Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Paolo Bonzini:
 "(Relatively) a lot of reverts, mostly.

  Bugs have trickled in for a new feature in 4.2 (MTRR support in
  guests) so I'm reverting it all; let's not make this -rc period busier
  for KVM than it's been so far.  This covers the four reverts from me.

  The fifth patch is being reverted because Radim found a bug in the
  implementation of stable scheduler clock, *but* also managed to
  implement the feature entirely without hypervisor support.  So instead
  of fixing the hypervisor side we can remove it completely; 4.4 will
  get the new implementation"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  Use WARN_ON_ONCE for missing X86_FEATURE_NRIPS
  Update KVM homepage Url
  Revert "KVM: SVM: use NPT page attributes"
  Revert "KVM: svm: handle KVM_X86_QUIRK_CD_NW_CLEARED in svm_get_mt_mask"
  Revert "KVM: SVM: Sync g_pat with guest-written PAT value"
  Revert "KVM: x86: apply guest MTRR virtualization on host reserved pages"
  Revert "KVM: x86: zero kvmclock_offset when vcpu0 initializes kvmclock system MSR"

4 files changed, 22 insertions, 119 deletions

diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 655e07a48f6c..67f08230103a 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -41,6 +41,7 @@ struct pvclock_wall_clock {
 
 #define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
 #define PVCLOCK_GUEST_STOPPED	(1 << 1)
+/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */
 #define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 94b7d15db3fc..2f9ed1ff0632 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -514,7 +514,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (svm->vmcb->control.next_rip != 0) {
-		WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
+		WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
 	}
 
@@ -866,64 +866,6 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
 	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
-#define MTRR_TYPE_UC_MINUS	7
-#define MTRR2PROTVAL_INVALID 0xff
-
-static u8 mtrr2protval[8];
-
-static u8 fallback_mtrr_type(int mtrr)
-{
-	/*
-	 * WT and WP aren't always available in the host PAT.  Treat
-	 * them as UC and UC- respectively.  Everything else should be
-	 * there.
-	 */
-	switch (mtrr)
-	{
-	case MTRR_TYPE_WRTHROUGH:
-		return MTRR_TYPE_UNCACHABLE;
-	case MTRR_TYPE_WRPROT:
-		return MTRR_TYPE_UC_MINUS;
-	default:
-		BUG();
-	}
-}
-
-static void build_mtrr2protval(void)
-{
-	int i;
-	u64 pat;
-
-	for (i = 0; i < 8; i++)
-		mtrr2protval[i] = MTRR2PROTVAL_INVALID;
-
-	/* Ignore the invalid MTRR types.  */
-	mtrr2protval[2] = 0;
-	mtrr2protval[3] = 0;
-
-	/*
-	 * Use host PAT value to figure out the mapping from guest MTRR
-	 * values to nested page table PAT/PCD/PWT values.  We do not
-	 * want to change the host PAT value every time we enter the
-	 * guest.
-	 */
-	rdmsrl(MSR_IA32_CR_PAT, pat);
-	for (i = 0; i < 8; i++) {
-		u8 mtrr = pat >> (8 * i);
-
-		if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
-			mtrr2protval[mtrr] = __cm_idx2pte(i);
-	}
-
-	for (i = 0; i < 8; i++) {
-		if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
-			u8 fallback = fallback_mtrr_type(i);
-			mtrr2protval[i] = mtrr2protval[fallback];
-			BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
-		}
-	}
-}
-
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -990,7 +932,6 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
-	build_mtrr2protval();
 	return 0;
 
 err:
@@ -1145,43 +1086,6 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 	return target_tsc - tsc;
 }
 
-static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
-{
-	struct kvm_vcpu *vcpu = &svm->vcpu;
-
-	/* Unlike Intel, AMD takes the guest's CR0.CD into account.
-	 *
-	 * AMD does not have IPAT.  To emulate it for the case of guests
-	 * with no assigned devices, just set everything to WB.  If guests
-	 * have assigned devices, however, we cannot force WB for RAM
-	 * pages only, so use the guest PAT directly.
-	 */
-	if (!kvm_arch_has_assigned_device(vcpu->kvm))
-		*g_pat = 0x0606060606060606;
-	else
-		*g_pat = vcpu->arch.pat;
-}
-
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	u8 mtrr;
-
-	/*
-	 * 1. MMIO: trust guest MTRR, so same as item 3.
-	 * 2. No passthrough: always map as WB, and force guest PAT to WB as well
-	 * 3. Passthrough: can't guarantee the result, try to trust guest.
-	 */
-	if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
-		return 0;
-
-	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) &&
-	    kvm_read_cr0(vcpu) & X86_CR0_CD)
-		return _PAGE_NOCACHE;
-
-	mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
-	return mtrr2protval[mtrr];
-}
-
 static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1278,7 +1182,6 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 		clr_cr_intercept(svm, INTERCEPT_CR3_READ);
 		clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
 		save->g_pat = svm->vcpu.arch.pat;
-		svm_set_guest_pat(svm, &save->g_pat);
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -1673,10 +1576,13 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	if (!vcpu->fpu_active)
 		cr0 |= X86_CR0_TS;
-
-	/* These are emulated via page tables.  */
-	cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
-
+	/*
+	 * re-enable caching here because the QEMU bios
+	 * does not do it - this results in some delay at
+	 * reboot
+	 */
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+		cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
 	svm->vmcb->save.cr0 = cr0;
 	mark_dirty(svm->vmcb, VMCB_CR);
 	update_cr0_intercept(svm);
@@ -3351,16 +3257,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
-	case MSR_IA32_CR_PAT:
-		if (npt_enabled) {
-			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
-				return 1;
-			vcpu->arch.pat = data;
-			svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
-			mark_dirty(svm->vmcb, VMCB_NPT);
-			break;
-		}
-		/* fall through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -4195,6 +4091,11 @@ static bool svm_has_high_real_mode_segbase(void)
 	return true;
 }
 
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+	return 0;
+}
+
 static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 64076740251e..06ef4908ba61 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8617,17 +8617,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	u64 ipat = 0;
 
 	/* For VT-d and EPT combination
-	 * 1. MMIO: guest may want to apply WC, trust it.
+	 * 1. MMIO: always map as UC
 	 * 2. EPT with VT-d:
 	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.  So the same as item 1.
+	 *	result, try to trust guest.
 	 *   b. VT-d with snooping control feature: snooping control feature of
 	 *	VT-d engine can guarantee the cache correctness. Just set it
 	 *	to WB to keep consistent with host. So the same as item 3.
 	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
 	 *    consistent with host MTRR
 	 */
-	if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+	if (is_mmio) {
+		cache = MTRR_TYPE_UNCACHABLE;
+		goto exit;
+	}
+
+	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
 		ipat = VMX_EPT_IPAT_BIT;
 		cache = MTRR_TYPE_WRBACK;
 		goto exit;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 991466bf8dee..92511d4b7236 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1708,8 +1708,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		vcpu->pvclock_set_guest_stopped_request = false;
 	}
 
-	pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO;
-
 	/* If the host uses TSC clocksource, then it is stable */
 	if (use_master_clock)
 		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
@@ -2007,8 +2005,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					&vcpu->requests);
 
 			ka->boot_vcpu_runs_old_kvmclock = tmp;
-
-			ka->kvmclock_offset = -get_kernel_ns();
 		}
 
 		vcpu->arch.time = data;