Merge tag 'kvm-4.14-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "First batch of KVM changes for 4.14

  Common:
   - improve heuristic for boosting preempted spinlocks by ignoring
     VCPUs in user mode

  ARM:
   - fix for decoding external abort types from guests

   - added support for migrating the active priority of interrupts when
     running a GICv2 guest on a GICv3 host

   - minor cleanup

  PPC:
   - expose storage keys to userspace

   - merge kvm-ppc-fixes with a fix that missed 4.13 because of
     vacations

   - fixes

  s390:
   - merge of kvm/master to avoid conflicts with additional sthyi fixes

   - wire up the no-dat enhancements in KVM

   - multiple epoch facility (z14 feature)

   - Configuration z/Architecture Mode

   - more sthyi fixes

   - gdb server range checking fix

   - small code cleanups

  x86:
   - emulate Hyper-V TSC frequency MSRs

   - add nested INVPCID

   - emulate EPTP switching VMFUNC

   - support Virtual GIF

   - support 5 level page tables

   - speedup nested VM exits by packing byte operations

   - speedup MMIO by using hardware provided physical address

   - a lot of fixes and cleanups, especially nested"

* tag 'kvm-4.14-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (67 commits)
  KVM: arm/arm64: Support uaccess of GICC_APRn
  KVM: arm/arm64: Extract GICv3 max APRn index calculation
  KVM: arm/arm64: vITS: Drop its_ite->lpi field
  KVM: arm/arm64: vgic: constify seq_operations and file_operations
  KVM: arm/arm64: Fix guest external abort matching
  KVM: PPC: Book3S HV: Fix memory leak in kvm_vm_ioctl_get_htab_fd
  KVM: s390: vsie: cleanup mcck reinjection
  KVM: s390: use WARN_ON_ONCE only for checking
  KVM: s390: guestdbg: fix range check
  KVM: PPC: Book3S HV: Report storage key support to userspace
  KVM: PPC: Book3S HV: Fix case where HDEC is treated as 32-bit on POWER9
  KVM: PPC: Book3S HV: Fix invalid use of register expression
  KVM: PPC: Book3S HV: Fix H_REGISTER_VPA VPA size validation
  KVM: PPC: Book3S HV: Fix setting of storage key in H_ENTER
  KVM: PPC: e500mc: Fix a NULL dereference
  KVM: PPC: e500: Fix some NULL dereferences on error
  KVM: PPC: Book3S HV: Protect updates to spapr_tce_tables list
  KVM: s390: we are always in czam mode
  KVM: s390: expose no-DAT to guest and migration support
  KVM: s390: sthyi: remove invalid guest write access
  ...

5 files changed, 41 insertions, 32 deletions

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 42bbbf0f173d..2519c6c801c9 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -288,6 +288,7 @@
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
 #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF	(15*32+16) /* Virtual GIF */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
 #define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index fde36f189836..fa2558e12024 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -219,8 +219,8 @@ struct x86_emulate_ops {
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
 
-	void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
-			  u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
+	bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx,
+			  u32 *ecx, u32 *edx, bool check_limit);
 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
 
 	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 369e41c23f07..8844eee290b2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -79,15 +79,14 @@
 			  | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
 			  | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
 
-#define CR3_L_MODE_RESERVED_BITS 0xFFFFFF0000000000ULL
 #define CR3_PCID_INVD		 BIT_64(63)
 #define CR4_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
 			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
-			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE | X86_CR4_SMAP \
-			  | X86_CR4_PKE))
+			  | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
+			  | X86_CR4_SMAP | X86_CR4_PKE))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
 
@@ -204,7 +203,6 @@ enum {
 #define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT)
 
 #define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK |	\
-				 PFERR_USER_MASK |		\
 				 PFERR_WRITE_MASK |		\
 				 PFERR_PRESENT_MASK)
 
@@ -317,15 +315,17 @@ struct kvm_pio_request {
 	int size;
 };
 
+#define PT64_ROOT_MAX_LEVEL 5
+
 struct rsvd_bits_validate {
-	u64 rsvd_bits_mask[2][4];
+	u64 rsvd_bits_mask[2][PT64_ROOT_MAX_LEVEL];
 	u64 bad_mt_xwr;
 };
 
 /*
- * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
- * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
- * mode.
+ * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit,
+ * and 2-level 32-bit).  The kvm_mmu structure abstracts the details of the
+ * current mmu mode.
  */
 struct kvm_mmu {
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
@@ -548,8 +548,8 @@ struct kvm_vcpu_arch {
 
 	struct kvm_queued_exception {
 		bool pending;
+		bool injected;
 		bool has_error_code;
-		bool reinject;
 		u8 nr;
 		u32 error_code;
 		u8 nested_apf;
@@ -687,8 +687,12 @@ struct kvm_vcpu_arch {
 	int pending_ioapic_eoi;
 	int pending_external_vector;
 
-	/* GPA available (AMD only) */
+	/* GPA available */
 	bool gpa_available;
+	gpa_t gpa_val;
+
+	/* be preempted when it's in kernel-mode(cpl=0) */
+	bool preempted_in_kernel;
 };
 
 struct kvm_lpage_info {
@@ -979,7 +983,7 @@ struct kvm_x86_ops {
 	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
-	int (*get_tdp_level)(void);
+	int (*get_tdp_level)(struct kvm_vcpu *vcpu);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
@@ -1297,20 +1301,6 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
 }
 
-static inline u64 get_canonical(u64 la)
-{
-	return ((int64_t)la << 16) >> 16;
-}
-
-static inline bool is_noncanonical_address(u64 la)
-{
-#ifdef CONFIG_X86_64
-	return get_canonical(la) != la;
-#else
-	return false;
-#endif
-}
-
 #define TSS_IOPB_BASE_OFFSET 0x66
 #define TSS_BASE_SIZE 0x68
 #define TSS_IOPB_SIZE (65536 / 8)
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 58fffe79e417..14835dd205a5 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -107,6 +107,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define V_IRQ_SHIFT 8
 #define V_IRQ_MASK (1 << V_IRQ_SHIFT)
 
+#define V_GIF_SHIFT 9
+#define V_GIF_MASK (1 << V_GIF_SHIFT)
+
 #define V_INTR_PRIO_SHIFT 16
 #define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
 
@@ -116,6 +119,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define V_INTR_MASKING_SHIFT 24
 #define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
 
+#define V_GIF_ENABLE_SHIFT 25
+#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT)
+
 #define AVIC_ENABLE_SHIFT 31
 #define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT)
 
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 35cd06f636ab..caec8417539f 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -72,6 +72,7 @@
 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
 #define SECONDARY_EXEC_RDRAND			0x00000800
 #define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
+#define SECONDARY_EXEC_ENABLE_VMFUNC            0x00002000
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
 #define SECONDARY_EXEC_RDSEED			0x00010000
 #define SECONDARY_EXEC_ENABLE_PML               0x00020000
@@ -114,6 +115,10 @@
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 #define VMX_MISC_ACTIVITY_HLT			0x00000040
 
+/* VMFUNC functions */
+#define VMX_VMFUNC_EPTP_SWITCHING               0x00000001
+#define VMFUNC_EPTP_ENTRIES  512
+
 static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic)
 {
 	return vmx_basic & GENMASK_ULL(30, 0);
@@ -187,6 +192,8 @@ enum vmcs_field {
 	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
 	POSTED_INTR_DESC_ADDR           = 0x00002016,
 	POSTED_INTR_DESC_ADDR_HIGH      = 0x00002017,
+	VM_FUNCTION_CONTROL             = 0x00002018,
+	VM_FUNCTION_CONTROL_HIGH        = 0x00002019,
 	EPT_POINTER                     = 0x0000201a,
 	EPT_POINTER_HIGH                = 0x0000201b,
 	EOI_EXIT_BITMAP0                = 0x0000201c,
@@ -197,6 +204,8 @@ enum vmcs_field {
 	EOI_EXIT_BITMAP2_HIGH           = 0x00002021,
 	EOI_EXIT_BITMAP3                = 0x00002022,
 	EOI_EXIT_BITMAP3_HIGH           = 0x00002023,
+	EPTP_LIST_ADDRESS               = 0x00002024,
+	EPTP_LIST_ADDRESS_HIGH          = 0x00002025,
 	VMREAD_BITMAP                   = 0x00002026,
 	VMWRITE_BITMAP                  = 0x00002028,
 	XSS_EXIT_BITMAP                 = 0x0000202C,
@@ -444,6 +453,7 @@ enum vmcs_field {
 
 #define VMX_EPT_EXECUTE_ONLY_BIT		(1ull)
 #define VMX_EPT_PAGE_WALK_4_BIT			(1ull << 6)
+#define VMX_EPT_PAGE_WALK_5_BIT			(1ull << 7)
 #define VMX_EPTP_UC_BIT				(1ull << 8)
 #define VMX_EPTP_WB_BIT				(1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
@@ -459,12 +469,14 @@ enum vmcs_field {
 #define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT      (1ull << 10) /* (42 - 32) */
 #define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT   (1ull << 11) /* (43 - 32) */
 
-#define VMX_EPT_DEFAULT_GAW			3
-#define VMX_EPT_MAX_GAW				0x4
 #define VMX_EPT_MT_EPTE_SHIFT			3
-#define VMX_EPT_GAW_EPTP_SHIFT			3
-#define VMX_EPT_AD_ENABLE_BIT			(1ull << 6)
-#define VMX_EPT_DEFAULT_MT			0x6ull
+#define VMX_EPTP_PWL_MASK			0x38ull
+#define VMX_EPTP_PWL_4				0x18ull
+#define VMX_EPTP_PWL_5				0x20ull
+#define VMX_EPTP_AD_ENABLE_BIT			(1ull << 6)
+#define VMX_EPTP_MT_MASK			0x7ull
+#define VMX_EPTP_MT_WB				0x6ull
+#define VMX_EPTP_MT_UC				0x0ull
 #define VMX_EPT_READABLE_MASK			0x1ull
 #define VMX_EPT_WRITABLE_MASK			0x2ull
 #define VMX_EPT_EXECUTABLE_MASK			0x4ull