Merge branch 'x86/fpu' into x86/cleanups

17 files changed, 93 insertions, 85 deletions

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/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/vmi.h b/arch/x86/include/asm/vmi.h
index b7c0dea119f..61e08c0a290 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/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/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-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/setup.c b/arch/x86/kernel/setup.c
index 81f5d22747a..6adab307210 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -795,6 +795,9 @@ 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();
 
@@ -881,13 +884,8 @@ 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 1a3c3253f0e..161011342c1 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/traps.c b/arch/x86/kernel/traps.c
index 04d242ab016..f5a640ba04b 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -664,7 +664,7 @@ void math_error(void __user *ip)
 {
 	struct task_struct *task;
 	siginfo_t info;
-	unsigned short cwd, swd;
+	unsigned short cwd, swd, err;
 
 	/*
 	 * Save the info for the exception handler and clear the error.
@@ -675,7 +675,6 @@ void math_error(void __user *ip)
 	task->thread.error_code = 0;
 	info.si_signo = SIGFPE;
 	info.si_errno = 0;
-	info.si_code = __SI_FAULT;
 	info.si_addr = ip;
 	/*
 	 * (~cwd & swd) will mask out exceptions that are not set to unmasked
@@ -689,34 +688,28 @@ void math_error(void __user *ip)
 	 */
 	cwd = get_fpu_cwd(task);
 	swd = get_fpu_swd(task);
-	switch (swd & ~cwd & 0x3f) {
-	case 0x000: /* No unmasked exception */
-#ifdef CONFIG_X86_32
-		return;
-#endif
-	default: /* Multiple exceptions */
-		break;
-	case 0x001: /* Invalid Op */
+
+	err = swd & ~cwd;
+
+	if (err & 0x001) {	/* Invalid op */
 		/*
 		 * swd & 0x240 == 0x040: Stack Underflow
 		 * swd & 0x240 == 0x240: Stack Overflow
 		 * User must clear the SF bit (0x40) if set
 		 */
 		info.si_code = FPE_FLTINV;
-		break;
-	case 0x002: /* Denormalize */
-	case 0x010: /* Underflow */
-		info.si_code = FPE_FLTUND;
-		break;
-	case 0x004: /* Zero Divide */
+	} else if (err & 0x004) { /* Divide by Zero */
 		info.si_code = FPE_FLTDIV;
-		break;
-	case 0x008: /* Overflow */
+	} else if (err & 0x008) { /* Overflow */
 		info.si_code = FPE_FLTOVF;
-		break;
-	case 0x020: /* Precision */
+	} else if (err & 0x012) { /* Denormal, Underflow */
+		info.si_code = FPE_FLTUND;
+	} else if (err & 0x020) { /* Precision */
 		info.si_code = FPE_FLTRES;
-		break;
+	} else {
+		/* If we're using IRQ 13, or supposedly even some trap 16
+		   implementations, it's possible we get a spurious trap... */
+		return;		/* Spurious trap, no error */
 	}
 	force_sig_info(SIGFPE, &info, task);
 }
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 8087e0cd877..23206ba1687 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -841,8 +841,6 @@ static inline int __init activate_vmi(void)
 
 void __init vmi_init(void)
 {
-	unsigned long flags;
-
 	if (!vmi_rom)
 		probe_vmi_rom();
 	else
@@ -854,13 +852,21 @@ 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/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 716d26f0e5d..e9f80c744cf 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/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;