[PATCH 3/5] KVM: x86/hyperv: Ensure vCPU's Hyper-V object is initialized on cross-vCPU accesses

[Sean Christopherson <seanjc@google.com>]

When initializing a vCPU's Hyper-V object, ensure the object is fully
initialized prior to exposing it through the vCPU, and ensure accesses from
other tasks (e.g. other vCPUs) see the fully initialized object if
vcpu->arch.hyperv is non-NULL.

Lack of ordering manifests as a lockdep splat due to attempting to lock a
TLB flush FIFO before the spinlock is initialized.

  INFO: trying to register non-static key.
  The code is fine but needs lockdep annotation, or maybe
  you didn't initialize this object before use?
  turning off the locking correctness validator.
  CPU: 1 PID: 5005 Comm: syz-executor189 Not tainted 6.6.120-smp-DEV #1
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/18/2026
  Call Trace:
   <TASK>
    [<ffffffff810dd10c>] dump_stack_lvl+0xcc/0x130 lib/dump_stack.c:106
    [<ffffffff8192bddd>] assign_lock_key+0x1fd/0x230 kernel/locking/lockdep.c:977
    [<ffffffff8191cb97>] register_lock_class+0x187/0x7a0 kernel/locking/lockdep.c:1291
    [<ffffffff8191e7a9>] __lock_acquire+0x179/0x7650 kernel/locking/lockdep.c:5016
    [<ffffffff8191e28f>] lock_acquire+0x13f/0x3d0 kernel/locking/lockdep.c:5756
    [<ffffffff8101a65b>] __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline]
    [<ffffffff8101a65b>] _raw_spin_lock+0x2b/0x40 kernel/locking/spinlock.c:154
    [<ffffffff81319d44>] spin_lock include/linux/spinlock.h:351 [inline]
    [<ffffffff81319d44>] hv_tlb_flush_enqueue+0xb4/0x270 arch/x86/kvm/hyperv.c:1946
    [<ffffffff813160c6>] kvm_hv_flush_tlb+0xa96/0x1dc0 arch/x86/kvm/hyperv.c:2145
    [<ffffffff8131438b>] kvm_hv_hypercall+0x103b/0x1fe0 arch/x86/kvm/hyperv.c:-1
    [<ffffffff8133bff3>] __vmx_handle_exit arch/x86/kvm/vmx/vmx.c:6624 [inline]
    [<ffffffff8133bff3>] vmx_handle_exit+0x12e3/0x21f0 arch/x86/kvm/vmx/vmx.c:6641
    [<ffffffff81215d11>] vcpu_enter_guest arch/x86/kvm/x86.c:11649 [inline]
    [<ffffffff81215d11>] vcpu_run+0x4d01/0x79c0 arch/x86/kvm/x86.c:11832
    [<ffffffff8120fe39>] kvm_arch_vcpu_ioctl_run+0xb49/0x1c80 arch/x86/kvm/x86.c:12179
    [<ffffffff8119cd60>] kvm_vcpu_ioctl+0xc80/0xff0 virt/kvm/kvm_main.c:6029
    [<ffffffff8226fefd>] vfs_ioctl fs/ioctl.c:52 [inline]
    [<ffffffff8226fefd>] __do_sys_ioctl fs/ioctl.c:872 [inline]
    [<ffffffff8226fefd>] __se_sys_ioctl+0xfd/0x170 fs/ioctl.c:858
    [<ffffffff85ac97d9>] do_syscall_x64 arch/x86/entry/common.c:52 [inline]
    [<ffffffff85ac97d9>] do_syscall_64+0x69/0xb0 arch/x86/entry/common.c:93
   [<ffffffff85c000d0>] entry_SYSCALL_64_after_hwframe+0x68/0xd2
   </TASK>

Use the "safe" variant in all paths that are known to access the Hyper-V
object, as detected by an upcoming lockdep assertion.

Fixes: 0823570f0198 ("KVM: x86: hyper-v: Introduce TLB flush fifo")
Fixes: fc08b628d7c9 ("KVM: x86: hyper-v: Allocate Hyper-V context lazily")
Reported-by: syzbot+5b32c49cd8f005e65654@syzkaller.appspotmail.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/hyperv.c | 23 ++++++++++++++++++-----
 arch/x86/kvm/hyperv.h | 16 ++++++++++++++--
 2 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 3cf8b3cdfc1c..92a715d06d92 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -206,13 +206,19 @@ static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx)
 
 static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vpidx)
 {
-	struct kvm_vcpu *vcpu;
 	struct kvm_vcpu_hv_synic *synic;
+	struct kvm_vcpu_hv *hv_vcpu;
+	struct kvm_vcpu *vcpu;
 
 	vcpu = get_vcpu_by_vpidx(kvm, vpidx);
-	if (!vcpu || !to_hv_vcpu(vcpu))
+	if (!vcpu)
 		return NULL;
-	synic = to_hv_synic(vcpu);
+
+	hv_vcpu = to_hv_vcpu_safe(vcpu);
+	if (!hv_vcpu)
+		return NULL;
+
+	synic = &hv_vcpu->synic;
 	return (synic->active) ? synic : NULL;
 }
 
@@ -972,7 +978,6 @@ int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
 	if (!hv_vcpu)
 		return -ENOMEM;
 
-	vcpu->arch.hyperv = hv_vcpu;
 	hv_vcpu->vcpu = vcpu;
 
 	synic_init(&hv_vcpu->synic);
@@ -988,6 +993,14 @@ int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
 		spin_lock_init(&hv_vcpu->tlb_flush_fifo[i].write_lock);
 	}
 
+	/*
+	 * Ensure the structure is fully initialized before it's visible to
+	 * other tasks, as much of the state can be legally accessed without
+	 * holding vcpu->mutex.
+	 *
+	 * Pairs with the smp_load_acquire() in to_hv_vcpu_safe().
+	 */
+	smp_store_release(&vcpu->arch.hyperv, hv_vcpu);
 	return 0;
 }
 
@@ -2159,7 +2172,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 		bitmap_zero(vcpu_mask, KVM_MAX_VCPUS);
 
 		kvm_for_each_vcpu(i, v, kvm) {
-			hv_v = to_hv_vcpu(v);
+			hv_v = to_hv_vcpu_safe(v);
 
 			/*
 			 * The following check races with nested vCPUs entering/exiting
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 53534e1004bb..ca5366341110 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -61,6 +61,18 @@ static inline struct kvm_hv *to_kvm_hv(struct kvm *kvm)
 	return &kvm->arch.hyperv;
 }
 
+static inline struct kvm_vcpu_hv *to_hv_vcpu_safe(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Ensure the HyperV structure is fully initialized when accessing it
+	 * without holding vcpu->mutex (or some other guarantee that KVM can't
+	 * concurrently instantiate the structure).
+	 *
+	 * Pairs with the smp_store_release() in kvm_hv_vcpu_init().
+	 */
+	return smp_load_acquire(&vcpu->arch.hyperv);
+}
+
 static inline struct kvm_vcpu_hv *to_hv_vcpu(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.hyperv;
@@ -87,7 +99,7 @@ static inline struct kvm_hv_syndbg *to_hv_syndbg(struct kvm_vcpu *vcpu)
 
 static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu_safe(vcpu);
 
 	return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx;
 }
@@ -197,7 +209,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 static inline struct kvm_vcpu_hv_tlb_flush_fifo *kvm_hv_get_tlb_flush_fifo(struct kvm_vcpu *vcpu,
 									   bool is_guest_mode)
 {
-	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu_safe(vcpu);
 	int i = is_guest_mode ? HV_L2_TLB_FLUSH_FIFO :
 				HV_L1_TLB_FLUSH_FIFO;
 
-- 
2.54.0.545.g6539524ca2-goog