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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Move the arch-specific code into arch/arm64/kvm

   - Start the post-32bit cleanup

   - Cherry-pick a few non-invasive pre-NV patches

  x86:
   - Rework of TLB flushing

   - Rework of event injection, especially with respect to nested
     virtualization

   - Nested AMD event injection facelift, building on the rework of
     generic code and fixing a lot of corner cases

   - Nested AMD live migration support

   - Optimization for TSC deadline MSR writes and IPIs

   - Various cleanups

   - Asynchronous page fault cleanups (from tglx, common topic branch
     with tip tree)

   - Interrupt-based delivery of asynchronous "page ready" events (host
     side)

   - Hyper-V MSRs and hypercalls for guest debugging

   - VMX preemption timer fixes

  s390:
   - Cleanups

  Generic:
   - switch vCPU thread wakeup from swait to rcuwait

  The other architectures, and the guest side of the asynchronous page
  fault work, will come next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (256 commits)
  KVM: selftests: fix rdtsc() for vmx_tsc_adjust_test
  KVM: check userspace_addr for all memslots
  KVM: selftests: update hyperv_cpuid with SynDBG tests
  x86/kvm/hyper-v: Add support for synthetic debugger via hypercalls
  x86/kvm/hyper-v: enable hypercalls regardless of hypercall page
  x86/kvm/hyper-v: Add support for synthetic debugger interface
  x86/hyper-v: Add synthetic debugger definitions
  KVM: selftests: VMX preemption timer migration test
  KVM: nVMX: Fix VMX preemption timer migration
  x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit
  KVM: x86/pmu: Support full width counting
  KVM: x86/pmu: Tweak kvm_pmu_get_msr to pass 'struct msr_data' in
  KVM: x86: announce KVM_FEATURE_ASYNC_PF_INT
  KVM: x86: acknowledgment mechanism for async pf page ready notifications
  KVM: x86: interrupt based APF 'page ready' event delivery
  KVM: introduce kvm_read_guest_offset_cached()
  KVM: rename kvm_arch_can_inject_async_page_present() to kvm_arch_can_dequeue_async_page_present()
  KVM: x86: extend struct kvm_vcpu_pv_apf_data with token info
  Revert "KVM: async_pf: Fix #DF due to inject "Page not Present" and "Page Ready" exceptions simultaneously"
  KVM: VMX: Replace zero-length array with flexible-array
  ...

1 files changed, 61 insertions, 36 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 731c1e517716..7fa1e38e1659 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -349,7 +349,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
 	vcpu->pid = NULL;
-	init_swait_queue_head(&vcpu->wq);
+	rcuwait_init(&vcpu->wait);
 	kvm_async_pf_vcpu_init(vcpu);
 
 	vcpu->pre_pcpu = -1;
@@ -718,6 +718,8 @@ static struct kvm *kvm_create_vm(unsigned long type)
 			goto out_err_no_arch_destroy_vm;
 	}
 
+	kvm->max_halt_poll_ns = halt_poll_ns;
+
 	r = kvm_arch_init_vm(kvm, type);
 	if (r)
 		goto out_err_no_arch_destroy_vm;
@@ -1223,10 +1225,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
 		return -EINVAL;
 	/* We can read the guest memory with __xxx_user() later on. */
-	if ((id < KVM_USER_MEM_SLOTS) &&
-	    ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
+	if ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
 	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
-			mem->memory_size)))
+			mem->memory_size))
 		return -EINVAL;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
 		return -EINVAL;
@@ -1610,16 +1611,13 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn
 {
 	return __gfn_to_memslot(kvm_vcpu_memslots(vcpu), gfn);
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_memslot);
 
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);
 
-	if (!memslot || memslot->id >= KVM_USER_MEM_SLOTS ||
-	      memslot->flags & KVM_MEMSLOT_INVALID)
-		return false;
-
-	return true;
+	return kvm_is_visible_memslot(memslot);
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
@@ -2511,13 +2509,15 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest_cached);
 
-int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
-			   void *data, unsigned long len)
+int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+				 void *data, unsigned int offset,
+				 unsigned long len)
 {
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
+	gpa_t gpa = ghc->gpa + offset;
 
-	BUG_ON(len > ghc->len);
+	BUG_ON(len + offset > ghc->len);
 
 	if (slots->generation != ghc->generation) {
 		if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
@@ -2528,14 +2528,21 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 		return -EFAULT;
 
 	if (unlikely(!ghc->memslot))
-		return kvm_read_guest(kvm, ghc->gpa, data, len);
+		return kvm_read_guest(kvm, gpa, data, len);
 
-	r = __copy_from_user(data, (void __user *)ghc->hva, len);
+	r = __copy_from_user(data, (void __user *)ghc->hva + offset, len);
 	if (r)
 		return -EFAULT;
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(kvm_read_guest_offset_cached);
+
+int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			  void *data, unsigned long len)
+{
+	return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len);
+}
 EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
 
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
@@ -2673,19 +2680,27 @@ out:
 	return ret;
 }
 
+static inline void
+update_halt_poll_stats(struct kvm_vcpu *vcpu, u64 poll_ns, bool waited)
+{
+	if (waited)
+		vcpu->stat.halt_poll_fail_ns += poll_ns;
+	else
+		vcpu->stat.halt_poll_success_ns += poll_ns;
+}
+
 /*
  * The vCPU has executed a HLT instruction with in-kernel mode enabled.
  */
 void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 {
-	ktime_t start, cur;
-	DECLARE_SWAITQUEUE(wait);
+	ktime_t start, cur, poll_end;
 	bool waited = false;
 	u64 block_ns;
 
 	kvm_arch_vcpu_blocking(vcpu);
 
-	start = cur = ktime_get();
+	start = cur = poll_end = ktime_get();
 	if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) {
 		ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
 
@@ -2701,12 +2716,13 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 					++vcpu->stat.halt_poll_invalid;
 				goto out;
 			}
-			cur = ktime_get();
+			poll_end = cur = ktime_get();
 		} while (single_task_running() && ktime_before(cur, stop));
 	}
 
+	prepare_to_rcuwait(&vcpu->wait);
 	for (;;) {
-		prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
@@ -2714,25 +2730,28 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		waited = true;
 		schedule();
 	}
-
-	finish_swait(&vcpu->wq, &wait);
+	finish_rcuwait(&vcpu->wait);
 	cur = ktime_get();
 out:
 	kvm_arch_vcpu_unblocking(vcpu);
 	block_ns = ktime_to_ns(cur) - ktime_to_ns(start);
 
+	update_halt_poll_stats(
+		vcpu, ktime_to_ns(ktime_sub(poll_end, start)), waited);
+
 	if (!kvm_arch_no_poll(vcpu)) {
 		if (!vcpu_valid_wakeup(vcpu)) {
 			shrink_halt_poll_ns(vcpu);
-		} else if (halt_poll_ns) {
+		} else if (vcpu->kvm->max_halt_poll_ns) {
 			if (block_ns <= vcpu->halt_poll_ns)
 				;
 			/* we had a long block, shrink polling */
-			else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns)
+			else if (vcpu->halt_poll_ns &&
+					block_ns > vcpu->kvm->max_halt_poll_ns)
 				shrink_halt_poll_ns(vcpu);
 			/* we had a short halt and our poll time is too small */
-			else if (vcpu->halt_poll_ns < halt_poll_ns &&
-				block_ns < halt_poll_ns)
+			else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns &&
+					block_ns < vcpu->kvm->max_halt_poll_ns)
 				grow_halt_poll_ns(vcpu);
 		} else {
 			vcpu->halt_poll_ns = 0;
@@ -2746,11 +2765,10 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_block);
 
 bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
 {
-	struct swait_queue_head *wqp;
+	struct rcuwait *waitp;
 
-	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (swq_has_sleeper(wqp)) {
-		swake_up_one(wqp);
+	waitp = kvm_arch_vcpu_get_wait(vcpu);
+	if (rcuwait_wake_up(waitp)) {
 		WRITE_ONCE(vcpu->ready, true);
 		++vcpu->stat.halt_wakeup;
 		return true;
@@ -2807,7 +2825,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
  *
  *  (a) VCPU which has not done pl-exit or cpu relax intercepted recently
  *  (preempted lock holder), indicated by @in_spin_loop.
- *  Set at the beiginning and cleared at the end of interception/PLE handler.
+ *  Set at the beginning and cleared at the end of interception/PLE handler.
  *
  *  (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get
  *  chance last time (mostly it has become eligible now since we have probably
@@ -2892,7 +2910,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 				continue;
 			if (vcpu == me)
 				continue;
-			if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu))
+			if (rcuwait_active(&vcpu->wait) &&
+			    !vcpu_dy_runnable(vcpu))
 				continue;
 			if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
 				!kvm_arch_vcpu_in_kernel(vcpu))
@@ -3039,8 +3058,6 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	if (r)
 		goto vcpu_free_run_page;
 
-	kvm_create_vcpu_debugfs(vcpu);
-
 	mutex_lock(&kvm->lock);
 	if (kvm_get_vcpu_by_id(kvm, id)) {
 		r = -EEXIST;
@@ -3069,11 +3086,11 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 
 	mutex_unlock(&kvm->lock);
 	kvm_arch_vcpu_postcreate(vcpu);
+	kvm_create_vcpu_debugfs(vcpu);
 	return r;
 
 unlock_vcpu_destroy:
 	mutex_unlock(&kvm->lock);
-	debugfs_remove_recursive(vcpu->debugfs_dentry);
 	kvm_arch_vcpu_destroy(vcpu);
 vcpu_free_run_page:
 	free_page((unsigned long)vcpu->run);
@@ -3143,7 +3160,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 				synchronize_rcu();
 			put_pid(oldpid);
 		}
-		r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
+		r = kvm_arch_vcpu_ioctl_run(vcpu);
 		trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
 		break;
 	}
@@ -3168,7 +3185,6 @@ out_free1:
 	case KVM_SET_REGS: {
 		struct kvm_regs *kvm_regs;
 
-		r = -ENOMEM;
 		kvm_regs = memdup_user(argp, sizeof(*kvm_regs));
 		if (IS_ERR(kvm_regs)) {
 			r = PTR_ERR(kvm_regs);
@@ -3524,6 +3540,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_IOEVENTFD_ANY_LENGTH:
 	case KVM_CAP_CHECK_EXTENSION_VM:
 	case KVM_CAP_ENABLE_CAP_VM:
+	case KVM_CAP_HALT_POLL:
 		return 1;
 #ifdef CONFIG_KVM_MMIO
 	case KVM_CAP_COALESCED_MMIO:
@@ -3574,6 +3591,13 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 		return 0;
 	}
 #endif
+	case KVM_CAP_HALT_POLL: {
+		if (cap->flags || cap->args[0] != (unsigned int)cap->args[0])
+			return -EINVAL;
+
+		kvm->max_halt_poll_ns = cap->args[0];
+		return 0;
+	}
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);
 	}
@@ -4647,6 +4671,7 @@ struct kvm_vcpu *kvm_get_running_vcpu(void)
 
 	return vcpu;
 }
+EXPORT_SYMBOL_GPL(kvm_get_running_vcpu);
 
 /**
  * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus.