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
  ...

Documentation/virtual/kvm/devices/arm-vgic.txt

@@ -83,6 +83,11 @@ Groups:
 
     Bits for undefined preemption levels are RAZ/WI.
 
+    Note that this differs from a CPU's view of the APRs on hardware in which
+    a GIC without the security extensions expose group 0 and group 1 active
+    priorities in separate register groups, whereas we show a combined view
+    similar to GICv2's GICH_APR.
+
     For historical reasons and to provide ABI compatibility with userspace we
     export the GICC_PMR register in the format of the GICH_VMCR.VMPriMask
     field in the lower 5 bits of a word, meaning that userspace must always

Documentation/virtual/kvm/devices/vm.txt

@@ -176,7 +176,8 @@ Architectures: s390
 
 3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH
 
-Allows user space to set/get the TOD clock extension (u8).
+Allows user space to set/get the TOD clock extension (u8) (superseded by
+KVM_S390_VM_TOD_EXT).
 
 Parameters: address of a buffer in user space to store the data (u8) to
 Returns:    -EFAULT if the given address is not accessible from kernel space
@@ -190,6 +191,17 @@ the POP (u64).
 Parameters: address of a buffer in user space to store the data (u64) to
 Returns:    -EFAULT if the given address is not accessible from kernel space
 
+3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT
+Allows user space to set/get bits 0-63 of the TOD clock register as defined in
+the POP (u64). If the guest CPU model supports the TOD clock extension (u8), it
+also allows user space to get/set it. If the guest CPU model does not support
+it, it is stored as 0 and not allowed to be set to a value != 0.
+
+Parameters: address of a buffer in user space to store the data
+            (kvm_s390_vm_tod_clock) to
+Returns:    -EFAULT if the given address is not accessible from kernel space
+	    -EINVAL if setting the TOD clock extension to != 0 is not supported
+
 4. GROUP: KVM_S390_VM_CRYPTO
 Architectures: s390
 

MAINTAINERS

@@ -7464,26 +7464,38 @@ L:	kvm@vger.kernel.org
 W:	http://www.linux-kvm.org
 T:	git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
 S:	Supported
-F:	Documentation/*/kvm*.txt
 F:	Documentation/virtual/kvm/
-F:	arch/*/kvm/
-F:	arch/x86/kernel/kvm.c
-F:	arch/x86/kernel/kvmclock.c
-F:	arch/*/include/asm/kvm*
-F:	include/linux/kvm*
+F:	include/trace/events/kvm.h
+F:	include/uapi/asm-generic/kvm*
 F:	include/uapi/linux/kvm*
-F:	virt/kvm/
+F:	include/asm-generic/kvm*
+F:	include/linux/kvm*
+F:	include/kvm/iodev.h
+F:	virt/kvm/*
 F:	tools/kvm/
 
-KERNEL VIRTUAL MACHINE (KVM) FOR AMD-V
+KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86)
+M:	Paolo Bonzini <pbonzini@redhat.com>
+M:	Radim KrÄmář <rkrcmar@redhat.com>
+L:	kvm@vger.kernel.org
+W:	http://www.linux-kvm.org
+T:	git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
+S:	Supported
+F:	arch/x86/kvm/
+F:	arch/x86/include/uapi/asm/kvm*
+F:	arch/x86/include/asm/kvm*
+F:	arch/x86/kernel/kvm.c
+F:	arch/x86/kernel/kvmclock.c
+
+KERNEL VIRTUAL MACHINE FOR AMD-V (KVM/amd)
 M:	Joerg Roedel <joro@8bytes.org>
 L:	kvm@vger.kernel.org
 W:	http://www.linux-kvm.org/
 S:	Maintained
 F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
 
-KERNEL VIRTUAL MACHINE (KVM) FOR ARM
+KERNEL VIRTUAL MACHINE FOR ARM (KVM/arm)
 M:	Christoffer Dall <christoffer.dall@linaro.org>
 M:	Marc Zyngier <marc.zyngier@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -7497,14 +7509,16 @@ F:	arch/arm/kvm/
 F:	virt/kvm/arm/
 F:	include/kvm/arm_*
 
-KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
+KERNEL VIRTUAL MACHINE FOR POWERPC (KVM/powerpc)
 M:	Alexander Graf <agraf@suse.com>
 L:	kvm-ppc@vger.kernel.org
 W:	http://www.linux-kvm.org/
 T:	git git://github.com/agraf/linux-2.6.git
 S:	Supported
+F:	arch/powerpc/include/uapi/asm/kvm*
 F:	arch/powerpc/include/asm/kvm*
 F:	arch/powerpc/kvm/
+F:	arch/powerpc/kernel/kvm*
 
 KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
 M:	Christoffer Dall <christoffer.dall@linaro.org>
@@ -7531,7 +7545,8 @@ L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git
 S:	Supported
-F:	Documentation/s390/kvm.txt
+F:	arch/s390/include/uapi/asm/kvm*
+F:	arch/s390/include/asm/gmap.h
 F:	arch/s390/include/asm/kvm*
 F:	arch/s390/kvm/
 F:	arch/s390/mm/gmap.c

arch/arm/include/asm/kvm_arm.h

@@ -227,7 +227,6 @@
 
 #define HSR_DABT_S1PTW		(_AC(1, UL) << 7)
 #define HSR_DABT_CM		(_AC(1, UL) << 8)
-#define HSR_DABT_EA		(_AC(1, UL) << 9)
 
 #define kvm_arm_exception_type	\
 	{0, "RESET" }, 		\

arch/arm/include/asm/kvm_emulate.h

@@ -149,11 +149,6 @@ static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu)
 	return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT;
 }
 
-static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu)
-{
-	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_EA;
-}
-
 static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW;
@@ -206,6 +201,25 @@ static inline u8 kvm_vcpu_trap_get_fault_type(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE;
 }
 
+static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu)
+{
+	switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+	case FSC_SEA:
+	case FSC_SEA_TTW0:
+	case FSC_SEA_TTW1:
+	case FSC_SEA_TTW2:
+	case FSC_SEA_TTW3:
+	case FSC_SECC:
+	case FSC_SECC_TTW0:
+	case FSC_SECC_TTW1:
+	case FSC_SECC_TTW2:
+	case FSC_SECC_TTW3:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;

arch/arm/kvm/handle_exit.c

@@ -67,7 +67,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) {
 		trace_kvm_wfx(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
-		kvm_vcpu_on_spin(vcpu);
+		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
 	} else {
 		trace_kvm_wfx(*vcpu_pc(vcpu), false);
 		vcpu->stat.wfi_exit_stat++;

arch/arm64/include/asm/kvm_emulate.h

@@ -188,11 +188,6 @@ static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
-static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
-{
-	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_EA);
-}
-
 static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
@@ -240,6 +235,25 @@ static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
+static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
+{
+	switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+	case FSC_SEA:
+	case FSC_SEA_TTW0:
+	case FSC_SEA_TTW1:
+	case FSC_SEA_TTW2:
+	case FSC_SEA_TTW3:
+	case FSC_SECC:
+	case FSC_SECC_TTW0:
+	case FSC_SECC_TTW1:
+	case FSC_SECC_TTW2:
+	case FSC_SECC_TTW3:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 {
 	u32 esr = kvm_vcpu_get_hsr(vcpu);

arch/arm64/kvm/handle_exit.c

@@ -84,7 +84,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
-		kvm_vcpu_on_spin(vcpu);
+		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
 	} else {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
 		vcpu->stat.wfi_exit_stat++;

arch/arm64/kvm/vgic-sys-reg-v3.c

@@ -208,29 +208,12 @@ static void vgic_v3_access_apr_reg(struct kvm_vcpu *vcpu,
 static bool access_gic_aprn(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			    const struct sys_reg_desc *r, u8 apr)
 {
-	struct vgic_cpu *vgic_v3_cpu = &vcpu->arch.vgic_cpu;
 	u8 idx = r->Op2 & 3;
 
-	/*
-	 * num_pri_bits are initialized with HW supported values.
-	 * We can rely safely on num_pri_bits even if VM has not
-	 * restored ICC_CTLR_EL1 before restoring APnR registers.
-	 */
-	switch (vgic_v3_cpu->num_pri_bits) {
-	case 7:
-		vgic_v3_access_apr_reg(vcpu, p, apr, idx);
-		break;
-	case 6:
-		if (idx > 1)
-			goto err;
-		vgic_v3_access_apr_reg(vcpu, p, apr, idx);
-		break;
-	default:
-		if (idx > 0)
-			goto err;
-		vgic_v3_access_apr_reg(vcpu, p, apr, idx);
-	}
+	if (idx > vgic_v3_max_apr_idx(vcpu))
+		goto err;
 
+	vgic_v3_access_apr_reg(vcpu, p, apr, idx);
 	return true;
 err:
 	if (!p->is_write)

arch/mips/kvm/mips.c

@@ -98,6 +98,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return !!(vcpu->arch.pending_exceptions);
 }
 
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return 1;

arch/powerpc/include/asm/book3s/64/mmu-hash.h

@@ -104,6 +104,7 @@
 #define HPTE_R_C		ASM_CONST(0x0000000000000080)
 #define HPTE_R_R		ASM_CONST(0x0000000000000100)
 #define HPTE_R_KEY_LO		ASM_CONST(0x0000000000000e00)
+#define HPTE_R_KEY		(HPTE_R_KEY_LO | HPTE_R_KEY_HI)
 
 #define HPTE_V_1TB_SEG		ASM_CONST(0x4000000000000000)
 #define HPTE_V_VRMA_MASK	ASM_CONST(0x4001ffffff000000)

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -1941,6 +1941,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
 	rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
 	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC);
 	if (ret < 0) {
+		kfree(ctx);
 		kvm_put_kvm(kvm);
 		return ret;
 	}

arch/powerpc/kvm/book3s_64_vio.c

@@ -265,8 +265,11 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 {
 	struct kvmppc_spapr_tce_table *stt = filp->private_data;
 	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
+	struct kvm *kvm = stt->kvm;
 
+	mutex_lock(&kvm->lock);
 	list_del_rcu(&stt->list);
+	mutex_unlock(&kvm->lock);
 
 	list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
 		WARN_ON(!kref_read(&stit->kref));
@@ -298,7 +301,6 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	unsigned long npages, size;
 	int ret = -ENOMEM;
 	int i;
-	int fd = -1;
 
 	if (!args->size)
 		return -EINVAL;
@@ -328,11 +330,6 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 			goto fail;
 	}
 
-	ret = fd = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				    stt, O_RDWR | O_CLOEXEC);
-	if (ret < 0)
-		goto fail;
-
 	mutex_lock(&kvm->lock);
 
 	/* Check this LIOBN hasn't been previously allocated */
@@ -344,17 +341,19 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 		}
 	}
 
-	if (!ret) {
+	if (!ret)
+		ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
+				       stt, O_RDWR | O_CLOEXEC);
+
+	if (ret >= 0) {
 		list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
 		kvm_get_kvm(kvm);
 	}
 
 	mutex_unlock(&kvm->lock);
 
-	if (!ret)
-		return fd;
-
-	put_unused_fd(fd);
+	if (ret >= 0)
+		return ret;
 
  fail:
 	for (i = 0; i < npages; i++)

arch/powerpc/kvm/book3s_hv.c

@@ -485,7 +485,13 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 
 	switch (subfunc) {
 	case H_VPA_REG_VPA:		/* register VPA */
-		if (len < sizeof(struct lppaca))
+		/*
+		 * The size of our lppaca is 1kB because of the way we align
+		 * it for the guest to avoid crossing a 4kB boundary. We only
+		 * use 640 bytes of the structure though, so we should accept
+		 * clients that set a size of 640.
+		 */
+		if (len < 640)
 			break;
 		vpap = &tvcpu->arch.vpa;
 		err = 0;
@@ -3336,6 +3342,14 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
 	if (radix_enabled())
 		return -EINVAL;
 
+	/*
+	 * POWER7, POWER8 and POWER9 all support 32 storage keys for data.
+	 * POWER7 doesn't support keys for instruction accesses,
+	 * POWER8 and POWER9 do.
+	 */
+	info->data_keys = 32;
+	info->instr_keys = cpu_has_feature(CPU_FTR_ARCH_207S) ? 32 : 0;
+
 	info->flags = KVM_PPC_PAGE_SIZES_REAL;
 	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
 		info->flags |= KVM_PPC_1T_SEGMENTS;

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -269,7 +269,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	if (!realmode)
 		local_irq_restore(irq_flags);
 
-	ptel &= ~(HPTE_R_PP0 - psize);
+	ptel &= HPTE_R_KEY | HPTE_R_PP0 | (psize-1);
 	ptel |= pa;
 
 	if (pa)

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -982,7 +982,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 #ifdef CONFIG_KVM_XICS
 	/* We are entering the guest on that thread, push VCPU to XIVE */
 	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
-	cmpldi	cr0, r10, r0
+	cmpldi	cr0, r10, 0
 	beq	no_xive
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
@@ -1286,7 +1286,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
 	bne	2f
 	mfspr	r3,SPRN_HDEC
-	cmpwi	r3,0
+	EXTEND_HDEC(r3)
+	cmpdi	r3,0
 	mr	r4,r9
 	bge	fast_guest_return
 2: