Merge commit 'v2.6.28-rc8' into x86/uv

32 files changed, 223 insertions, 166 deletions

diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c
index 0be77b39328..7e8e8b25f5f 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 1a30c0440c6..ac302a2fa33 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 7f225a4b2a2..097794ff6b7 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 72c5a190bf4..a95008457ea 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 5b28995d664..d02d936840a 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 d1531c8480b..eefb0594b05 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 4850e4b02b6..ff386ff50ed 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/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 664f15280f1..f8cfd00db45 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -46,7 +46,7 @@ int __copy_from_user(void *dst, const void __user *src, unsigned size)
 		return ret;
 	case 10:
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
-			       ret, "q", "", "=r", 16);
+			       ret, "q", "", "=r", 10);
 		if (unlikely(ret))
 			return ret;
 		__get_user_asm(*(u16 *)(8 + (char *)dst),
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index e489ff9cb3e..b62a7667828 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 e4899e0e878..a7b6dec6fc3 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)
@@ -254,8 +259,6 @@ 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 +284,6 @@ 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 +344,7 @@ 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 +600,7 @@ 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 +763,6 @@ 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 +857,9 @@ 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 +910,7 @@ 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 +922,8 @@ 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 +983,8 @@ 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 +1034,7 @@ 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 +1062,7 @@ 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 +1128,7 @@ 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 +1173,7 @@ 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 +1224,7 @@ 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 +1255,7 @@ 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/apic.c b/arch/x86/kernel/apic.c
index 04a7f960bbc..16f94879b52 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 d3dcd58b87c..7f05f44b97e 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 ab48cfed4d9..65cfb5d7f77 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/ds.c b/arch/x86/kernel/ds.c
index d1a121443bd..a2d1176c38e 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 1f20608d4ca..b0f61f0dcd0 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 7a3f2028e2e..9043251210f 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -1140,6 +1140,20 @@ static void __clear_irq_vector(int irq)
 
 	cfg->vector = 0;
 	cpus_clear(cfg->domain);
+
+	if (likely(!cfg->move_in_progress))
+		return;
+	cpus_and(mask, cfg->old_domain, cpu_online_map);
+	for_each_cpu_mask_nr(cpu, mask) {
+		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+								vector++) {
+			if (per_cpu(vector_irq, cpu)[vector] != irq)
+				continue;
+			per_cpu(vector_irq, cpu)[vector] = -1;
+			break;
+		}
+	}
+	cfg->move_in_progress = 0;
 }
 
 void __setup_vector_irq(int cpu)
@@ -3594,27 +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;
 }
 
 /* --------------------------------------------------------------------------
@@ -3761,7 +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;
@@ -3778,16 +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 1c9cc431ea4..e169ae9b6a6 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/mpparse.c b/arch/x86/kernel/mpparse.c
index f98f4e1dba0..0f4c1fd5a1f 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 0e9f1982b1d..95777b0faa7 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 e1e731d78f3..d28bbdc35e4 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 a42b02b4df6..ba7ad83e20a 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);
 }
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 724adfc63cb..cc5a2545dd4 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -169,6 +169,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "0KW626"),
 		},
 	},
+	{   /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */
+		.callback = set_bios_reboot,
+		.ident = "Dell OptiPlex 330",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"),
+			DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
+		},
+	},
 	{	/* Handle problems with rebooting on Dell 2400's */
 		.callback = set_bios_reboot,
 		.ident = "Dell PowerEdge 2400",
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index b13acb75e82..15c3e699918 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 f1983d9477c..410ddbc1aa2 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 613ec9aa674..84eee43bbe7 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 d06b4dc0e2e..a4018b01e1f 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 022cd41ea9b..202864ad49a 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 3f1b81a83e2..e9f80c744cf 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 3c27a809393..2051dc96b8e 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 688936044dc..636ef4caa52 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 d77da613b1d..acd9b6705e0 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 d7422dc2a55..9e1afae8461 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);