From: David Woodhouse <[email protected]> Replace the transient map/unmap of the vmcb12 page on every nested VMRUN (control/save copy-in) and nested VM-exit (state copy-back) with a gfn_to_pfn_cache keyed on vmcb12_gpa. With unmanaged guest memory the transient map is a memremap/memunmap cycle on every L1<->L2 transition; the cache persists the kernel mapping for as long as the gPA and its translation are unchanged.
No pinning is needed, unlike the nVMX APIC pages: SVM never hands an L1-owned physical address to the CPU in vmcb02 (the merged MSRPM and the IOPM are kernel-owned pages), so the vmcb12 page is only ever accessed by KVM itself, under the SRCU read lock, with the usual check/refresh protocol. Dirty marking moves from unconditional-at-unmap to the actual write paths: the SVM_EXIT_ERR reflection in the VMRUN consistency-check failure path, and the copy-back at nested VM-exit. The SMM enter/leave and VMLOAD/VMSAVE emulation paths keep the transient map: they are cold, and VMLOAD/VMSAVE takes an arbitrary gPA from RAX which would thrash a single-slot cache. Signed-off-by: David Woodhouse <[email protected]> Assisted-by: Claude:claude-mythos-5 --- arch/x86/kvm/svm/nested.c | 26 +++++++++++++++++++------- arch/x86/kvm/svm/svm.h | 3 +++ 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index acc423b13445..a8ee0a03d9f7 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1088,12 +1088,13 @@ static int nested_svm_copy_vmcb12_to_cache(struct kvm_vcpu *vcpu, u64 vmcb12_gpa struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb12; int r = 0; + int idx; - CLASS(kvm_vcpu_map_local, m)(vcpu, gpa_to_gfn(vmcb12_gpa)); - if (m.ret) + idx = kvm_gpc_lock_page(&svm->nested.vmcb12_cache, vmcb12_gpa); + if (idx < 0) return -EFAULT; - vmcb12 = m.map.hva; + vmcb12 = svm->nested.vmcb12_cache.khva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); @@ -1104,9 +1105,11 @@ static int nested_svm_copy_vmcb12_to_cache(struct kvm_vcpu *vcpu, u64 vmcb12_gpa vmcb12->control.event_inj = 0; vmcb12->control.event_inj_err = 0; svm_set_gif(svm, false); + kvm_gpc_mark_dirty_in_slot(&svm->nested.vmcb12_cache); r = -EINVAL; } + kvm_gpc_unlock(&svm->nested.vmcb12_cache, idx); return r; } @@ -1251,12 +1254,14 @@ static int nested_svm_vmexit_update_vmcb12(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; struct vmcb *vmcb12; + int idx; - CLASS(kvm_vcpu_map_local, m)(vcpu, gpa_to_gfn(svm->nested.vmcb12_gpa)); - if (m.ret) - return m.ret; + idx = kvm_gpc_lock_page(&svm->nested.vmcb12_cache, + svm->nested.vmcb12_gpa); + if (idx < 0) + return idx; - vmcb12 = m.map.hva; + vmcb12 = svm->nested.vmcb12_cache.khva; vmcb12->save.es = vmcb02->save.es; vmcb12->save.cs = vmcb02->save.cs; @@ -1311,6 +1316,9 @@ static int nested_svm_vmexit_update_vmcb12(struct kvm_vcpu *vcpu) vmcb12->control.exit_int_info_err, KVM_ISA_SVM); + kvm_gpc_mark_dirty_in_slot(&svm->nested.vmcb12_cache); + kvm_gpc_unlock(&svm->nested.vmcb12_cache, idx); + return 0; } @@ -1494,6 +1502,8 @@ int svm_allocate_nested(struct vcpu_svm *svm) if (!svm->nested.msrpm) goto err_free_vmcb02; + kvm_gpc_init(&svm->nested.vmcb12_cache, svm->vcpu.kvm); + svm->nested.initialized = true; return 0; @@ -1513,6 +1523,8 @@ void svm_free_nested(struct vcpu_svm *svm) svm_vcpu_free_msrpm(svm->nested.msrpm); svm->nested.msrpm = NULL; + kvm_gpc_deactivate(&svm->nested.vmcb12_cache); + __free_page(virt_to_page(svm->nested.vmcb02.ptr)); svm->nested.vmcb02.ptr = NULL; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index e958943b8162..cd0755919062 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -218,6 +218,9 @@ struct svm_nested_state { u64 last_vmcb12_gpa; u64 last_bus_lock_rip; + /* Cached mapping of the vmcb12 page, keyed on vmcb12_gpa */ + struct gfn_to_pfn_cache vmcb12_cache; + /* * The MSR permissions map used for vmcb02, which is the merge result * of vmcb01 and vmcb12 -- 2.55.0
