From: Rick Edgecombe Date: Tue, 28 Oct 2025 00:28:24 +0000 (-0700) Subject: KVM: TDX: Take MMU lock around tdh_vp_init() X-Git-Tag: v6.19-rc1~103^2~6^2~4 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=9a89894f30d5795c5ac46a9ee9c009d610306025;p=thirdparty%2Flinux.git KVM: TDX: Take MMU lock around tdh_vp_init() Take MMU lock around tdh_vp_init() in KVM_TDX_INIT_VCPU to prevent meeting contention during retries in some no-fail MMU paths. The TDX module takes various try-locks internally, which can cause SEAMCALLs to return an error code when contention is met. Dealing with an error in some of the MMU paths that make SEAMCALLs is not straight forward, so KVM takes steps to ensure that these will meet no contention during a single BUSY error retry. The whole scheme relies on KVM to take appropriate steps to avoid making any SEAMCALLs that could contend while the retry is happening. Unfortunately, there is a case where contention could be met if userspace does something unusual. Specifically, hole punching a gmem fd while initializing the TD vCPU. The impact would be triggering a KVM_BUG_ON(). The resource being contended is called the "TDR resource" in TDX docs parlance. The tdh_vp_init() can take this resource as exclusive if the 'version' passed is 1, which happens to be version the kernel passes. The various MMU operations (tdh_mem_range_block(), tdh_mem_track() and tdh_mem_page_remove()) take it as shared. There isn't a KVM lock that maps conceptually and in a lock order friendly way to the TDR lock. So to minimize infrastructure, just take MMU lock around tdh_vp_init(). This makes the operations we care about mutually exclusive. Since the other operations are under a write mmu_lock, the code could just take the lock for read, however this is weirdly inverted from the actual underlying resource being contended. Since this is covering an edge case that shouldn't be hit in normal usage, be a little less weird and take the mmu_lock for write around the call. Fixes: 02ab57707bdb ("KVM: TDX: Implement hooks to propagate changes of TDP MMU mirror page table") Reported-by: Yan Zhao Suggested-by: Yan Zhao Link: https://patch.msgid.link/20251028002824.1470939-1-rick.p.edgecombe@intel.com Signed-off-by: Rick Edgecombe [sean: tweak comment and capture PUNCH_HOLE interaction] Signed-off-by: Sean Christopherson --- diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 865d18b349889..b5087d40f50b1 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -2969,9 +2969,20 @@ static int tdx_td_vcpu_init(struct kvm_vcpu *vcpu, u64 vcpu_rcx) } } - err = tdh_vp_init(&tdx->vp, vcpu_rcx, vcpu->vcpu_id); - if (TDX_BUG_ON(err, TDH_VP_INIT, vcpu->kvm)) - return -EIO; + /* + * tdh_vp_init() can take an exclusive lock of the TDR resource inside + * the TDX-Module. The TDR resource is also taken as shared in several + * no-fail MMU paths, which could return TDX_OPERAND_BUSY on contention + * (TDX-Module locks are try-lock implementations with no slow path). + * Take mmu_lock for write to reflect the nature of the lock taken by + * the TDX-Module, and to ensure the no-fail MMU paths succeed, e.g. if + * a concurrent PUNCH_HOLE on guest_memfd triggers removal of SPTEs. + */ + scoped_guard(write_lock, &vcpu->kvm->mmu_lock) { + err = tdh_vp_init(&tdx->vp, vcpu_rcx, vcpu->vcpu_id); + if (TDX_BUG_ON(err, TDH_VP_INIT, vcpu->kvm)) + return -EIO; + } vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;