Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini: "One of the largest releases for KVM... Hardly any generic changes, but lots of architecture-specific updates. ARM: - VHE support so that we can run the kernel at EL2 on ARMv8.1 systems - PMU support for guests - 32bit world switch rewritten in C - various optimizations to the vgic save/restore code. PPC: - enabled KVM-VFIO integration ("VFIO device") - optimizations to speed up IPIs between vcpus - in-kernel handling of IOMMU hypercalls - support for dynamic DMA windows (DDW). s390: - provide the floating point registers via sync regs; - separated instruction vs. data accesses - dirty log improvements for huge guests - bugfixes and documentation improvements. x86: - Hyper-V VMBus hypercall userspace exit - alternative implementation of lowest-priority interrupts using vector hashing (for better VT-d posted interrupt support) - fixed guest debugging with nested virtualizations - improved interrupt tracking in the in-kernel IOAPIC - generic infrastructure for tracking writes to guest memory - currently its only use is to speedup the legacy shadow paging (pre-EPT) case, but in the future it will be used for virtual GPUs as well - much cleanup (LAPIC, kvmclock, MMU, PIT), including ubsan fixes" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (217 commits) KVM: x86: remove eager_fpu field of struct kvm_vcpu_arch KVM: x86: disable MPX if host did not enable MPX XSAVE features arm64: KVM: vgic-v3: Only wipe LRs on vcpu exit arm64: KVM: vgic-v3: Reset LRs at boot time arm64: KVM: vgic-v3: Do not save an LR known to be empty arm64: KVM: vgic-v3: Save maintenance interrupt state only if required arm64: KVM: vgic-v3: Avoid accessing ICH registers KVM: arm/arm64: vgic-v2: Make GICD_SGIR quicker to hit KVM: arm/arm64: vgic-v2: Only wipe LRs on vcpu exit KVM: arm/arm64: vgic-v2: Reset LRs at boot time KVM: arm/arm64: vgic-v2: Do not save an LR known to be empty KVM: arm/arm64: vgic-v2: Move GICH_ELRSR saving to its own function KVM: arm/arm64: vgic-v2: Save maintenance interrupt state only if required KVM: arm/arm64: vgic-v2: Avoid accessing GICH registers KVM: s390: allocate only one DMA page per VM KVM: s390: enable STFLE interpretation only if enabled for the guest KVM: s390: wake up when the VCPU cpu timer expires KVM: s390: step the VCPU timer while in enabled wait KVM: s390: protect VCPU cpu timer with a seqcount KVM: s390: step VCPU cpu timer during kvm_run ioctl ...
2016-03-16 09:55:35 -07:00
parent 047486d8e7 f958ee745f
commit 10dc374766
142 changed files with 6754 additions and 2936 deletions
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/kvm.h>
 #include <trace/events/kvm.h>
+#include <kvm/arm_pmu.h>

 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -265,6 +266,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_vgic_vcpu_destroy(vcpu);
+	kvm_pmu_vcpu_destroy(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }

@@ -320,6 +322,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	vcpu->cpu = -1;

 	kvm_arm_set_running_vcpu(NULL);
+	kvm_timer_vcpu_put(vcpu);
 }

 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
@@ -577,6 +580,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * non-preemptible context.
 		 */
 		preempt_disable();
+		kvm_pmu_flush_hwstate(vcpu);
 		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);

@@ -593,6 +597,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
 			vcpu->arch.power_off || vcpu->arch.pause) {
 			local_irq_enable();
+			kvm_pmu_sync_hwstate(vcpu);
 			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			preempt_enable();
@@ -642,10 +647,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));

 		/*
-		 * We must sync the timer state before the vgic state so that
-		 * the vgic can properly sample the updated state of the
+		 * We must sync the PMU and timer state before the vgic state so
+		 * that the vgic can properly sample the updated state of the
 		 * interrupt line.
 		 */
+		kvm_pmu_sync_hwstate(vcpu);
 		kvm_timer_sync_hwstate(vcpu);

 		kvm_vgic_sync_hwstate(vcpu);
@@ -823,11 +829,54 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	return 0;
 }

+static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
 	struct kvm_vcpu *vcpu = filp->private_data;
 	void __user *argp = (void __user *)arg;
+	struct kvm_device_attr attr;

 	switch (ioctl) {
 	case KVM_ARM_VCPU_INIT: {
@@ -870,6 +919,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			return -E2BIG;
 		return kvm_arm_copy_reg_indices(vcpu, user_list->reg);
 	}
+	case KVM_SET_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_set_attr(vcpu, &attr);
+	}
+	case KVM_GET_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_get_attr(vcpu, &attr);
+	}
+	case KVM_HAS_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_has_attr(vcpu, &attr);
+	}
 	default:
 		return -EINVAL;
 	}
@@ -967,6 +1031,11 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 }

+static void cpu_init_stage2(void *dummy)
+{
+	__cpu_init_stage2();
+}
+
 static void cpu_init_hyp_mode(void *dummy)
 {
 	phys_addr_t boot_pgd_ptr;
@@ -985,6 +1054,7 @@ static void cpu_init_hyp_mode(void *dummy)
 	vector_ptr = (unsigned long)__kvm_hyp_vector;

 	__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
+	__cpu_init_stage2();

 	kvm_arm_init_debug();
 }
@@ -1035,6 +1105,82 @@ static inline void hyp_cpu_pm_init(void)
 }
 #endif

+static void teardown_common_resources(void)
+{
+	free_percpu(kvm_host_cpu_state);
+}
+
+static int init_common_resources(void)
+{
+	kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
+	if (!kvm_host_cpu_state) {
+		kvm_err("Cannot allocate host CPU state\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int init_subsystems(void)
+{
+	int err;
+
+	/*
+	 * Init HYP view of VGIC
+	 */
+	err = kvm_vgic_hyp_init();
+	switch (err) {
+	case 0:
+		vgic_present = true;
+		break;
+	case -ENODEV:
+	case -ENXIO:
+		vgic_present = false;
+		break;
+	default:
+		return err;
+	}
+
+	/*
+	 * Init HYP architected timer support
+	 */
+	err = kvm_timer_hyp_init();
+	if (err)
+		return err;
+
+	kvm_perf_init();
+	kvm_coproc_table_init();
+
+	return 0;
+}
+
+static void teardown_hyp_mode(void)
+{
+	int cpu;
+
+	if (is_kernel_in_hyp_mode())
+		return;
+
+	free_hyp_pgds();
+	for_each_possible_cpu(cpu)
+		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+}
+
+static int init_vhe_mode(void)
+{
+	/*
+	 * Execute the init code on each CPU.
+	 */
+	on_each_cpu(cpu_init_stage2, NULL, 1);
+
+	/* set size of VMID supported by CPU */
+	kvm_vmid_bits = kvm_get_vmid_bits();
+	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+
+	kvm_info("VHE mode initialized successfully\n");
+	return 0;
+}
+
 /**
 * Inits Hyp-mode on all online CPUs
 */
@@ -1065,7 +1211,7 @@ static int init_hyp_mode(void)
 		stack_page = __get_free_page(GFP_KERNEL);
 		if (!stack_page) {
 			err = -ENOMEM;
-			goto out_free_stack_pages;
+			goto out_err;
 		}

 		per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
@@ -1074,16 +1220,16 @@ static int init_hyp_mode(void)
 	/*
 	 * Map the Hyp-code called directly from the host
 	 */
-	err = create_hyp_mappings(__kvm_hyp_code_start, __kvm_hyp_code_end);
+	err = create_hyp_mappings(__hyp_text_start, __hyp_text_end);
 	if (err) {
 		kvm_err("Cannot map world-switch code\n");
-		goto out_free_mappings;
+		goto out_err;
 	}

 	err = create_hyp_mappings(__start_rodata, __end_rodata);
 	if (err) {
 		kvm_err("Cannot map rodata section\n");
-		goto out_free_mappings;
+		goto out_err;
 	}

 	/*
@@ -1095,20 +1241,10 @@ static int init_hyp_mode(void)

 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
-			goto out_free_mappings;
+			goto out_err;
 		}
 	}

-	/*
-	 * Map the host CPU structures
-	 */
-	kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
-	if (!kvm_host_cpu_state) {
-		err = -ENOMEM;
-		kvm_err("Cannot allocate host CPU state\n");
-		goto out_free_mappings;
-	}
-
 	for_each_possible_cpu(cpu) {
 		kvm_cpu_context_t *cpu_ctxt;

@@ -1117,7 +1253,7 @@ static int init_hyp_mode(void)

 		if (err) {
 			kvm_err("Cannot map host CPU state: %d\n", err);
-			goto out_free_context;
+			goto out_err;
 		}
 	}

@@ -1126,34 +1262,22 @@ static int init_hyp_mode(void)
 	 */
 	on_each_cpu(cpu_init_hyp_mode, NULL, 1);

-	/*
-	 * Init HYP view of VGIC
-	 */
-	err = kvm_vgic_hyp_init();
-	switch (err) {
-	case 0:
-		vgic_present = true;
-		break;
-	case -ENODEV:
-	case -ENXIO:
-		vgic_present = false;
-		break;
-	default:
-		goto out_free_context;
-	}
-
-	/*
-	 * Init HYP architected timer support
-	 */
-	err = kvm_timer_hyp_init();
-	if (err)
-		goto out_free_context;
-
 #ifndef CONFIG_HOTPLUG_CPU
 	free_boot_hyp_pgd();
 #endif

-	kvm_perf_init();
+	cpu_notifier_register_begin();
+
+	err = __register_cpu_notifier(&hyp_init_cpu_nb);
+
+	cpu_notifier_register_done();
+
+	if (err) {
+		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
+		goto out_err;
+	}
+
+	hyp_cpu_pm_init();

 	/* set size of VMID supported by CPU */
 	kvm_vmid_bits = kvm_get_vmid_bits();
@@ -1162,14 +1286,9 @@ static int init_hyp_mode(void)
 	kvm_info("Hyp mode initialized successfully\n");

 	return 0;
-out_free_context:
-	free_percpu(kvm_host_cpu_state);
-out_free_mappings:
-	free_hyp_pgds();
-out_free_stack_pages:
-	for_each_possible_cpu(cpu)
-		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+
 out_err:
+	teardown_hyp_mode();
 	kvm_err("error initializing Hyp mode: %d\n", err);
 	return err;
 }
@@ -1213,26 +1332,27 @@ int kvm_arch_init(void *opaque)
 		}
 	}

-	cpu_notifier_register_begin();
+	err = init_common_resources();
+	if (err)
+		return err;

-	err = init_hyp_mode();
+	if (is_kernel_in_hyp_mode())
+		err = init_vhe_mode();
+	else
+		err = init_hyp_mode();
 	if (err)
 		goto out_err;

-	err = __register_cpu_notifier(&hyp_init_cpu_nb);
-	if (err) {
-		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
-		goto out_err;
-	}
+	err = init_subsystems();
+	if (err)
+		goto out_hyp;

-	cpu_notifier_register_done();
-
-	hyp_cpu_pm_init();
-
-	kvm_coproc_table_init();
 	return 0;
+
+out_hyp:
+	teardown_hyp_mode();
 out_err:
-	cpu_notifier_register_done();
+	teardown_common_resources();
 	return err;
 }