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

Pull kvm updates from Paolo Bonzini:
 "The first batch of KVM patches, mostly covering x86.

  ARM:

   - Account stage2 page table allocations in memory stats

  x86:

   - Account EPT/NPT arm64 page table allocations in memory stats

   - Tracepoint cleanups/fixes for nested VM-Enter and emulated MSR
     accesses

   - Drop eVMCS controls filtering for KVM on Hyper-V, all known
     versions of Hyper-V now support eVMCS fields associated with
     features that are enumerated to the guest

   - Use KVM's sanitized VMCS config as the basis for the values of
     nested VMX capabilities MSRs

   - A myriad event/exception fixes and cleanups. Most notably, pending
     exceptions morph into VM-Exits earlier, as soon as the exception is
     queued, instead of waiting until the next vmentry. This fixed a
     longstanding issue where the exceptions would incorrecly become
     double-faults instead of triggering a vmexit; the common case of
     page-fault vmexits had a special workaround, but now it's fixed for
     good

   - A handful of fixes for memory leaks in error paths

   - Cleanups for VMREAD trampoline and VMX's VM-Exit assembly flow

   - Never write to memory from non-sleepable kvm_vcpu_check_block()

   - Selftests refinements and cleanups

   - Misc typo cleanups

  Generic:

   - remove KVM_REQ_UNHALT"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (94 commits)
  KVM: remove KVM_REQ_UNHALT
  KVM: mips, x86: do not rely on KVM_REQ_UNHALT
  KVM: x86: never write to memory from kvm_vcpu_check_block()
  KVM: x86: Don't snapshot pending INIT/SIPI prior to checking nested events
  KVM: nVMX: Make event request on VMXOFF iff INIT/SIPI is pending
  KVM: nVMX: Make an event request if INIT or SIPI is pending on VM-Enter
  KVM: SVM: Make an event request if INIT or SIPI is pending when GIF is set
  KVM: x86: lapic does not have to process INIT if it is blocked
  KVM: x86: Rename kvm_apic_has_events() to make it INIT/SIPI specific
  KVM: x86: Rename and expose helper to detect if INIT/SIPI are allowed
  KVM: nVMX: Make an event request when pending an MTF nested VM-Exit
  KVM: x86: make vendor code check for all nested events
  mailmap: Update Oliver's email address
  KVM: x86: Allow force_emulation_prefix to be written without a reload
  KVM: selftests: Add an x86-only test to verify nested exception queueing
  KVM: selftests: Use uapi header to get VMX and SVM exit reasons/codes
  KVM: x86: Rename inject_pending_events() to kvm_check_and_inject_events()
  KVM: VMX: Update MTF and ICEBP comments to document KVM's subtle behavior
  KVM: x86: Treat pending TRIPLE_FAULT requests as pending exceptions
  KVM: x86: Morph pending exceptions to pending VM-Exits at queue time
  ...

3 files changed, 42 insertions, 21 deletions

diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 0a9407dc0859..3089ec352743 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -138,6 +138,9 @@
 #define HV_X64_NESTED_GUEST_MAPPING_FLUSH		BIT(18)
 #define HV_X64_NESTED_MSR_BITMAP			BIT(19)
 
+/* Nested features #2. These are HYPERV_CPUID_NESTED_FEATURES.EBX bits. */
+#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL		BIT(0)
+
 /*
  * This is specific to AMD and specifies that enlightened TLB flush is
  * supported. If guest opts in to this feature, ASID invalidations only
@@ -546,7 +549,7 @@ struct hv_enlightened_vmcs {
 	u64 guest_rip;
 
 	u32 hv_clean_fields;
-	u32 hv_padding_32;
+	u32 padding32_1;
 	u32 hv_synthetic_controls;
 	struct {
 		u32 nested_flush_hypercall:1;
@@ -554,14 +557,25 @@ struct hv_enlightened_vmcs {
 		u32 reserved:30;
 	}  __packed hv_enlightenments_control;
 	u32 hv_vp_id;
-
+	u32 padding32_2;
 	u64 hv_vm_id;
 	u64 partition_assist_page;
 	u64 padding64_4[4];
 	u64 guest_bndcfgs;
-	u64 padding64_5[7];
+	u64 guest_ia32_perf_global_ctrl;
+	u64 guest_ia32_s_cet;
+	u64 guest_ssp;
+	u64 guest_ia32_int_ssp_table_addr;
+	u64 guest_ia32_lbr_ctl;
+	u64 padding64_5[2];
 	u64 xss_exit_bitmap;
-	u64 padding64_6[7];
+	u64 encls_exiting_bitmap;
+	u64 host_ia32_perf_global_ctrl;
+	u64 tsc_multiplier;
+	u64 host_ia32_s_cet;
+	u64 host_ssp;
+	u64 host_ia32_int_ssp_table_addr;
+	u64 padding64_6;
 } __packed;
 
 #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE			0
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 51f777071584..82ba4a564e58 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -67,7 +67,7 @@ KVM_X86_OP(get_interrupt_shadow)
 KVM_X86_OP(patch_hypercall)
 KVM_X86_OP(inject_irq)
 KVM_X86_OP(inject_nmi)
-KVM_X86_OP(queue_exception)
+KVM_X86_OP(inject_exception)
 KVM_X86_OP(cancel_injection)
 KVM_X86_OP(interrupt_allowed)
 KVM_X86_OP(nmi_allowed)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index aa381ab69a19..61b9dd34d333 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -615,6 +615,8 @@ struct kvm_vcpu_hv {
 		u32 enlightenments_eax; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */
 		u32 enlightenments_ebx; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EBX */
 		u32 syndbg_cap_eax; /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */
+		u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */
+		u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */
 	} cpuid_cache;
 };
 
@@ -639,6 +641,16 @@ struct kvm_vcpu_xen {
 	struct timer_list poll_timer;
 };
 
+struct kvm_queued_exception {
+	bool pending;
+	bool injected;
+	bool has_error_code;
+	u8 vector;
+	u32 error_code;
+	unsigned long payload;
+	bool has_payload;
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through
@@ -738,16 +750,12 @@ struct kvm_vcpu_arch {
 
 	u8 event_exit_inst_len;
 
-	struct kvm_queued_exception {
-		bool pending;
-		bool injected;
-		bool has_error_code;
-		u8 nr;
-		u32 error_code;
-		unsigned long payload;
-		bool has_payload;
-		u8 nested_apf;
-	} exception;
+	bool exception_from_userspace;
+
+	/* Exceptions to be injected to the guest. */
+	struct kvm_queued_exception exception;
+	/* Exception VM-Exits to be synthesized to L1. */
+	struct kvm_queued_exception exception_vmexit;
 
 	struct kvm_queued_interrupt {
 		bool injected;
@@ -858,7 +866,6 @@ struct kvm_vcpu_arch {
 		u32 id;
 		bool send_user_only;
 		u32 host_apf_flags;
-		unsigned long nested_apf_token;
 		bool delivery_as_pf_vmexit;
 		bool pageready_pending;
 	} apf;
@@ -1524,7 +1531,7 @@ struct kvm_x86_ops {
 				unsigned char *hypercall_addr);
 	void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected);
 	void (*inject_nmi)(struct kvm_vcpu *vcpu);
-	void (*queue_exception)(struct kvm_vcpu *vcpu);
+	void (*inject_exception)(struct kvm_vcpu *vcpu);
 	void (*cancel_injection)(struct kvm_vcpu *vcpu);
 	int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
 	int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
@@ -1634,10 +1641,10 @@ struct kvm_x86_ops {
 
 struct kvm_x86_nested_ops {
 	void (*leave_nested)(struct kvm_vcpu *vcpu);
+	bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector,
+				    u32 error_code);
 	int (*check_events)(struct kvm_vcpu *vcpu);
-	bool (*handle_page_fault_workaround)(struct kvm_vcpu *vcpu,
-					     struct x86_exception *fault);
-	bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
+	bool (*has_events)(struct kvm_vcpu *vcpu);
 	void (*triple_fault)(struct kvm_vcpu *vcpu);
 	int (*get_state)(struct kvm_vcpu *vcpu,
 			 struct kvm_nested_state __user *user_kvm_nested_state,
@@ -1863,7 +1870,7 @@ void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long pay
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
-bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
+void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
 				    struct x86_exception *fault);
 bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
 bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr);