From d0d538b9d1239ed6ed318a2304ba5a763f835089 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Wed, 9 Oct 2013 19:13:19 +0300 Subject: KVM: nVMX: fix shadow on EPT 72f857950f6f19 broke shadow on EPT. This patch reverts it and fixes PAE on nEPT (which reverted commit fixed) in other way. Shadow on EPT is now broken because while L1 builds shadow page table for L2 (which is PAE while L2 is in real mode) it never loads L2's GUEST_PDPTR[0-3]. They do not need to be loaded because without nested virtualization HW does this during guest entry if EPT is disabled, but in our case L0 emulates L2's vmentry while EPT is enables, so we cannot rely on vmcs12->guest_pdptr[0-3] to contain up-to-date values and need to re-read PDPTEs from L2 memory. This is what kvm_set_cr3() is doing, but by clearing cache bits during L2 vmentry we drop values that kvm_set_cr3() read from memory. So why the same code does not work for PAE on nEPT? kvm_set_cr3() reads pdptes into vcpu->arch.walk_mmu->pdptrs[]. walk_mmu points to vcpu->arch.nested_mmu while nested guest is running, but ept_load_pdptrs() uses vcpu->arch.mmu which contain incorrect values. Fix that by using walk_mmu in ept_(load|save)_pdptrs. Signed-off-by: Gleb Natapov Reviewed-by: Paolo Bonzini Tested-by: Paolo Bonzini Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 3b8e7459dd4d..2b2fce1b2009 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3255,25 +3255,29 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) static void ept_load_pdptrs(struct kvm_vcpu *vcpu) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + if (!test_bit(VCPU_EXREG_PDPTR, (unsigned long *)&vcpu->arch.regs_dirty)) return; if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { - vmcs_write64(GUEST_PDPTR0, vcpu->arch.mmu.pdptrs[0]); - vmcs_write64(GUEST_PDPTR1, vcpu->arch.mmu.pdptrs[1]); - vmcs_write64(GUEST_PDPTR2, vcpu->arch.mmu.pdptrs[2]); - vmcs_write64(GUEST_PDPTR3, vcpu->arch.mmu.pdptrs[3]); + vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]); + vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]); + vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]); + vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]); } } static void ept_save_pdptrs(struct kvm_vcpu *vcpu) { + struct kvm_mmu *mmu = vcpu->arch.walk_mmu; + if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { - vcpu->arch.mmu.pdptrs[0] = vmcs_read64(GUEST_PDPTR0); - vcpu->arch.mmu.pdptrs[1] = vmcs_read64(GUEST_PDPTR1); - vcpu->arch.mmu.pdptrs[2] = vmcs_read64(GUEST_PDPTR2); - vcpu->arch.mmu.pdptrs[3] = vmcs_read64(GUEST_PDPTR3); + mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0); + mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1); + mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); + mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); } __set_bit(VCPU_EXREG_PDPTR, @@ -7777,10 +7781,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); - __clear_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_avail); - __clear_bit(VCPU_EXREG_PDPTR, - (unsigned long *)&vcpu->arch.regs_dirty); } kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp); -- cgit v1.2.3 From cfc860253abd73e1681696c08ea268d33285a2c4 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Sat, 21 Sep 2013 09:53:28 +1000 Subject: KVM: PPC: Book3S HV: Fix typo in saving DSCR This fixes a typo in the code that saves the guest DSCR (Data Stream Control Register) into the kvm_vcpu_arch struct on guest exit. The effect of the typo was that the DSCR value was saved in the wrong place, so changes to the DSCR by the guest didn't persist across guest exit and entry, and some host kernel memory got corrupted. Cc: stable@vger.kernel.org [v3.1+] Signed-off-by: Paul Mackerras Acked-by: Alexander Graf Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 294b7af28cdd..c71103b8a748 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1066,7 +1066,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) BEGIN_FTR_SECTION mfspr r8, SPRN_DSCR ld r7, HSTATE_DSCR(r13) - std r8, VCPU_DSCR(r7) + std r8, VCPU_DSCR(r9) mtspr SPRN_DSCR, r7 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) -- cgit v1.2.3 From 40fde70d0df993d1a652d6cc69f8b4e967656170 Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Wed, 7 Aug 2013 15:33:46 +0530 Subject: kvm: ppc: booke: check range page invalidation progress on page setup When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the TLBs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been referencing a page. This patch calls the mmu_notifier_retry() while mapping the guest page to ensure we are not referencing a page when in range invalidation. This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Signed-off-by: Bharat Bhushan Acked-by: Alexander Graf [Backported to 3.12 - Paolo] Reviewed-by: Bharat Bhushan Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/e500_mmu_host.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 1c6a9d729df4..c65593abae8e 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -332,6 +332,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, unsigned long hva; int pfnmap = 0; int tsize = BOOK3E_PAGESZ_4K; + int ret = 0; + unsigned long mmu_seq; + struct kvm *kvm = vcpu_e500->vcpu.kvm; + + /* used to check for invalidations in progress */ + mmu_seq = kvm->mmu_notifier_seq; + smp_rmb(); /* * Translate guest physical to true physical, acquiring @@ -449,6 +456,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); } + spin_lock(&kvm->mmu_lock); + if (mmu_notifier_retry(kvm, mmu_seq)) { + ret = -EAGAIN; + goto out; + } + kvmppc_e500_ref_setup(ref, gtlbe, pfn); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, @@ -457,10 +470,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, /* Clear i-cache for new pages */ kvmppc_mmu_flush_icache(pfn); +out: + spin_unlock(&kvm->mmu_lock); + /* Drop refcount on page, so that mmu notifiers can clear it */ kvm_release_pfn_clean(pfn); - return 0; + return ret; } /* XXX only map the one-one case, for now use TLB0 */ -- cgit v1.2.3