KVM: x86/mmu: add support for GMET to NPT page table walks

GMET allows page table entries to be created with U=0 in NPT.
However, when GMET=1 U=0 only affects execution, not reads or
writes.  Ignore user faults on non-fetch accesses for NPT GMET.

Tested-by: David Riley <d.riley@proxmox.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7dde4ca87752224517b3a92caf613dfdd6e7d463..1da3d5c59e158f94051c4a55d8818a0fb6f64476 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -370,6 +370,8 @@ union kvm_mmu_page_role {
                 * cr4_smep is also set for EPT MBEC.  Because it affects
                 * which pages are considered non-present (bit 10 additionally
                 * must be zero if MBEC is on) it has to be in the base role.
+                * It also has to be in the base role for AMD GMET because
+                * kernel-executable pages need to have U=0 with GMET enabled.
                 */
                unsigned cr4_smep:1;
 

diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 1b354e1f2d812f34286446f33be3df6ba5f5dc47..ddf4e467c071ebc21d07613eda1f2ef6a91d16a6 100644 (file)
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -97,7 +97,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits);
 
 void kvm_init_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr4,
-                            u64 efer, gpa_t nested_cr3);
+                            u64 efer, gpa_t nested_cr3, u64 misc_ctl);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
                             int huge_page_level, bool accessed_dirty,
                             bool mbec, gpa_t new_eptp);

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b8ff834abf8861055969c71e86e2c3ff2df74150..d6c59579754248a2864ffe9df7dd9b3fcee63874 100644 (file)
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -55,6 +55,7 @@
 #include <asm/io.h>
 #include <asm/set_memory.h>
 #include <asm/spec-ctrl.h>
+#include <asm/svm.h>
 #include <asm/vmx.h>
 
 #include "trace.h"
@@ -5572,7 +5573,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_mmu *context, bool execonly)
         (14 & (access) ? 1 << 14 : 0) | \
         (15 & (access) ? 1 << 15 : 0))
 
-static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept)
+static void update_permission_bitmask(struct kvm_mmu *mmu, bool tdp, bool ept)
 {
        unsigned index;
 
@@ -5633,7 +5634,12 @@ static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept)
                        /* Faults from kernel mode accesses to user pages */
                        u16 kf = (pfec & PFERR_USER_MASK) ? 0 : u;
 
-                       uf = (pfec & PFERR_USER_MASK) ? (u16)~u : 0;
+                       /*
+                        * For NPT GMET, U=0 does not affect reads and writes.  Fetches
+                        * are handled below via cr4_smep.
+                        */
+                       if (!(tdp && cr4_smep))
+                               uf = (pfec & PFERR_USER_MASK) ? (u16)~u : 0;
 
                        if (efer_nx)
                                ff |= (pfec & PFERR_FETCH_MASK) ? (u16)~x : 0;
@@ -5744,7 +5750,7 @@ static void reset_guest_paging_metadata(struct kvm_vcpu *vcpu,
                return;
 
        reset_guest_rsvds_bits_mask(vcpu, mmu);
-       update_permission_bitmask(mmu, false);
+       update_permission_bitmask(mmu, mmu == &vcpu->arch.guest_mmu, false);
        update_pkru_bitmask(mmu);
 }
 
@@ -5940,7 +5946,7 @@ static void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu,
 }
 
 void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr4,
-                            u64 efer, gpa_t nested_cr3)
+                            u64 efer, gpa_t nested_cr3, u64 misc_ctl)
 {
        struct kvm_mmu *context = &vcpu->arch.guest_mmu;
        struct kvm_mmu_role_regs regs = {
@@ -5953,7 +5959,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr4,
 
        /* NPT requires CR0.PG=1. */
        WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode);
-       cpu_role.base.cr4_smep = false;
+       cpu_role.base.cr4_smep = (misc_ctl & SVM_MISC_ENABLE_GMET) != 0;
 
        root_role = cpu_role.base;
        root_role.level = kvm_mmu_get_tdp_level(vcpu);
@@ -6011,7 +6017,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
                context->gva_to_gpa = ept_gva_to_gpa;
                context->sync_spte = ept_sync_spte;
 
-               update_permission_bitmask(context, true);
+               update_permission_bitmask(context, true, true);
                context->pkru_mask = 0;
                reset_rsvds_bits_mask_ept(vcpu, context, execonly, huge_page_level);
                reset_ept_shadow_zero_bits_mask(context, execonly);

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index a1cffd27400052b552b36046d3884a1dd81c4716..7adfa7da210def795afa46d0d7a8e9bc66d27542 100644 (file)
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -95,7 +95,8 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
         */
        kvm_init_shadow_npt_mmu(vcpu, svm->vmcb01.ptr->save.cr4,
                                svm->vmcb01.ptr->save.efer,
-                               svm->nested.ctl.nested_cr3);
+                               svm->nested.ctl.nested_cr3,
+                               svm->nested.ctl.misc_ctl);
        vcpu->arch.mmu->get_guest_pgd     = nested_svm_get_tdp_cr3;
        vcpu->arch.mmu->get_pdptr         = nested_svm_get_tdp_pdptr;
        vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit;
@@ -2076,12 +2077,15 @@ static gpa_t svm_translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa,
                                      struct x86_exception *exception,
                                      u64 pte_access)
 {
+       struct vcpu_svm *svm = to_svm(vcpu);
        struct kvm_mmu *mmu = vcpu->arch.mmu;
 
        BUG_ON(!mmu_is_nested(vcpu));
 
-       /* NPT walks are always user-walks */
-       access |= PFERR_USER_MASK;
+       /* Non-GMET walks are always user-walks */
+       if (!(svm->nested.ctl.misc_ctl & SVM_MISC_ENABLE_GMET))
+               access |= PFERR_USER_MASK;
+
        return mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception);
 }