Merge tag 'kvm-x86-misc-6.14' of https://github.com/kvm-x86/linux into HEAD

KVM x86 misc changes for 6.14:

 - Overhaul KVM's CPUID feature infrastructure to track all vCPU capabilities
   instead of just those where KVM needs to manage state and/or explicitly
   enable the feature in hardware.  Along the way, refactor the code to make
   it easier to add features, and to make it more self-documenting how KVM
   is handling each feature.

 - Rework KVM's handling of VM-Exits during event vectoring; this plugs holes
   where KVM unintentionally puts the vCPU into infinite loops in some scenarios
   (e.g. if emulation is triggered by the exit), and brings parity between VMX
   and SVM.

 - Add pending request and interrupt injection information to the kvm_exit and
   kvm_entry tracepoints respectively.

 - Fix a relatively benign flaw where KVM would end up redoing RDPKRU when
   loading guest/host PKRU, due to a refactoring of the kernel helpers that
   didn't account for KVM's pre-checking of the need to do WRPKRU.

Author: bonzini

Documentation/virt/kvm/api.rst

@@ -1825,15 +1825,18 @@ emulate them efficiently. The fields in each entry are defined as follows:
          the values returned by the cpuid instruction for
          this function/index combination
 
-The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
-as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
-support.  Instead it is reported via::
+x2APIC (CPUID leaf 1, ecx[21) and TSC deadline timer (CPUID leaf 1, ecx[24])
+may be returned as true, but they depend on KVM_CREATE_IRQCHIP for in-kernel
+emulation of the local APIC.  TSC deadline timer support is also reported via::
 
   ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
 
 if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
 feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
 
+Enabling x2APIC in KVM_SET_CPUID2 requires KVM_CREATE_IRQCHIP as KVM doesn't
+support forwarding x2APIC MSR accesses to userspace, i.e. KVM does not support
+emulating x2APIC in userspace.
 
 4.47 KVM_PPC_GET_PVINFO
 -----------------------
@@ -7673,6 +7676,7 @@ branch to guests' 0x200 interrupt vector.
 :Architectures: x86
 :Parameters: args[0] defines which exits are disabled
 :Returns: 0 on success, -EINVAL when args[0] contains invalid exits
+          or if any vCPUs have already been created
 
 Valid bits in args[0] are::
 

arch/x86/include/asm/kvm-x86-ops.h

@@ -99,6 +99,7 @@ KVM_X86_OP(get_l2_tsc_multiplier)
 KVM_X86_OP(write_tsc_offset)
 KVM_X86_OP(write_tsc_multiplier)
 KVM_X86_OP(get_exit_info)
+KVM_X86_OP(get_entry_info)
 KVM_X86_OP(check_intercept)
 KVM_X86_OP(handle_exit_irqoff)
 KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging)

arch/x86/include/asm/kvm_host.h

@@ -739,6 +739,23 @@ struct kvm_queued_exception {
 	bool has_payload;
 };
 
+/*
+ * Hardware-defined CPUID leafs that are either scattered by the kernel or are
+ * unknown to the kernel, but need to be directly used by KVM.  Note, these
+ * word values conflict with the kernel's "bug" caps, but KVM doesn't use those.
+ */
+enum kvm_only_cpuid_leafs {
+	CPUID_12_EAX	 = NCAPINTS,
+	CPUID_7_1_EDX,
+	CPUID_8000_0007_EDX,
+	CPUID_8000_0022_EAX,
+	CPUID_7_2_EDX,
+	CPUID_24_0_EBX,
+	NR_KVM_CPU_CAPS,
+
+	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through
@@ -854,27 +871,23 @@ struct kvm_vcpu_arch {
 
 	int cpuid_nent;
 	struct kvm_cpuid_entry2 *cpuid_entries;
-	struct kvm_hypervisor_cpuid kvm_cpuid;
 	bool is_amd_compatible;
 
 	/*
-	 * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly
-	 * when "struct kvm_vcpu_arch" is no longer defined in an
-	 * arch/x86/include/asm header.  The max is mostly arbitrary, i.e.
-	 * can be increased as necessary.
-	 */
-#define KVM_MAX_NR_GOVERNED_FEATURES BITS_PER_LONG
-
-	/*
-	 * Track whether or not the guest is allowed to use features that are
-	 * governed by KVM, where "governed" means KVM needs to manage state
-	 * and/or explicitly enable the feature in hardware.  Typically, but
-	 * not always, governed features can be used by the guest if and only
-	 * if both KVM and userspace want to expose the feature to the guest.
+	 * cpu_caps holds the effective guest capabilities, i.e. the features
+	 * the vCPU is allowed to use.  Typically, but not always, features can
+	 * be used by the guest if and only if both KVM and userspace want to
+	 * expose the feature to the guest.
+	 *
+	 * A common exception is for virtualization holes, i.e. when KVM can't
+	 * prevent the guest from using a feature, in which case the vCPU "has"
+	 * the feature regardless of what KVM or userspace desires.
+	 *
+	 * Note, features that don't require KVM involvement in any way are
+	 * NOT enforced/sanitized by KVM, i.e. are taken verbatim from the
+	 * guest CPUID provided by userspace.
 	 */
-	struct {
-		DECLARE_BITMAP(enabled, KVM_MAX_NR_GOVERNED_FEATURES);
-	} governed_features;
+	u32 cpu_caps[NR_KVM_CPU_CAPS];
 
 	u64 reserved_gpa_bits;
 	int maxphyaddr;
@@ -1756,12 +1769,15 @@ struct kvm_x86_ops {
 	void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu);
 
 	/*
-	 * Retrieve somewhat arbitrary exit information.  Intended to
+	 * Retrieve somewhat arbitrary exit/entry information.  Intended to
 	 * be used only from within tracepoints or error paths.
 	 */
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u32 *reason,
 			      u64 *info1, u64 *info2,
-			      u32 *exit_int_info, u32 *exit_int_info_err_code);
+			      u32 *intr_info, u32 *error_code);
+
+	void (*get_entry_info)(struct kvm_vcpu *vcpu,
+			       u32 *intr_info, u32 *error_code);
 
 	int (*check_intercept)(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
@@ -2018,8 +2034,8 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
  *			VMware backdoor emulation handles select instructions
  *			and reinjects the #GP for all other cases.
  *
- * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which
- *		 case the CR2/GPA value pass on the stack is valid.
+ * EMULTYPE_PF - Set when an intercepted #PF triggers the emulation, in which case
+ *		 the CR2/GPA value pass on the stack is valid.
  *
  * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility
  *				 state and inject single-step #DBs after skipping
@@ -2054,13 +2070,20 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
 #define EMULTYPE_COMPLETE_USER_EXIT (1 << 7)
 #define EMULTYPE_WRITE_PF_TO_SP	    (1 << 8)
 
+static inline bool kvm_can_emulate_event_vectoring(int emul_type)
+{
+	return !(emul_type & EMULTYPE_PF);
+}
+
 int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type);
 int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 					void *insn, int insn_len);
 void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu,
 					  u64 *data, u8 ndata);
 void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu);
 
+void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa);
+
 void kvm_enable_efer_bits(u64);
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
 int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data);