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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - VHE optimizations

   - EL2 address space randomization

   - speculative execution mitigations ("variant 3a", aka execution past
     invalid privilege register access)

   - bugfixes and cleanups

  PPC:
   - improvements for the radix page fault handler for HV KVM on POWER9

  s390:
   - more kvm stat counters

   - virtio gpu plumbing

   - documentation

   - facilities improvements

  x86:
   - support for VMware magic I/O port and pseudo-PMCs

   - AMD pause loop exiting

   - support for AMD core performance extensions

   - support for synchronous register access

   - expose nVMX capabilities to userspace

   - support for Hyper-V signaling via eventfd

   - use Enlightened VMCS when running on Hyper-V

   - allow userspace to disable MWAIT/HLT/PAUSE vmexits

   - usual roundup of optimizations and nested virtualization bugfixes

  Generic:
   - API selftest infrastructure (though the only tests are for x86 as
     of now)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (174 commits)
  kvm: x86: fix a prototype warning
  kvm: selftests: add sync_regs_test
  kvm: selftests: add API testing infrastructure
  kvm: x86: fix a compile warning
  KVM: X86: Add Force Emulation Prefix for "emulate the next instruction"
  KVM: X86: Introduce handle_ud()
  KVM: vmx: unify adjacent #ifdefs
  x86: kvm: hide the unused 'cpu' variable
  KVM: VMX: remove bogus WARN_ON in handle_ept_misconfig
  Revert "KVM: X86: Fix SMRAM accessing even if VM is shutdown"
  kvm: Add emulation for movups/movupd
  KVM: VMX: raise internal error for exception during invalid protected mode state
  KVM: nVMX: Optimization: Dont set KVM_REQ_EVENT when VMExit with nested_run_pending
  KVM: nVMX: Require immediate-exit when event reinjected to L2 and L1 event pending
  KVM: x86: Fix misleading comments on handling pending exceptions
  KVM: x86: Rename interrupt.pending to interrupt.injected
  KVM: VMX: No need to clear pending NMI/interrupt on inject realmode interrupt
  x86/kvm: use Enlightened VMCS when running on Hyper-V
  x86/hyper-v: detect nested features
  x86/hyper-v: define struct hv_enlightened_vmcs and clean field bits
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -1907,6 +1907,9 @@
 	kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
 			Default is 0 (don't ignore, but inject #GP)
 
+	kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface.
+				   Default is false (don't support).
+
 	kvm.mmu_audit=	[KVM] This is a R/W parameter which allows audit
 			KVM MMU at runtime.
 			Default is 0 (off)

Documentation/arm64/memory.txt

@@ -86,9 +86,12 @@ Translation table lookup with 64KB pages:
  +-------------------------------------------------> [63] TTBR0/1
 
 
-When using KVM without the Virtualization Host Extensions, the hypervisor
-maps kernel pages in EL2 at a fixed offset from the kernel VA. See the
-kern_hyp_va macro for more details.
+When using KVM without the Virtualization Host Extensions, the
+hypervisor maps kernel pages in EL2 at a fixed (and potentially
+random) offset from the linear mapping. See the kern_hyp_va macro and
+kvm_update_va_mask function for more details. MMIO devices such as
+GICv2 gets mapped next to the HYP idmap page, as do vectors when
+ARM64_HARDEN_EL2_VECTORS is selected for particular CPUs.
 
 When using KVM with the Virtualization Host Extensions, no additional
 mappings are created, since the host kernel runs directly in EL2.

Documentation/virtual/kvm/00-INDEX

@@ -1,7 +1,12 @@
 00-INDEX
 	- this file.
+amd-memory-encryption.rst
+	- notes on AMD Secure Encrypted Virtualization feature and SEV firmware
+	  command description
 api.txt
 	- KVM userspace API.
+arm
+	- internal ABI between the kernel and HYP (for arm/arm64)
 cpuid.txt
 	- KVM-specific cpuid leaves (x86).
 devices/
@@ -26,6 +31,5 @@ s390-diag.txt
 	- Diagnose hypercall description (for IBM S/390)
 timekeeping.txt
 	- timekeeping virtualization for x86-based architectures.
-amd-memory-encryption.txt
-	- notes on AMD Secure Encrypted Virtualization feature and SEV firmware
-	  command description
+vcpu-requests.rst
+	- internal VCPU request API

Documentation/virtual/kvm/api.txt

@@ -3480,7 +3480,7 @@ encrypted VMs.
 
 Currently, this ioctl is used for issuing Secure Encrypted Virtualization
 (SEV) commands on AMD Processors. The SEV commands are defined in
-Documentation/virtual/kvm/amd-memory-encryption.txt.
+Documentation/virtual/kvm/amd-memory-encryption.rst.
 
 4.111 KVM_MEMORY_ENCRYPT_REG_REGION
 
@@ -3516,6 +3516,38 @@ Returns: 0 on success; -1 on error
 This ioctl can be used to unregister the guest memory region registered
 with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above.
 
+4.113 KVM_HYPERV_EVENTFD
+
+Capability: KVM_CAP_HYPERV_EVENTFD
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_hyperv_eventfd (in)
+
+This ioctl (un)registers an eventfd to receive notifications from the guest on
+the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without
+causing a user exit.  SIGNAL_EVENT hypercall with non-zero event flag number
+(bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit.
+
+struct kvm_hyperv_eventfd {
+	__u32 conn_id;
+	__s32 fd;
+	__u32 flags;
+	__u32 padding[3];
+};
+
+The conn_id field should fit within 24 bits:
+
+#define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
+
+The acceptable values for the flags field are:
+
+#define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
+
+Returns: 0 on success,
+	-EINVAL if conn_id or flags is outside the allowed range
+	-ENOENT on deassign if the conn_id isn't registered
+	-EEXIST on assign if the conn_id is already registered
+
 
 5. The kvm_run structure
 ------------------------
@@ -3873,7 +3905,7 @@ in userspace.
 	__u64 kvm_dirty_regs;
 	union {
 		struct kvm_sync_regs regs;
-		char padding[1024];
+		char padding[SYNC_REGS_SIZE_BYTES];
 	} s;
 
 If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
@@ -4078,6 +4110,46 @@ Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be
 accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from
 the guest.
 
+6.74 KVM_CAP_SYNC_REGS
+Architectures: s390, x86
+Target: s390: always enabled, x86: vcpu
+Parameters: none
+Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register
+sets are supported (bitfields defined in arch/x86/include/uapi/asm/kvm.h).
+
+As described above in the kvm_sync_regs struct info in section 5 (kvm_run):
+KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers
+without having to call SET/GET_*REGS". This reduces overhead by eliminating
+repeated ioctl calls for setting and/or getting register values. This is
+particularly important when userspace is making synchronous guest state
+modifications, e.g. when emulating and/or intercepting instructions in
+userspace.
+
+For s390 specifics, please refer to the source code.
+
+For x86:
+- the register sets to be copied out to kvm_run are selectable
+  by userspace (rather that all sets being copied out for every exit).
+- vcpu_events are available in addition to regs and sregs.
+
+For x86, the 'kvm_valid_regs' field of struct kvm_run is overloaded to
+function as an input bit-array field set by userspace to indicate the
+specific register sets to be copied out on the next exit.
+
+To indicate when userspace has modified values that should be copied into
+the vCPU, the all architecture bitarray field, 'kvm_dirty_regs' must be set.
+This is done using the same bitflags as for the 'kvm_valid_regs' field.
+If the dirty bit is not set, then the register set values will not be copied
+into the vCPU even if they've been modified.
+
+Unused bitfields in the bitarrays must be set to zero.
+
+struct kvm_sync_regs {
+        struct kvm_regs regs;
+        struct kvm_sregs sregs;
+        struct kvm_vcpu_events events;
+};
+
 7. Capabilities that can be enabled on VMs
 ------------------------------------------
 
@@ -4286,6 +4358,26 @@ enables QEMU to build error log and branch to guest kernel registered
 machine check handling routine. Without this capability KVM will
 branch to guests' 0x200 interrupt vector.
 
+7.13 KVM_CAP_X86_DISABLE_EXITS
+
+Architectures: x86
+Parameters: args[0] defines which exits are disabled
+Returns: 0 on success, -EINVAL when args[0] contains invalid exits
+
+Valid bits in args[0] are
+
+#define KVM_X86_DISABLE_EXITS_MWAIT            (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HLT              (1 << 1)
+
+Enabling this capability on a VM provides userspace with a way to no
+longer intercept some instructions for improved latency in some
+workloads, and is suggested when vCPUs are associated to dedicated
+physical CPUs.  More bits can be added in the future; userspace can
+just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable
+all such vmexits.
+
+Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
+
 8. Other capabilities.
 ----------------------
 
@@ -4398,15 +4490,6 @@ reserved.
     Both registers and addresses are 64-bits wide.
     It will be possible to run 64-bit or 32-bit guest code.
 
-8.8 KVM_CAP_X86_GUEST_MWAIT
-
-Architectures: x86
-
-This capability indicates that guest using memory monotoring instructions
-(MWAIT/MWAITX) to stop the virtual CPU will not cause a VM exit.  As such time
-spent while virtual CPU is halted in this way will then be accounted for as
-guest running time on the host (as opposed to e.g. HLT).
-
 8.9 KVM_CAP_ARM_USER_IRQ
 
 Architectures: arm, arm64
@@ -4483,3 +4566,33 @@ Parameters: none
 This capability indicates if the flic device will be able to get/set the
 AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows
 to discover this without having to create a flic device.
+
+8.14 KVM_CAP_S390_PSW
+
+Architectures: s390
+
+This capability indicates that the PSW is exposed via the kvm_run structure.
+
+8.15 KVM_CAP_S390_GMAP
+
+Architectures: s390
+
+This capability indicates that the user space memory used as guest mapping can
+be anywhere in the user memory address space, as long as the memory slots are
+aligned and sized to a segment (1MB) boundary.
+
+8.16 KVM_CAP_S390_COW
+
+Architectures: s390
+
+This capability indicates that the user space memory used as guest mapping can
+use copy-on-write semantics as well as dirty pages tracking via read-only page
+tables.
+
+8.17 KVM_CAP_S390_BPB
+
+Architectures: s390
+
+This capability indicates that kvm will implement the interfaces to handle
+reset, migration and nested KVM for branch prediction blocking. The stfle
+facility 82 should not be provided to the guest without this capability.

Documentation/virtual/kvm/cpuid.txt

@@ -23,8 +23,8 @@ This function queries the presence of KVM cpuid leafs.
 
 
 function: define KVM_CPUID_FEATURES (0x40000001)
-returns : ebx, ecx, edx = 0
-          eax = and OR'ed group of (1 << flag), where each flags is:
+returns : ebx, ecx
+          eax = an OR'ed group of (1 << flag), where each flags is:
 
 
 flag                               || value || meaning
@@ -66,3 +66,14 @@ KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
                                    ||       || per-cpu warps are expected in
                                    ||       || kvmclock.
 ------------------------------------------------------------------------------
+
+          edx = an OR'ed group of (1 << flag), where each flags is:
+
+
+flag                               || value || meaning
+==================================================================================
+KVM_HINTS_DEDICATED                ||     0 || guest checks this feature bit to
+                                   ||       || determine if there is vCPU pinning
+                                   ||       || and there is no vCPU over-commitment,
+                                   ||       || allowing optimizations
+----------------------------------------------------------------------------------

MAINTAINERS

@@ -6516,7 +6516,7 @@ S:	Maintained
 F:	Documentation/networking/netvsc.txt
 F:	arch/x86/include/asm/mshyperv.h
 F:	arch/x86/include/asm/trace/hyperv.h
-F:	arch/x86/include/uapi/asm/hyperv.h
+F:	arch/x86/include/asm/hyperv-tlfs.h
 F:	arch/x86/kernel/cpu/mshyperv.c
 F:	arch/x86/hyperv
 F:	drivers/hid/hid-hyperv.c

arch/arm/include/asm/kvm_asm.h

@@ -70,7 +70,10 @@ extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
 extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high);
 
-extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+/* no VHE on 32-bit :( */
+static inline int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { BUG(); return 0; }
+
+extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu);
 
 extern void __init_stage2_translation(void);
 

arch/arm/include/asm/kvm_emulate.h

@@ -41,7 +41,17 @@ static inline unsigned long *vcpu_reg32(struct kvm_vcpu *vcpu, u8 reg_num)
 	return vcpu_reg(vcpu, reg_num);
 }
 
-unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);
+unsigned long *__vcpu_spsr(struct kvm_vcpu *vcpu);
+
+static inline unsigned long vpcu_read_spsr(struct kvm_vcpu *vcpu)
+{
+	return *__vcpu_spsr(vcpu);
+}
+
+static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
+{
+	*__vcpu_spsr(vcpu) = v;
+}
 
 static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu,
 					 u8 reg_num)
@@ -92,14 +102,9 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 	vcpu->arch.hcr = HCR_GUEST_MASK;
 }
 
-static inline unsigned long vcpu_get_hcr(const struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.hcr;
-}
-
-static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
+static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr = hcr;
+	return (unsigned long *)&vcpu->arch.hcr;
 }
 
 static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)

arch/arm/include/asm/kvm_host.h

@@ -155,9 +155,6 @@ struct kvm_vcpu_arch {
 	/* HYP trapping configuration */
 	u32 hcr;
 
-	/* Interrupt related fields */
-	u32 irq_lines;		/* IRQ and FIQ levels */
-
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
@@ -315,4 +312,7 @@ static inline bool kvm_arm_harden_branch_predictor(void)
 	return false;
 }
 
+static inline void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu) {}
+static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {}
+
 #endif /* __ARM_KVM_HOST_H__ */

arch/arm/include/asm/kvm_hyp.h

@@ -110,6 +110,10 @@ void __sysreg_restore_state(struct kvm_cpu_context *ctxt);
 
 void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
 void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
+void __vgic_v3_activate_traps(struct kvm_vcpu *vcpu);
+void __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu);
+void __vgic_v3_save_aprs(struct kvm_vcpu *vcpu);
+void __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu);
 
 asmlinkage void __vfp_save_state(struct vfp_hard_struct *vfp);
 asmlinkage void __vfp_restore_state(struct vfp_hard_struct *vfp);

arch/arm/include/asm/kvm_mmu.h

@@ -28,6 +28,13 @@
  */
 #define kern_hyp_va(kva)	(kva)
 
+/* Contrary to arm64, there is no need to generate a PC-relative address */
+#define hyp_symbol_addr(s)						\
+	({								\
+		typeof(s) *addr = &(s);					\
+		addr;							\
+	})
+
 /*
  * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
  */
@@ -42,8 +49,15 @@
 #include <asm/pgalloc.h>
 #include <asm/stage2_pgtable.h>
 
+/* Ensure compatibility with arm64 */
+#define VA_BITS			32
+
 int create_hyp_mappings(void *from, void *to, pgprot_t prot);
-int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
+int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
+			   void __iomem **kaddr,
+			   void __iomem **haddr);
+int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
+			     void **haddr);
 void free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);

arch/arm/include/uapi/asm/kvm.h

@@ -135,6 +135,15 @@ struct kvm_arch_memory_slot {
 #define KVM_REG_ARM_CRM_SHIFT		7
 #define KVM_REG_ARM_32_CRN_MASK		0x0000000000007800
 #define KVM_REG_ARM_32_CRN_SHIFT	11
+/*
+ * For KVM currently all guest registers are nonsecure, but we reserve a bit
+ * in the encoding to distinguish secure from nonsecure for AArch32 system
+ * registers that are banked by security. This is 1 for the secure banked
+ * register, and 0 for the nonsecure banked register or if the register is
+ * not banked by security.
+ */
+#define KVM_REG_ARM_SECURE_MASK	0x0000000010000000
+#define KVM_REG_ARM_SECURE_SHIFT	28
 
 #define ARM_CP15_REG_SHIFT_MASK(x,n) \
 	(((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)