Merge remote-tracking branch 'tip/core/rcu' into next.2012.09.25b

Resolved conflict in kernel/sched/core.c using Peter Zijlstra's
approach from https://lkml.org/lkml/2012/9/5/585.

16 files changed, 115 insertions, 34 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ec3a1aa4abd..50a1d1f9b6d3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -746,10 +746,10 @@ config SWIOTLB
 	def_bool y if X86_64
 	---help---
 	  Support for software bounce buffers used on x86-64 systems
-	  which don't have a hardware IOMMU (e.g. the current generation
-	  of Intel's x86-64 CPUs). Using this PCI devices which can only
-	  access 32-bits of memory can be used on systems with more than
-	  3 GB of memory. If unsure, say Y.
+	  which don't have a hardware IOMMU. Using this PCI devices
+	  which can only access 32-bits of memory can be used on systems
+	  with more than 3 GB of memory.
+	  If unsure, say Y.
 
 config IOMMU_HELPER
 	def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU)
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 682e9c210baa..474ca35b1bce 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -142,7 +142,7 @@ KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)
 
-archscripts:
+archscripts: scripts_basic
 	$(Q)$(MAKE) $(build)=arch/x86/tools relocs
 
 ###
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 93971e841dd5..472b9b783019 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -51,7 +51,8 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 
 extern int m2p_add_override(unsigned long mfn, struct page *page,
 			    struct gnttab_map_grant_ref *kmap_op);
-extern int m2p_remove_override(struct page *page, bool clear_pte);
+extern int m2p_remove_override(struct page *page,
+				struct gnttab_map_grant_ref *kmap_op);
 extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6605a81ba339..8b6defe7eefc 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -586,6 +586,8 @@ extern struct event_constraint intel_westmere_pebs_event_constraints[];
 
 extern struct event_constraint intel_snb_pebs_event_constraints[];
 
+extern struct event_constraint intel_ivb_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_enable(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 7bfb5bec8630..eebd5ffe1bba 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -209,6 +209,15 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config)
 	return -EOPNOTSUPP;
 }
 
+static const struct perf_event_attr ibs_notsupp = {
+	.exclude_user	= 1,
+	.exclude_kernel	= 1,
+	.exclude_hv	= 1,
+	.exclude_idle	= 1,
+	.exclude_host	= 1,
+	.exclude_guest	= 1,
+};
+
 static int perf_ibs_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -229,6 +238,9 @@ static int perf_ibs_init(struct perf_event *event)
 	if (event->pmu != &perf_ibs->pmu)
 		return -ENOENT;
 
+	if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp))
+		return -EINVAL;
+
 	if (config & ~perf_ibs->config_mask)
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7f2739e03e79..6bca492b8547 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2008,6 +2008,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 28: /* Atom */
+	case 54: /* Cedariew */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -2047,7 +2048,6 @@ __init int intel_pmu_init(void)
 	case 42: /* SandyBridge */
 	case 45: /* SandyBridge, "Romely-EP" */
 		x86_add_quirk(intel_sandybridge_quirk);
-	case 58: /* IvyBridge */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
@@ -2072,6 +2072,29 @@ __init int intel_pmu_init(void)
 
 		pr_cont("SandyBridge events, ");
 		break;
+	case 58: /* IvyBridge */
+		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_snb_event_constraints;
+		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		x86_pmu.extra_regs = intel_snb_extra_regs;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
+		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
+
+		pr_cont("IvyBridge events, ");
+		break;
+
 
 	default:
 		switch (x86_pmu.version) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index e38d97bf4259..826054a4f2ee 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -407,6 +407,20 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_ivb_pebs_event_constraints[] = {
+        INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+        INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+        INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
+        INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+        INTEL_EVENT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+        EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *c;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 520b4265fcd2..da02e9cc3754 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void)
 	 * to have an operational LBR which can freeze
 	 * on PMU interrupt
 	 */
-	if (boot_cpu_data.x86_mask < 10) {
+	if (boot_cpu_data.x86_model == 28
+	    && boot_cpu_data.x86_mask < 10) {
 		pr_cont("LBR disabled due to erratum");
 		return;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 0a5571080e74..38e4894165b9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -661,6 +661,11 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
 	}
 }
 
+static struct uncore_event_desc snb_uncore_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+	{ /* end: all zeroes */ },
+};
+
 static struct attribute *snb_uncore_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -704,6 +709,7 @@ static struct intel_uncore_type snb_uncore_cbox = {
 	.constraints	= snb_uncore_cbox_constraints,
 	.ops		= &snb_uncore_msr_ops,
 	.format_group	= &snb_uncore_format_group,
+	.event_descs	= snb_uncore_events,
 };
 
 static struct intel_uncore_type *snb_msr_uncores[] = {
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 4873e62db6a1..9e5bcf1e2376 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
 	if (do_microcode_update(buf, len) == 0)
 		ret = (ssize_t)len;
 
+	if (ret > 0)
+		perf_check_microcode();
+
 	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index e498b18f010c..9fc9aa7ac703 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -318,7 +318,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 		if (val & 0x10) {
 			u8 edge_irr = s->irr & ~s->elcr;
 			int i;
-			bool found;
+			bool found = false;
 			struct kvm_vcpu *vcpu;
 
 			s->init4 = val & 1;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03de1b79..b1eb202ee76a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3619,6 +3619,7 @@ static void seg_setup(int seg)
 
 static int alloc_apic_access_page(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3633,7 +3634,13 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	if (r)
 		goto out;
 
-	kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
+	page = gfn_to_page(kvm, 0xfee00);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.apic_access_page = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -3641,6 +3648,7 @@ out:
 
 static int alloc_identity_pagetable(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3656,8 +3664,13 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	if (r)
 		goto out;
 
-	kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
-			kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.ept_identity_pagetable = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -6575,7 +6588,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	/* Exposing INVPCID only when PCID is exposed */
 	best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
 	if (vmx_invpcid_supported() &&
-	    best && (best->ecx & bit(X86_FEATURE_INVPCID)) &&
+	    best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
 	    guest_cpuid_has_pcid(vcpu)) {
 		exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
@@ -6585,7 +6598,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 			     exec_control);
 		if (best)
-			best->ecx &= ~bit(X86_FEATURE_INVPCID);
+			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 148ed666e311..2966c847d489 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5113,17 +5113,20 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 			!kvm_event_needs_reinjection(vcpu);
 }
 
-static void vapic_enter(struct kvm_vcpu *vcpu)
+static int vapic_enter(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct page *page;
 
 	if (!apic || !apic->vapic_addr)
-		return;
+		return 0;
 
 	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return -EFAULT;
 
 	vcpu->arch.apic->vapic_page = page;
+	return 0;
 }
 
 static void vapic_exit(struct kvm_vcpu *vcpu)
@@ -5430,7 +5433,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-	vapic_enter(vcpu);
+	r = vapic_enter(vcpu);
+	if (r) {
+		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+		return r;
+	}
 
 	r = 1;
 	while (r > 0) {
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index e0e6990723e9..ab1f6a93b527 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -319,7 +319,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
  */
 int devmem_is_allowed(unsigned long pagenr)
 {
-	if (pagenr <= 256)
+	if (pagenr < 256)
 		return 1;
 	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
 		return 0;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 9642d4a38602..1fbe75a95f15 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1452,6 +1452,10 @@ asmlinkage void __init xen_start_kernel(void)
 		pci_request_acs();
 
 		xen_acpi_sleep_register();
+
+		/* Avoid searching for BIOS MP tables */
+		x86_init.mpparse.find_smp_config = x86_init_noop;
+		x86_init.mpparse.get_smp_config = x86_init_uint_noop;
 	}
 #ifdef CONFIG_PCI
 	/* PCI BIOS service won't work from a PV guest. */
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 76ba0e97e530..72213da605f5 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -828,9 +828,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 
 			xen_mc_issue(PARAVIRT_LAZY_MMU);
 		}
-		/* let's use dev_bus_addr to record the old mfn instead */
-		kmap_op->dev_bus_addr = page->index;
-		page->index = (unsigned long) kmap_op;
 	}
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
@@ -857,7 +854,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(m2p_add_override);
-int m2p_remove_override(struct page *page, bool clear_pte)
+int m2p_remove_override(struct page *page,
+		struct gnttab_map_grant_ref *kmap_op)
 {
 	unsigned long flags;
 	unsigned long mfn;
@@ -887,10 +885,8 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 	WARN_ON(!PagePrivate(page));
 	ClearPagePrivate(page);
 
-	if (clear_pte) {
-		struct gnttab_map_grant_ref *map_op =
-			(struct gnttab_map_grant_ref *) page->index;
-		set_phys_to_machine(pfn, map_op->dev_bus_addr);
+	set_phys_to_machine(pfn, page->index);
+	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
 			struct multicall_space mcs;
 			struct gnttab_unmap_grant_ref *unmap_op;
@@ -902,13 +898,13 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 			 * issued. In this case handle is going to -1 because
 			 * it hasn't been modified yet.
 			 */
-			if (map_op->handle == -1)
+			if (kmap_op->handle == -1)
 				xen_mc_flush();
 			/*
-			 * Now if map_op->handle is negative it means that the
+			 * Now if kmap_op->handle is negative it means that the
 			 * hypercall actually returned an error.
 			 */
-			if (map_op->handle == GNTST_general_error) {
+			if (kmap_op->handle == GNTST_general_error) {
 				printk(KERN_WARNING "m2p_remove_override: "
 						"pfn %lx mfn %lx, failed to modify kernel mappings",
 						pfn, mfn);
@@ -918,8 +914,8 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 			mcs = xen_mc_entry(
 					sizeof(struct gnttab_unmap_grant_ref));
 			unmap_op = mcs.args;
-			unmap_op->host_addr = map_op->host_addr;
-			unmap_op->handle = map_op->handle;
+			unmap_op->host_addr = kmap_op->host_addr;
+			unmap_op->handle = kmap_op->handle;
 			unmap_op->dev_bus_addr = 0;
 
 			MULTI_grant_table_op(mcs.mc,
@@ -930,10 +926,9 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 			set_pte_at(&init_mm, address, ptep,
 					pfn_pte(pfn, PAGE_KERNEL));
 			__flush_tlb_single(address);
-			map_op->host_addr = 0;
+			kmap_op->host_addr = 0;
 		}
-	} else
-		set_phys_to_machine(pfn, page->index);
+	}
 
 	/* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
 	 * somewhere in this domain, even before being added to the