Merge branch 'sched/core' into cpus4096

Conflicts:
	include/linux/ftrace.h
	kernel/sched.c

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;
 };

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)

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
 

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);
 

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)

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);
 }

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);
 }
 

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;

arch/x86/oprofile/op_model_ppro.c

@@ -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;