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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Move the arch-specific code into arch/arm64/kvm

   - Start the post-32bit cleanup

   - Cherry-pick a few non-invasive pre-NV patches

  x86:
   - Rework of TLB flushing

   - Rework of event injection, especially with respect to nested
     virtualization

   - Nested AMD event injection facelift, building on the rework of
     generic code and fixing a lot of corner cases

   - Nested AMD live migration support

   - Optimization for TSC deadline MSR writes and IPIs

   - Various cleanups

   - Asynchronous page fault cleanups (from tglx, common topic branch
     with tip tree)

   - Interrupt-based delivery of asynchronous "page ready" events (host
     side)

   - Hyper-V MSRs and hypercalls for guest debugging

   - VMX preemption timer fixes

  s390:
   - Cleanups

  Generic:
   - switch vCPU thread wakeup from swait to rcuwait

  The other architectures, and the guest side of the asynchronous page
  fault work, will come next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (256 commits)
  KVM: selftests: fix rdtsc() for vmx_tsc_adjust_test
  KVM: check userspace_addr for all memslots
  KVM: selftests: update hyperv_cpuid with SynDBG tests
  x86/kvm/hyper-v: Add support for synthetic debugger via hypercalls
  x86/kvm/hyper-v: enable hypercalls regardless of hypercall page
  x86/kvm/hyper-v: Add support for synthetic debugger interface
  x86/hyper-v: Add synthetic debugger definitions
  KVM: selftests: VMX preemption timer migration test
  KVM: nVMX: Fix VMX preemption timer migration
  x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit
  KVM: x86/pmu: Support full width counting
  KVM: x86/pmu: Tweak kvm_pmu_get_msr to pass 'struct msr_data' in
  KVM: x86: announce KVM_FEATURE_ASYNC_PF_INT
  KVM: x86: acknowledgment mechanism for async pf page ready notifications
  KVM: x86: interrupt based APF 'page ready' event delivery
  KVM: introduce kvm_read_guest_offset_cached()
  KVM: rename kvm_arch_can_inject_async_page_present() to kvm_arch_can_dequeue_async_page_present()
  KVM: x86: extend struct kvm_vcpu_pv_apf_data with token info
  Revert "KVM: async_pf: Fix #DF due to inject "Page not Present" and "Page Ready" exceptions simultaneously"
  KVM: VMX: Replace zero-length array with flexible-array
  ...

Author: torvalds

Documentation/virt/kvm/api.rst

@@ -4336,9 +4336,13 @@ Errors:
   #define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE	0x00000001
   #define KVM_STATE_NESTED_VMX_SMM_VMXON	0x00000002
 
+#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001
+
   struct kvm_vmx_nested_state_hdr {
+	__u32 flags;
 	__u64 vmxon_pa;
 	__u64 vmcs12_pa;
+	__u64 preemption_timer_deadline;
 
 	struct {
 		__u16 flags;
@@ -5068,10 +5072,13 @@ EOI was received.
 		struct kvm_hyperv_exit {
   #define KVM_EXIT_HYPERV_SYNIC          1
   #define KVM_EXIT_HYPERV_HCALL          2
+  #define KVM_EXIT_HYPERV_SYNDBG         3
 			__u32 type;
+			__u32 pad1;
 			union {
 				struct {
 					__u32 msr;
+					__u32 pad2;
 					__u64 control;
 					__u64 evt_page;
 					__u64 msg_page;
@@ -5081,6 +5088,15 @@ EOI was received.
 					__u64 result;
 					__u64 params[2];
 				} hcall;
+				struct {
+					__u32 msr;
+					__u32 pad2;
+					__u64 control;
+					__u64 status;
+					__u64 send_page;
+					__u64 recv_page;
+					__u64 pending_page;
+				} syndbg;
 			} u;
 		};
 		/* KVM_EXIT_HYPERV */
@@ -5097,6 +5113,12 @@ Hyper-V SynIC state change. Notification is used to remap SynIC
 event/message pages and to enable/disable SynIC messages/events processing
 in userspace.
 
+	- KVM_EXIT_HYPERV_SYNDBG -- synchronously notify user-space about
+
+Hyper-V Synthetic debugger state change. Notification is used to either update
+the pending_page location or to send a control command (send the buffer located
+in send_page or recv a buffer to recv_page).
+
 ::
 
 		/* KVM_EXIT_ARM_NISV */
@@ -5779,7 +5801,7 @@ will be initialized to 1 when created.  This also improves performance because
 dirty logging can be enabled gradually in small chunks on the first call
 to KVM_CLEAR_DIRTY_LOG.  KVM_DIRTY_LOG_INITIALLY_SET depends on
 KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (it is also only available on
-x86 for now).
+x86 and arm64 for now).
 
 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name
 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make
@@ -5804,6 +5826,23 @@ If present, this capability can be enabled for a VM, meaning that KVM
 will allow the transition to secure guest mode.  Otherwise KVM will
 veto the transition.
 
+7.20 KVM_CAP_HALT_POLL
+----------------------
+
+:Architectures: all
+:Target: VM
+:Parameters: args[0] is the maximum poll time in nanoseconds
+:Returns: 0 on success; -1 on error
+
+This capability overrides the kvm module parameter halt_poll_ns for the
+target VM.
+
+VCPU polling allows a VCPU to poll for wakeup events instead of immediately
+scheduling during guest halts. The maximum time a VCPU can spend polling is
+controlled by the kvm module parameter halt_poll_ns. This capability allows
+the maximum halt time to specified on a per-VM basis, effectively overriding
+the module parameter for the target VM.
+
 8. Other capabilities.
 ======================
 

Documentation/virt/kvm/cpuid.rst

@@ -50,8 +50,8 @@ KVM_FEATURE_NOP_IO_DELAY          1           not necessary to perform delays
 KVM_FEATURE_MMU_OP                2           deprecated
 
 KVM_FEATURE_CLOCKSOURCE2          3           kvmclock available at msrs
-
                                               0x4b564d00 and 0x4b564d01
+
 KVM_FEATURE_ASYNC_PF              4           async pf can be enabled by
                                               writing to msr 0x4b564d02
 
@@ -86,6 +86,12 @@ KVM_FEATURE_PV_SCHED_YIELD        13          guest checks this feature bit
                                               before using paravirtualized
                                               sched yield.
 
+KVM_FEATURE_ASYNC_PF_INT          14          guest checks this feature bit
+                                              before using the second async
+                                              pf control msr 0x4b564d06 and
+                                              async pf acknowledgment msr
+                                              0x4b564d07.
+
 KVM_FEATURE_CLOCSOURCE_STABLE_BIT 24          host will warn if no guest-side
                                               per-cpu warps are expeced in
                                               kvmclock

Documentation/virt/kvm/msr.rst

@@ -190,41 +190,72 @@ MSR_KVM_ASYNC_PF_EN:
 	0x4b564d02
 
 data:
-	Bits 63-6 hold 64-byte aligned physical address of a
-	64 byte memory area which must be in guest RAM and must be
-	zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1
-	when asynchronous page faults are enabled on the vcpu 0 when
-	disabled. Bit 1 is 1 if asynchronous page faults can be injected
-	when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults
-	are delivered to L1 as #PF vmexits.  Bit 2 can be set only if
-	KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID.
-
-	First 4 byte of 64 byte memory location will be written to by
-	the hypervisor at the time of asynchronous page fault (APF)
-	injection to indicate type of asynchronous page fault. Value
-	of 1 means that the page referred to by the page fault is not
-	present. Value 2 means that the page is now available. Disabling
-	interrupt inhibits APFs. Guest must not enable interrupt
-	before the reason is read, or it may be overwritten by another
-	APF. Since APF uses the same exception vector as regular page
-	fault guest must reset the reason to 0 before it does
-	something that can generate normal page fault.  If during page
-	fault APF reason is 0 it means that this is regular page
-	fault.
-
-	During delivery of type 1 APF cr2 contains a token that will
-	be used to notify a guest when missing page becomes
-	available. When page becomes available type 2 APF is sent with
-	cr2 set to the token associated with the page. There is special
-	kind of token 0xffffffff which tells vcpu that it should wake
-	up all processes waiting for APFs and no individual type 2 APFs
-	will be sent.
+	Asynchronous page fault (APF) control MSR.
+
+	Bits 63-6 hold 64-byte aligned physical address of a 64 byte memory area
+	which must be in guest RAM and must be zeroed. This memory is expected
+	to hold a copy of the following structure::
+
+	  struct kvm_vcpu_pv_apf_data {
+		/* Used for 'page not present' events delivered via #PF */
+		__u32 flags;
+
+		/* Used for 'page ready' events delivered via interrupt notification */
+		__u32 token;
+
+		__u8 pad[56];
+		__u32 enabled;
+	  };
+
+	Bits 5-4 of the MSR are reserved and should be zero. Bit 0 is set to 1
+	when asynchronous page faults are enabled on the vcpu, 0 when disabled.
+	Bit 1 is 1 if asynchronous page faults can be injected when vcpu is in
+	cpl == 0. Bit 2 is 1 if asynchronous page faults are delivered to L1 as
+	#PF vmexits.  Bit 2 can be set only if KVM_FEATURE_ASYNC_PF_VMEXIT is
+	present in CPUID. Bit 3 enables interrupt based delivery of 'page ready'
+	events. Bit 3 can only be set if KVM_FEATURE_ASYNC_PF_INT is present in
+	CPUID.
+
+	'Page not present' events are currently always delivered as synthetic
+	#PF exception. During delivery of these events APF CR2 register contains
+	a token that will be used to notify the guest when missing page becomes
+	available. Also, to make it possible to distinguish between real #PF and
+	APF, first 4 bytes of 64 byte memory location ('flags') will be written
+	to by the hypervisor at the time of injection. Only first bit of 'flags'
+	is currently supported, when set, it indicates that the guest is dealing
+	with asynchronous 'page not present' event. If during a page fault APF
+	'flags' is '0' it means that this is regular page fault. Guest is
+	supposed to clear 'flags' when it is done handling #PF exception so the
+	next event can be delivered.
+
+	Note, since APF 'page not present' events use the same exception vector
+	as regular page fault, guest must reset 'flags' to '0' before it does
+	something that can generate normal page fault.
+
+	Bytes 5-7 of 64 byte memory location ('token') will be written to by the
+	hypervisor at the time of APF 'page ready' event injection. The content
+	of these bytes is a token which was previously delivered as 'page not
+	present' event. The event indicates the page in now available. Guest is
+	supposed to write '0' to 'token' when it is done handling 'page ready'
+	event and to write 1' to MSR_KVM_ASYNC_PF_ACK after clearing the location;
+	writing to the MSR forces KVM to re-scan its queue and deliver the next
+	pending notification.
+
+	Note, MSR_KVM_ASYNC_PF_INT MSR specifying the interrupt vector for 'page
+	ready' APF delivery needs to be written to before enabling APF mechanism
+	in MSR_KVM_ASYNC_PF_EN or interrupt #0 can get injected. The MSR is
+	available if KVM_FEATURE_ASYNC_PF_INT is present in CPUID.
+
+	Note, previously, 'page ready' events were delivered via the same #PF
+	exception as 'page not present' events but this is now deprecated. If
+	bit 3 (interrupt based delivery) is not set APF events are not delivered.
 
 	If APF is disabled while there are outstanding APFs, they will
 	not be delivered.
 
-	Currently type 2 APF will be always delivered on the same vcpu as
-	type 1 was, but guest should not rely on that.
+	Currently 'page ready' APF events will be always delivered on the
+	same vcpu as 'page not present' event was, but guest should not rely on
+	that.
 
 MSR_KVM_STEAL_TIME:
 	0x4b564d03
@@ -319,3 +350,29 @@ data:
 
 	KVM guests can request the host not to poll on HLT, for example if
 	they are performing polling themselves.
+
+MSR_KVM_ASYNC_PF_INT:
+	0x4b564d06
+
+data:
+	Second asynchronous page fault (APF) control MSR.
+
+	Bits 0-7: APIC vector for delivery of 'page ready' APF events.
+	Bits 8-63: Reserved
+
+	Interrupt vector for asynchnonous 'page ready' notifications delivery.
+	The vector has to be set up before asynchronous page fault mechanism
+	is enabled in MSR_KVM_ASYNC_PF_EN.  The MSR is only available if
+	KVM_FEATURE_ASYNC_PF_INT is present in CPUID.
+
+MSR_KVM_ASYNC_PF_ACK:
+	0x4b564d07
+
+data:
+	Asynchronous page fault (APF) acknowledgment.
+
+	When the guest is done processing 'page ready' APF event and 'token'
+	field in 'struct kvm_vcpu_pv_apf_data' is cleared it is supposed to
+	write '1' to bit 0 of the MSR, this causes the host to re-scan its queue
+	and check if there are more notifications pending. The MSR is available
+	if KVM_FEATURE_ASYNC_PF_INT is present in CPUID.

Documentation/virt/kvm/nested-vmx.rst

@@ -116,10 +116,7 @@ struct shadow_vmcs is ever changed.
 		natural_width cr4_guest_host_mask;
 		natural_width cr0_read_shadow;
 		natural_width cr4_read_shadow;
-		natural_width cr3_target_value0;
-		natural_width cr3_target_value1;
-		natural_width cr3_target_value2;
-		natural_width cr3_target_value3;
+		natural_width dead_space[4]; /* Last remnants of cr3_target_value[0-3]. */
 		natural_width exit_qualification;
 		natural_width guest_linear_address;
 		natural_width guest_cr0;

MAINTAINERS

@@ -9368,7 +9368,6 @@ F:	arch/arm64/include/asm/kvm*
 F:	arch/arm64/include/uapi/asm/kvm*
 F:	arch/arm64/kvm/
 F:	include/kvm/arm_*
-F:	virt/kvm/arm/
 
 KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)
 L:	[email protected]

arch/arm64/include/asm/kvm_asm.h

@@ -64,12 +64,14 @@ extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
-extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high);
+extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
 extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu);
 
 extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu);
 
+extern void __kvm_enable_ssbs(void);
+
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
 extern u64 __vgic_v3_read_vmcr(void);
 extern void __vgic_v3_write_vmcr(u32 vmcr);

arch/arm64/include/asm/kvm_host.h

@@ -46,6 +46,9 @@
 #define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 #define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
 
+#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
+				     KVM_DIRTY_LOG_INITIALLY_SET)
+
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
 extern unsigned int kvm_sve_max_vl;
@@ -112,12 +115,8 @@ struct kvm_vcpu_fault_info {
 	u64 disr_el1;		/* Deferred [SError] Status Register */
 };
 
-/*
- * 0 is reserved as an invalid value.
- * Order should be kept in sync with the save/restore code.
- */
 enum vcpu_sysreg {
-	__INVALID_SYSREG__,
+	__INVALID_SYSREG__,   /* 0 is reserved as an invalid value */
 	MPIDR_EL1,	/* MultiProcessor Affinity Register */
 	CSSELR_EL1,	/* Cache Size Selection Register */
 	SCTLR_EL1,	/* System Control Register */
@@ -415,6 +414,8 @@ struct kvm_vm_stat {
 struct kvm_vcpu_stat {
 	u64 halt_successful_poll;
 	u64 halt_attempted_poll;
+	u64 halt_poll_success_ns;
+	u64 halt_poll_fail_ns;
 	u64 halt_poll_invalid;
 	u64 halt_wakeup;
 	u64 hvc_exit_stat;
@@ -530,39 +531,6 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
 	cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr();
 }
 
-void __kvm_enable_ssbs(void);
-
-static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
-				       unsigned long hyp_stack_ptr,
-				       unsigned long vector_ptr)
-{
-	/*
-	 * Calculate the raw per-cpu offset without a translation from the
-	 * kernel's mapping to the linear mapping, and store it in tpidr_el2
-	 * so that we can use adr_l to access per-cpu variables in EL2.
-	 */
-	u64 tpidr_el2 = ((u64)this_cpu_ptr(&kvm_host_data) -
-			 (u64)kvm_ksym_ref(kvm_host_data));
-
-	/*
-	 * Call initialization code, and switch to the full blown HYP code.
-	 * If the cpucaps haven't been finalized yet, something has gone very
-	 * wrong, and hyp will crash and burn when it uses any
-	 * cpus_have_const_cap() wrapper.
-	 */
-	BUG_ON(!system_capabilities_finalized());
-	__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
-
-	/*
-	 * Disabling SSBD on a non-VHE system requires us to enable SSBS
-	 * at EL2.
-	 */
-	if (!has_vhe() && this_cpu_has_cap(ARM64_SSBS) &&
-	    arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
-		kvm_call_hyp(__kvm_enable_ssbs);
-	}
-}
-
 static inline bool kvm_arch_requires_vhe(void)
 {
 	/*
@@ -594,8 +562,6 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
 int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 
-static inline void __cpu_init_stage2(void) {}
-
 /* Guest/host FPSIMD coordination helpers */
 int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);

arch/arm64/include/asm/kvm_hyp.h

@@ -55,12 +55,12 @@
 
 int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
-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);
+void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if);
 int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
 void __timer_enable_traps(struct kvm_vcpu *vcpu);