set in early boot
+                         */
+                        desc = irq_to_desc(irq);
+                        if (desc->status &
+                            (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
+                                mask = desc->affinity;
+                        else
+                                mask = TARGET_CPUS;
+
 #ifdef CONFIG_INTR_REMAP
-                        else if (intr_remapping_enabled)
-                                set_ir_ioapic_affinity_irq(irq, TARGET_CPUS);
-#endif
+                        if (intr_remapping_enabled)
+                                set_ir_ioapic_affinity_irq(irq, mask);
                         else
-                                set_ioapic_affinity_irq(irq, TARGET_CPUS);
+#endif
+                                set_ioapic_affinity_irq(irq, mask);
                 }
 
         }
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1c9cc431ea4f..e169ae9b6a62 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -128,7 +128,7 @@ static int kvm_register_clock(char *txt)
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
-static void __devinit kvm_setup_secondary_clock(void)
+static void __cpuinit kvm_setup_secondary_clock(void)
 {
         /*
          * Now that the first cpu already had this clocksource initialized,
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 82fb2809ce32..c4b5b24e0217 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -272,13 +272,18 @@ static struct attribute_group mc_attr_group = {
         .name = "microcode",
 };
 
-static void microcode_fini_cpu(int cpu)
+static void __microcode_fini_cpu(int cpu)
 {
         struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
-        mutex_lock(&microcode_mutex);
         microcode_ops->microcode_fini_cpu(cpu);
         uci->valid = 0;
+}
+
+static void microcode_fini_cpu(int cpu)
+{
+        mutex_lock(&microcode_mutex);
+        __microcode_fini_cpu(cpu);
         mutex_unlock(&microcode_mutex);
 }
 
@@ -306,12 +311,16 @@ static int microcode_resume_cpu(int cpu)
          * to this cpu (a bit of paranoia):
          */
         if (microcode_ops->collect_cpu_info(cpu, &nsig)) {
-                microcode_fini_cpu(cpu);
+                __microcode_fini_cpu(cpu);
+                printk(KERN_ERR "failed to collect_cpu_info for resuming cpu #%d\n",
+                                cpu);
                 return -1;
         }
 
-        if (memcmp(&nsig, &uci->cpu_sig, sizeof(nsig))) {
-                microcode_fini_cpu(cpu);
+        if ((nsig.sig != uci->cpu_sig.sig) || (nsig.pf != uci->cpu_sig.pf)) {
+                __microcode_fini_cpu(cpu);
+                printk(KERN_ERR "cached ucode doesn't match the resuming cpu #%d\n",
+                                cpu);
                 /* Should we look for a new ucode here? */
                 return 1;
         }
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 622dc4a21784..a8e62792d171 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -155,6 +155,7 @@ static DEFINE_SPINLOCK(microcode_update_lock);
 static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 {
         struct cpuinfo_x86 *c = &cpu_data(cpu_num);
+        unsigned long flags;
         unsigned int val[2];
 
         memset(csig, 0, sizeof(*csig));
@@ -174,11 +175,16 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
                 csig->pf = 1 << ((val[1] >> 18) & 7);
         }
 
+        /* serialize access to the physical write to MSR 0x79 */
+        spin_lock_irqsave(&microcode_update_lock, flags);
+
         wrmsr(MSR_IA32_UCODE_REV, 0, 0);
         /* see notes above for revision 1.07.  Apparent chip bug */
         sync_core();
         /* get the current revision from MSR 0x8B */
         rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev);
+        spin_unlock_irqrestore(&microcode_update_lock, flags);
+
         pr_debug("microcode: collect_cpu_info : sig=0x%x, pf=0x%x, rev=0x%x\n",
                         csig->sig, csig->pf, csig->rev);
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index f98f4e1dba09..0f4c1fd5a1f4 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -604,6 +604,9 @@ static void __init __get_smp_config(unsigned int early)
                 printk(KERN_INFO "Using ACPI for processor (LAPIC) "
                        "configuration information\n");
 
+        if (!mpf)
+                return;
+
         printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
                mpf->mpf_specification);
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 0e9f1982b1dd..95777b0faa73 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -7,7 +7,8 @@
 
 #include <asm/paravirt.h>
 
-static void default_spin_lock_flags(struct raw_spinlock *lock, unsigned long flags)
+static inline void
+default_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
 {
         __raw_spin_lock(lock);
 }
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index e1e731d78f38..d28bbdc35e4e 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1567,7 +1567,7 @@ static int __init calgary_parse_options(char *p)
                                 ++p;
                         if (*p == '\0')
                                 break;
-                        bridge = simple_strtol(p, &endp, 0);
+                        bridge = simple_strtoul(p, &endp, 0);
                         if (p == endp)
                                 break;
 
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index a42b02b4df68..a35eaa379ff6 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -123,6 +123,8 @@ static void free_iommu(unsigned long offset, int size)
 
         spin_lock_irqsave(&iommu_bitmap_lock, flags);
         iommu_area_free(iommu_gart_bitmap, offset, size);
+        if (offset >= next_bit)
+                next_bit = offset + size;
         spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
 }
 
@@ -743,10 +745,8 @@ void __init gart_iommu_init(void)
         unsigned long scratch;
         long i;
 
-        if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) {
-                printk(KERN_INFO "PCI-GART: No AMD GART found.\n");
+        if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0)
                 return;
-        }
 
 #ifndef CONFIG_AGP_AMD64
         no_agp = 1;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9d5674f7b6cc..bdec76e55594 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -794,6 +794,9 @@ void __init setup_arch(char **cmdline_p)
         printk(KERN_INFO "Command line: %s\n", boot_command_line);
 #endif
 
+        /* VMI may relocate the fixmap; do this before touching ioremap area */
+        vmi_init();
+
         early_cpu_init();
         early_ioremap_init();
 
@@ -880,13 +883,8 @@ void __init setup_arch(char **cmdline_p)
         check_efer();
 #endif
 
-#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
-        /*
-         * Must be before kernel pagetables are setup
-         * or fixmap area is touched.
-         */
-        vmi_init();
-#endif
+        /* Must be before kernel pagetables are setup */
+        vmi_activate();
 
         /* after early param, so could get panic from serial */
         reserve_early_setup_data();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7b1093397319..f71f96fc9e62 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -294,9 +294,7 @@ static void __cpuinit start_secondary(void *unused)
          * fragile that we want to limit the things done here to the
          * most necessary things.
          */
-#ifdef CONFIG_VMI
         vmi_bringup();
-#endif
         cpu_init();
         preempt_disable();
         smp_callin();
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 8b6c393ab9fd..22fd6577156a 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -960,8 +960,6 @@ static inline int __init activate_vmi(void)
 
 void __init vmi_init(void)
 {
-        unsigned long flags;
-
         if (!vmi_rom)
                 probe_vmi_rom();
         else
@@ -973,13 +971,21 @@ void __init vmi_init(void)
 
         reserve_top_address(-vmi_rom->virtual_top);
 
-        local_irq_save(flags);
-        activate_vmi();
-
 #ifdef CONFIG_X86_IO_APIC
         /* This is virtual hardware; timer routing is wired correctly */
         no_timer_check = 1;
 #endif
+}
+
+void vmi_activate(void)
+{
+        unsigned long flags;
+
+        if (!vmi_rom)
+                return;
+
+        local_irq_save(flags);
+        activate_vmi();
         local_irq_restore(flags & X86_EFLAGS_IF);
 }
 
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index b13acb75e822..15c3e6999182 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -310,7 +310,7 @@ static void __init setup_xstate_init(void)
 /*
  * Enable and initialize the xsave feature.
  */
-void __init xsave_cntxt_init(void)
+void __ref xsave_cntxt_init(void)
 {
         unsigned int eax, ebx, ecx, edx;
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f1983d9477cd..410ddbc1aa2e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1038,13 +1038,13 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
         }
 
         rmap_write_protect(vcpu->kvm, sp->gfn);
+        kvm_unlink_unsync_page(vcpu->kvm, sp);
         if (vcpu->arch.mmu.sync_page(vcpu, sp)) {
                 kvm_mmu_zap_page(vcpu->kvm, sp);
                 return 1;
         }
 
         kvm_mmu_flush_tlb(vcpu);
-        kvm_unlink_unsync_page(vcpu->kvm, sp);
         return 0;
 }
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 613ec9aa674a..84eee43bbe74 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -331,6 +331,7 @@ static int FNAME(shadow_walk_entry)(struct kvm_shadow_walk *_sw,
                 r = kvm_read_guest_atomic(vcpu->kvm, gw->pte_gpa[level - 2],
                                           &curr_pte, sizeof(curr_pte));
                 if (r || curr_pte != gw->ptes[level - 2]) {
+                        kvm_mmu_put_page(shadow_page, sptep);
                         kvm_release_pfn_clean(sw->pfn);
                         sw->sptep = NULL;
                         return 1;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d06b4dc0e2ea..a4018b01e1f9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3149,7 +3149,9 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
 
         if (cpu_has_virtual_nmis()) {
                 if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
-                        if (vmx_nmi_enabled(vcpu)) {
+                        if (vcpu->arch.interrupt.pending) {
+                                enable_nmi_window(vcpu);
+                        } else if (vmx_nmi_enabled(vcpu)) {
                                 vcpu->arch.nmi_pending = false;
                                 vcpu->arch.nmi_injected = true;
                         } else {
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 022cd41ea9b4..202864ad49a7 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -401,14 +401,13 @@ static int __init ppro_init(char **cpu_type)
                 *cpu_type = "i386/pii";
                 break;
         case 6 ... 8:
+        case 10 ... 11:
                 *cpu_type = "i386/piii";
                 break;
         case 9:
+        case 13:
                 *cpu_type = "i386/p6_mobile";
                 break;
-        case 10 ... 13:
-                *cpu_type = "i386/p6";
-                break;
         case 14:
                 *cpu_type = "i386/core";
                 break;
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 3f1b81a83e2e..e9f80c744cf3 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -69,7 +69,7 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
         int i;
 
         if (!reset_value) {
-                reset_value = kmalloc(sizeof(unsigned) * num_counters,
+                reset_value = kmalloc(sizeof(reset_value[0]) * num_counters,
                                         GFP_ATOMIC);
                 if (!reset_value)
                         return;
@@ -156,6 +156,8 @@ static void ppro_start(struct op_msrs const * const msrs)
         unsigned int low, high;
         int i;
 
+        if (!reset_value)
+                return;
         for (i = 0; i < num_counters; ++i) {
                 if (reset_value[i]) {
                         CTRL_READ(low, high, msrs, i);
@@ -171,6 +173,8 @@ static void ppro_stop(struct op_msrs const * const msrs)
         unsigned int low, high;
         int i;
 
+        if (!reset_value)
+                return;
         for (i = 0; i < num_counters; ++i) {
                 if (!reset_value[i])
                         continue;
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 3c27a809393b..2051dc96b8e9 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -496,21 +496,24 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015,
                           pci_siemens_interrupt_controller);
 
 /*
- * Regular PCI devices have 256 bytes, but AMD Family 10h Opteron ext config
- * have 4096 bytes.  Even if the device is capable, that doesn't mean we can
- * access it.  Maybe we don't have a way to generate extended config space
- * accesses.   So check it
+ * Regular PCI devices have 256 bytes, but AMD Family 10h/11h CPUs have
+ * 4096 bytes configuration space for each function of their processor
+ * configuration space.
  */
-static void fam10h_pci_cfg_space_size(struct pci_dev *dev)
+static void amd_cpu_pci_cfg_space_size(struct pci_dev *dev)
 {
         dev->cfg_size = pci_cfg_space_size_ext(dev);
 }
-
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, fam10h_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, fam10h_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, fam10h_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, fam10h_pci_cfg_space_size);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1300, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1301, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1302, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1303, amd_cpu_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1304, amd_cpu_pci_cfg_space_size);
 
 /*
  * SB600: Disable BAR1 on device 14.0 to avoid HPET resources from
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 688936044dc9..636ef4caa52d 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -661,12 +661,11 @@ void xen_set_pgd(pgd_t *ptr, pgd_t val)
  * For 64-bit, we must skip the Xen hole in the middle of the address
  * space, just after the big x86-64 virtual hole.
  */
-static int xen_pgd_walk(struct mm_struct *mm,
-                        int (*func)(struct mm_struct *mm, struct page *,
-                                    enum pt_level),
-                        unsigned long limit)
+static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
+                          int (*func)(struct mm_struct *mm, struct page *,
+                                      enum pt_level),
+                          unsigned long limit)
 {
-        pgd_t *pgd = mm->pgd;
         int flush = 0;
         unsigned hole_low, hole_high;
         unsigned pgdidx_limit, pudidx_limit, pmdidx_limit;
@@ -753,6 +752,14 @@ out:
         return flush;
 }
 
+static int xen_pgd_walk(struct mm_struct *mm,
+                        int (*func)(struct mm_struct *mm, struct page *,
+                                    enum pt_level),
+                        unsigned long limit)
+{
+        return __xen_pgd_walk(mm, mm->pgd, func, limit);
+}
+
 /* If we're using split pte locks, then take the page's lock and
    return a pointer to it.  Otherwise return NULL. */
 static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
@@ -854,7 +861,7 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 
         xen_mc_batch();
 
-         if (xen_pgd_walk(mm, xen_pin_page, USER_LIMIT)) {
+        if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
                 /* re-enable interrupts for flushing */
                 xen_mc_issue(0);
 
@@ -998,7 +1005,7 @@ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
                        PT_PMD);
 #endif
 
-        xen_pgd_walk(mm, xen_unpin_page, USER_LIMIT);
+        __xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT);
 
         xen_mc_issue(0);
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index d77da613b1d2..acd9b6705e02 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -362,7 +362,7 @@ static void xen_cpu_die(unsigned int cpu)
                 alternatives_smp_switch(0);
 }
 
-static void xen_play_dead(void)
+static void __cpuinit xen_play_dead(void) /* used only with CPU_HOTPLUG */
 {
         play_dead_common();
         HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index d7422dc2a55c..9e1afae8461f 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -49,7 +49,7 @@ bool xen_vcpu_stolen(int vcpu);
 
 void xen_mark_init_mm_pinned(void);
 
-void __init xen_setup_vcpu_info_placement(void);
+void xen_setup_vcpu_info_placement(void);
 
 #ifdef CONFIG_SMP
 void xen_smp_init(void);