From: Sean Christopherson seanjc@google.com
[ Upstream commit cf9f4c0eb1699d306e348b1fd0225af7b2c282d3 ]
Refresh the MMU's snapshot of the vCPU's CR0.WP prior to checking for permission faults when emulating a guest memory access and CR0.WP may be guest owned. If the guest toggles only CR0.WP and triggers emulation of a supervisor write, e.g. when KVM is emulating UMIP, KVM may consume a stale CR0.WP, i.e. use stale protection bits metadata.
Note, KVM passes through CR0.WP if and only if EPT is enabled as CR0.WP is part of the MMU role for legacy shadow paging, and SVM (NPT) doesn't support per-bit interception controls for CR0. Don't bother checking for EPT vs. NPT as the "old == new" check will always be true under NPT, i.e. the only cost is the read of vcpu->arch.cr4 (SVM unconditionally grabs CR0 from the VMCB on VM-Exit).
Reported-by: Mathias Krause minipli@grsecurity.net Link: https://lkml.kernel.org/r/677169b4-051f-fcae-756b-9a3e1bb9f8fe%40grsecurity.... Fixes: fb509f76acc8 ("KVM: VMX: Make CR0.WP a guest owned bit") Tested-by: Mathias Krause minipli@grsecurity.net Link: https://lore.kernel.org/r/20230405002608.418442-1-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Mathias Krause minipli@grsecurity.net # backport to v5.15.x --- - the MMU role wasn't folded into the CPU role yet in this kernel version and the "not_smap" handling was done slightly different, however, independent of the permission bitmap handling, so refreshing the bitmap prior to determining the fault state is still sufficient
arch/x86/kvm/mmu.h | 26 +++++++++++++++++++++++++- arch/x86/kvm/mmu/mmu.c | 15 +++++++++++++++ 2 files changed, 40 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 03a9e37e446a..a3c0dc07fc96 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -76,6 +76,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); +void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu);
int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); @@ -176,6 +178,24 @@ static inline bool is_writable_pte(unsigned long pte) return pte & PT_WRITABLE_MASK; }
+static inline void kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + /* + * When EPT is enabled, KVM may passthrough CR0.WP to the guest, i.e. + * @mmu's snapshot of CR0.WP and thus all related paging metadata may + * be stale. Refresh CR0.WP and the metadata on-demand when checking + * for permission faults. Exempt nested MMUs, i.e. MMUs for shadowing + * nEPT and nNPT, as CR0.WP is ignored in both cases. Note, KVM does + * need to refresh nested_mmu, a.k.a. the walker used to translate L2 + * GVAs to GPAs, as that "MMU" needs to honor L2's CR0.WP. + */ + if (!tdp_enabled || mmu == &vcpu->arch.guest_mmu) + return; + + __kvm_mmu_refresh_passthrough_bits(vcpu, mmu); +} + /* * Check if a given access (described through the I/D, W/R and U/S bits of a * page fault error code pfec) causes a permission fault with the given PTE @@ -207,8 +227,12 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long smap = (cpl - 3) & (rflags & X86_EFLAGS_AC); int index = (pfec >> 1) + (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1)); - bool fault = (mmu->permissions[index] >> pte_access) & 1; u32 errcode = PFERR_PRESENT_MASK; + bool fault; + + kvm_mmu_refresh_passthrough_bits(vcpu, mmu); + + fault = (mmu->permissions[index] >> pte_access) & 1;
WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK)); if (unlikely(mmu->pkru_mask)) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7c3b809f24b3..0e50b4dd01e5 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4713,6 +4713,21 @@ static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu, return role; }
+void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + const bool cr0_wp = !!kvm_read_cr0_bits(vcpu, X86_CR0_WP); + + BUILD_BUG_ON((KVM_MMU_CR0_ROLE_BITS & KVM_POSSIBLE_CR0_GUEST_BITS) != X86_CR0_WP); + BUILD_BUG_ON((KVM_MMU_CR4_ROLE_BITS & KVM_POSSIBLE_CR4_GUEST_BITS)); + + if (is_cr0_wp(mmu) == cr0_wp) + return; + + mmu->mmu_role.base.cr0_wp = cr0_wp; + reset_guest_paging_metadata(vcpu, mmu); +} + static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) { /* tdp_root_level is architecture forced level, use it if nonzero */