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

Pull KVM updates from Paolo Bonzini:
 "For x86, there is a new alternative and (in the future) more scalable
  implementation of extended page tables that does not need a reverse
  map from guest physical addresses to host physical addresses.

  For now it is disabled by default because it is still lacking a few of
  the existing MMU's bells and whistles. However it is a very solid
  piece of work and it is already available for people to hammer on it.

  Other updates:

  ARM:
   - New page table code for both hypervisor and guest stage-2
   - Introduction of a new EL2-private host context
   - Allow EL2 to have its own private per-CPU variables
   - Support of PMU event filtering
   - Complete rework of the Spectre mitigation

  PPC:
   - Fix for running nested guests with in-kernel IRQ chip
   - Fix race condition causing occasional host hard lockup
   - Minor cleanups and bugfixes

  x86:
   - allow trapping unknown MSRs to userspace
   - allow userspace to force #GP on specific MSRs
   - INVPCID support on AMD
   - nested AMD cleanup, on demand allocation of nested SVM state
   - hide PV MSRs and hypercalls for features not enabled in CPUID
   - new test for MSR_IA32_TSC writes from host and guest
   - cleanups: MMU, CPUID, shared MSRs
   - LAPIC latency optimizations ad bugfixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (232 commits)
  kvm: x86/mmu: NX largepage recovery for TDP MMU
  kvm: x86/mmu: Don't clear write flooding count for direct roots
  kvm: x86/mmu: Support MMIO in the TDP MMU
  kvm: x86/mmu: Support write protection for nesting in tdp MMU
  kvm: x86/mmu: Support disabling dirty logging for the tdp MMU
  kvm: x86/mmu: Support dirty logging for the TDP MMU
  kvm: x86/mmu: Support changed pte notifier in tdp MMU
  kvm: x86/mmu: Add access tracking for tdp_mmu
  kvm: x86/mmu: Support invalidate range MMU notifier for TDP MMU
  kvm: x86/mmu: Allocate struct kvm_mmu_pages for all pages in TDP MMU
  kvm: x86/mmu: Add TDP MMU PF handler
  kvm: x86/mmu: Remove disallowed_hugepage_adjust shadow_walk_iterator arg
  kvm: x86/mmu: Support zapping SPTEs in the TDP MMU
  KVM: Cache as_id in kvm_memory_slot
  kvm: x86/mmu: Add functions to handle changed TDP SPTEs
  kvm: x86/mmu: Allocate and free TDP MMU roots
  kvm: x86/mmu: Init / Uninit the TDP MMU
  kvm: x86/mmu: Introduce tdp_iter
  KVM: mmu: extract spte.h and spte.c
  KVM: mmu: Separate updating a PTE from kvm_set_pte_rmapp
  ...

1 files changed, 56 insertions, 47 deletions

diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index a798e1731709..1d853fe4c778 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -31,6 +31,7 @@ static const u32 host_save_user_msrs[] = {
 
 #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
 
+#define MAX_DIRECT_ACCESS_MSRS	15
 #define MSRPM_OFFSETS	16
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
@@ -85,8 +86,7 @@ struct svm_nested_state {
 	struct vmcb *hsave;
 	u64 hsave_msr;
 	u64 vm_cr_msr;
-	u64 vmcb;
-	u32 host_intercept_exceptions;
+	u64 vmcb12_gpa;
 
 	/* These are the merged vectors */
 	u32 *msrpm;
@@ -97,6 +97,8 @@ struct svm_nested_state {
 
 	/* cache for control fields of the guest */
 	struct vmcb_control_area ctl;
+
+	bool initialized;
 };
 
 struct vcpu_svm {
@@ -158,6 +160,12 @@ struct vcpu_svm {
 	 */
 	struct list_head ir_list;
 	spinlock_t ir_list_lock;
+
+	/* Save desired MSR intercept (read: pass-through) state */
+	struct {
+		DECLARE_BITMAP(read, MAX_DIRECT_ACCESS_MSRS);
+		DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS);
+	} shadow_msr_intercept;
 };
 
 struct svm_cpu_data {
@@ -214,51 +222,44 @@ static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm)
 		return svm->vmcb;
 }
 
-static inline void set_cr_intercept(struct vcpu_svm *svm, int bit)
+static inline void vmcb_set_intercept(struct vmcb_control_area *control, u32 bit)
 {
-	struct vmcb *vmcb = get_host_vmcb(svm);
-
-	vmcb->control.intercept_cr |= (1U << bit);
-
-	recalc_intercepts(svm);
+	WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT);
+	__set_bit(bit, (unsigned long *)&control->intercepts);
 }
 
-static inline void clr_cr_intercept(struct vcpu_svm *svm, int bit)
+static inline void vmcb_clr_intercept(struct vmcb_control_area *control, u32 bit)
 {
-	struct vmcb *vmcb = get_host_vmcb(svm);
-
-	vmcb->control.intercept_cr &= ~(1U << bit);
-
-	recalc_intercepts(svm);
+	WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT);
+	__clear_bit(bit, (unsigned long *)&control->intercepts);
 }
 
-static inline bool is_cr_intercept(struct vcpu_svm *svm, int bit)
+static inline bool vmcb_is_intercept(struct vmcb_control_area *control, u32 bit)
 {
-	struct vmcb *vmcb = get_host_vmcb(svm);
-
-	return vmcb->control.intercept_cr & (1U << bit);
+	WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT);
+	return test_bit(bit, (unsigned long *)&control->intercepts);
 }
 
 static inline void set_dr_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_dr = (1 << INTERCEPT_DR0_READ)
-		| (1 << INTERCEPT_DR1_READ)
-		| (1 << INTERCEPT_DR2_READ)
-		| (1 << INTERCEPT_DR3_READ)
-		| (1 << INTERCEPT_DR4_READ)
-		| (1 << INTERCEPT_DR5_READ)
-		| (1 << INTERCEPT_DR6_READ)
-		| (1 << INTERCEPT_DR7_READ)
-		| (1 << INTERCEPT_DR0_WRITE)
-		| (1 << INTERCEPT_DR1_WRITE)
-		| (1 << INTERCEPT_DR2_WRITE)
-		| (1 << INTERCEPT_DR3_WRITE)
-		| (1 << INTERCEPT_DR4_WRITE)
-		| (1 << INTERCEPT_DR5_WRITE)
-		| (1 << INTERCEPT_DR6_WRITE)
-		| (1 << INTERCEPT_DR7_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
 
 	recalc_intercepts(svm);
 }
@@ -267,25 +268,27 @@ static inline void clr_dr_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_dr = 0;
+	vmcb->control.intercepts[INTERCEPT_DR] = 0;
 
 	recalc_intercepts(svm);
 }
 
-static inline void set_exception_intercept(struct vcpu_svm *svm, int bit)
+static inline void set_exception_intercept(struct vcpu_svm *svm, u32 bit)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_exceptions |= (1U << bit);
+	WARN_ON_ONCE(bit >= 32);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit);
 
 	recalc_intercepts(svm);
 }
 
-static inline void clr_exception_intercept(struct vcpu_svm *svm, int bit)
+static inline void clr_exception_intercept(struct vcpu_svm *svm, u32 bit)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_exceptions &= ~(1U << bit);
+	WARN_ON_ONCE(bit >= 32);
+	vmcb_clr_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit);
 
 	recalc_intercepts(svm);
 }
@@ -294,7 +297,7 @@ static inline void svm_set_intercept(struct vcpu_svm *svm, int bit)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept |= (1ULL << bit);
+	vmcb_set_intercept(&vmcb->control, bit);
 
 	recalc_intercepts(svm);
 }
@@ -303,14 +306,14 @@ static inline void svm_clr_intercept(struct vcpu_svm *svm, int bit)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept &= ~(1ULL << bit);
+	vmcb_clr_intercept(&vmcb->control, bit);
 
 	recalc_intercepts(svm);
 }
 
 static inline bool svm_is_intercept(struct vcpu_svm *svm, int bit)
 {
-	return (svm->vmcb->control.intercept & (1ULL << bit)) != 0;
+	return vmcb_is_intercept(&svm->vmcb->control, bit);
 }
 
 static inline bool vgif_enabled(struct vcpu_svm *svm)
@@ -345,11 +348,15 @@ static inline bool gif_set(struct vcpu_svm *svm)
 /* svm.c */
 #define MSR_CR3_LEGACY_RESERVED_MASK		0xfe7U
 #define MSR_CR3_LEGACY_PAE_RESERVED_MASK	0x7U
-#define MSR_CR3_LONG_RESERVED_MASK		0xfff0000000000fe7U
+#define MSR_CR3_LONG_MBZ_MASK			0xfff0000000000000U
 #define MSR_INVALID				0xffffffffU
 
 u32 svm_msrpm_offset(u32 msr);
-void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);
+u32 *svm_vcpu_alloc_msrpm(void);
+void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm);
+void svm_vcpu_free_msrpm(u32 *msrpm);
+
+int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);
 void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 void svm_flush_tlb(struct kvm_vcpu *vcpu);
@@ -374,22 +381,24 @@ static inline bool nested_svm_virtualize_tpr(struct kvm_vcpu *vcpu)
 
 static inline bool nested_exit_on_smi(struct vcpu_svm *svm)
 {
-	return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_SMI));
+	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SMI);
 }
 
 static inline bool nested_exit_on_intr(struct vcpu_svm *svm)
 {
-	return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_INTR));
+	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INTR);
 }
 
 static inline bool nested_exit_on_nmi(struct vcpu_svm *svm)
 {
-	return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_NMI));
+	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI);
 }
 
 int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 			 struct vmcb *nested_vmcb);
 void svm_leave_nested(struct vcpu_svm *svm);
+void svm_free_nested(struct vcpu_svm *svm);
+int svm_allocate_nested(struct vcpu_svm *svm);
 int nested_svm_vmrun(struct vcpu_svm *svm);
 void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb);
 int nested_svm_vmexit(struct vcpu_svm *svm);