KVM generic changes for 6.11

- Enable halt poll shrinking by default, as Intel found it to be a clear win.
 
  - Setup empty IRQ routing when creating a VM to avoid having to synchronize
    SRCU when creating a split IRQCHIP on x86.
 
  - Rework the sched_in/out() paths to replace kvm_arch_sched_in() with a flag
    that arch code can use for hooking both sched_in() and sched_out().
 
  - Take the vCPU @id as an "unsigned long" instead of "u32" to avoid
    truncating a bogus value from userspace, e.g. to help userspace detect bugs.
 
  - Mark a vCPU as preempted if and only if it's scheduled out while in the
    KVM_RUN loop, e.g. to avoid marking it preempted and thus writing guest
    memory when retrieving guest state during live migration blackout.
 
  - A few minor cleanups
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEKTobbabEP7vbhhN9OlYIJqCjN/0FAmaRuOYACgkQOlYIJqCj
 N/1UnQ/8CI5Qfr+/0gzYgtWmtEMczGG+rMNpzD3XVqPjJjXcMcBiQnplnzUVLhha
 vlPdYVK7vgmEt003XGzV55mik46LHL+DX/v4hI3HEdblfyCeNLW3fKEWVRB44qJe
 o+YUQwSK42SORUp9oXuQINxhA//U9EnI7CQxlJ8w8wenv5IJKfIGr01DefmfGPAV
 PKm9t6WLcNqvhZMEyy/zmzM3KVPCJL0NcwI97x6sHxFpQYIDtL0E/VexA4AFqMoT
 QK7cSDC/2US41Zvem/r/GzM/ucdF6vb9suzZYBohwhxtVhwJe2CDeYQZvtNKJ1U7
 GOHPaKL6nBWdZCm/yyWbbX2nstY1lHqxhN3JD0X8wqU5rNcwm2b8Vfyav0Ehc7H+
 jVbDTshOx4YJmIgajoKjgM050rdBK59TdfVL+l+AAV5q/TlHocalYtvkEBdGmIDg
 2td9UHSime6sp20vQfczUEz4bgrQsh4l2Fa/qU2jFwLievnBw0AvEaMximkSGMJe
 b8XfjmdTjlOesWAejANKtQolfrq14+1wYw0zZZ8PA+uNVpKdoovmcqSOcaDC9bT8
 GO/NFUvoG+lkcvJcIlo1SSl81SmGLosijwxWfGvFAqsgpR3/3l3dYp0QtztoCNJO
 d3+HnjgYn5o5FwufuTD3eUOXH4AFjG108DH0o25XrIkb2Kymy0o=
 =BalU
 -----END PGP SIGNATURE-----

Merge tag 'kvm-x86-generic-6.11' of https://github.com/kvm-x86/linux into HEAD

KVM generic changes for 6.11

 - Enable halt poll shrinking by default, as Intel found it to be a clear win.

 - Setup empty IRQ routing when creating a VM to avoid having to synchronize
   SRCU when creating a split IRQCHIP on x86.

 - Rework the sched_in/out() paths to replace kvm_arch_sched_in() with a flag
   that arch code can use for hooking both sched_in() and sched_out().

 - Take the vCPU @id as an "unsigned long" instead of "u32" to avoid
   truncating a bogus value from userspace, e.g. to help userspace detect bugs.

 - Mark a vCPU as preempted if and only if it's scheduled out while in the
   KVM_RUN loop, e.g. to avoid marking it preempted and thus writing guest
   memory when retrieving guest state during live migration blackout.

 - A few minor cleanups

Documentation/virt/kvm/api.rst

@@ -7969,10 +7969,10 @@ perform a bulk copy of tags to/from the guest.
 7.29 KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM
 -------------------------------------
 
-Architectures: x86 SEV enabled
+:Architectures: x86 SEV enabled
-Type: vm
+:Type: vm
-Parameters: args[0] is the fd of the source vm
+:Parameters: args[0] is the fd of the source vm
-Returns: 0 on success
+:Returns: 0 on success
 
 This capability enables userspace to migrate the encryption context from the VM
 indicated by the fd to the VM this is called on.

Documentation/virt/kvm/halt-polling.rst

@@ -79,11 +79,11 @@ adjustment of the polling interval.
 Module Parameters
 =================
 
-The kvm module has 3 tuneable module parameters to adjust the global max
+The kvm module has 4 tunable module parameters to adjust the global max polling
-polling interval as well as the rate at which the polling interval is grown and
+interval, the initial value (to grow from 0), and the rate at which the polling
-shrunk. These variables are defined in include/linux/kvm_host.h and as module
+interval is grown and shrunk. These variables are defined in
-parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the
+include/linux/kvm_host.h and as module parameters in virt/kvm/kvm_main.c, or
-powerpc kvm-hv case.
+arch/powerpc/kvm/book3s_hv.c in the powerpc kvm-hv case.
 
 +-----------------------+---------------------------+-------------------------+
 |Module Parameter	|   Description		    |	     Default Value    |
@@ -105,7 +105,7 @@ powerpc kvm-hv case.
 |			| grow_halt_poll_ns()	    |			      |
 |			| function.		    |			      |
 +-----------------------+---------------------------+-------------------------+
-|halt_poll_ns_shrink	| The value by which the    | 0			      |
+|halt_poll_ns_shrink	| The value by which the    | 2			      |
 |			| halt polling interval is  |			      |
 |			| divided in the	    |			      |
 |			| shrink_halt_poll_ns()	    |			      |

arch/arm64/include/asm/kvm_host.h

@@ -1289,7 +1289,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void)
 }
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
 void kvm_arm_init_debug(void);
 void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);

arch/arm64/kvm/arm.c

@@ -1138,7 +1138,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	vcpu_load(vcpu);
 
-	if (run->immediate_exit) {
+	if (!vcpu->wants_to_run) {
 		ret = -EINTR;
 		goto out;
 	}

arch/loongarch/include/asm/kvm_host.h

@@ -274,7 +274,6 @@ static inline bool kvm_is_ifetch_fault(struct kvm_vcpu_arch *arch)
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}

arch/loongarch/kvm/vcpu.c

@@ -1416,7 +1416,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			kvm_complete_iocsr_read(vcpu, run);
 	}
 
-	if (run->immediate_exit)
+	if (!vcpu->wants_to_run)
 		return r;
 
 	/* Clear exit_reason */

arch/mips/include/asm/kvm_host.h

@@ -890,7 +890,6 @@ static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
 					 struct kvm_memory_slot *slot) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 

arch/mips/kvm/mips.c

@@ -436,7 +436,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		vcpu->mmio_needed = 0;
 	}
 
-	if (vcpu->run->immediate_exit)
+	if (!vcpu->wants_to_run)
 		goto out;
 
 	lose_fpu(1);

arch/powerpc/include/asm/kvm_host.h

@@ -897,7 +897,6 @@ struct kvm_vcpu_arch {
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
 static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 

arch/powerpc/kvm/powerpc.c

@@ -1852,7 +1852,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	kvm_sigset_activate(vcpu);
 
-	if (run->immediate_exit)
+	if (!vcpu->wants_to_run)
 		r = -EINTR;
 	else
 		r = kvmppc_vcpu_run(vcpu);

arch/riscv/include/asm/kvm_host.h

@@ -286,7 +286,6 @@ struct kvm_vcpu_arch {
 };
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
 #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
 

arch/riscv/kvm/vcpu.c

@@ -763,7 +763,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		return ret;
 	}
 
-	if (run->immediate_exit) {
+	if (!vcpu->wants_to_run) {
 		kvm_vcpu_srcu_read_unlock(vcpu);
 		return -EINTR;
 	}

arch/s390/include/asm/kvm_host.h

@@ -1045,7 +1045,6 @@ extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc);
 extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc);
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
 					 struct kvm_memory_slot *slot) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}

arch/s390/kvm/kvm-s390.c

@@ -2997,14 +2997,9 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 		break;
 	}
 	case KVM_CREATE_IRQCHIP: {
-		struct kvm_irq_routing_entry routing;
-
 		r = -EINVAL;
-		if (kvm->arch.use_irqchip) {
+		if (kvm->arch.use_irqchip)
-			/* Set up dummy routing. */
+			r = 0;
-			memset(&routing, 0, sizeof(routing));
-			r = kvm_set_irq_routing(kvm, &routing, 0, 0);
-		}
 		break;
 	}
 	case KVM_SET_DEVICE_ATTR: {
@@ -5032,7 +5027,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	if (vcpu->kvm->arch.pv.dumping)
 		return -EINVAL;
 
-	if (kvm_run->immediate_exit)
+	if (!vcpu->wants_to_run)
 		return -EINTR;
 
 	if (kvm_run->kvm_valid_regs & ~KVM_SYNC_S390_VALID_FIELDS ||

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

@@ -103,7 +103,6 @@ KVM_X86_OP(write_tsc_multiplier)
 KVM_X86_OP(get_exit_info)
 KVM_X86_OP(check_intercept)
 KVM_X86_OP(handle_exit_irqoff)
-KVM_X86_OP(sched_in)
 KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging)
 KVM_X86_OP_OPTIONAL(vcpu_blocking)
 KVM_X86_OP_OPTIONAL(vcpu_unblocking)

arch/x86/include/asm/kvm_host.h

@@ -1750,8 +1750,6 @@ struct kvm_x86_ops {
 			       struct x86_exception *exception);
 	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
 
-	void (*sched_in)(struct kvm_vcpu *vcpu, int cpu);
-
 	/*
 	 * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer.  A zero
 	 * value indicates CPU dirty logging is unsupported or disabled.

arch/x86/kvm/irq.h

@@ -106,7 +106,6 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu);
 int apic_has_pending_timer(struct kvm_vcpu *vcpu);
 
 int kvm_setup_default_irq_routing(struct kvm *kvm);
-int kvm_setup_empty_irq_routing(struct kvm *kvm);
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 			     struct kvm_lapic_irq *irq,
 			     struct dest_map *dest_map);

arch/x86/kvm/irq_comm.c

@@ -395,13 +395,6 @@ int kvm_setup_default_irq_routing(struct kvm *kvm)
 				   ARRAY_SIZE(default_routing), 0);
 }
 
-static const struct kvm_irq_routing_entry empty_routing[] = {};
-
-int kvm_setup_empty_irq_routing(struct kvm *kvm)
-{
-	return kvm_set_irq_routing(kvm, empty_routing, 0, 0);
-}
-
 void kvm_arch_post_irq_routing_update(struct kvm *kvm)
 {
 	if (!irqchip_split(kvm))

arch/x86/kvm/pmu.c

@@ -521,9 +521,9 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 	}
 
 	/*
-	 * Unused perf_events are only released if the corresponding MSRs
+	 * Release unused perf_events if the corresponding guest MSRs weren't
-	 * weren't accessed during the last vCPU time slice. kvm_arch_sched_in
+	 * accessed during the last vCPU time slice (need_cleanup is set when
-	 * triggers KVM_REQ_PMU if cleanup is needed.
+	 * the vCPU is scheduled back in).
 	 */
 	if (unlikely(pmu->need_cleanup))
 		kvm_pmu_cleanup(vcpu);

arch/x86/kvm/svm/svm.c

@@ -1554,6 +1554,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
 
+	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
+		shrink_ple_window(vcpu);
+
 	if (sd->current_vmcb != svm->vmcb) {
 		sd->current_vmcb = svm->vmcb;
 
@@ -4607,12 +4610,6 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 		vcpu->arch.at_instruction_boundary = true;
 }
 
-static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
-{
-	if (!kvm_pause_in_guest(vcpu->kvm))
-		shrink_ple_window(vcpu);
-}
-
 static void svm_setup_mce(struct kvm_vcpu *vcpu)
 {
 	/* [63:9] are reserved. */
@@ -5075,8 +5072,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.check_intercept = svm_check_intercept,
 	.handle_exit_irqoff = svm_handle_exit_irqoff,
 
-	.sched_in = svm_sched_in,
-
 	.nested_ops = &svm_nested_ops,
 
 	.deliver_interrupt = svm_deliver_interrupt,

arch/x86/kvm/vmx/main.c

@@ -122,8 +122,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.check_intercept = vmx_check_intercept,
 	.handle_exit_irqoff = vmx_handle_exit_irqoff,
 
-	.sched_in = vmx_sched_in,
-
 	.cpu_dirty_log_size = PML_ENTITY_NUM,
 	.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
 

arch/x86/kvm/vmx/vmx.c

@@ -1411,6 +1411,38 @@ static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
 }
 #endif
 
+static void grow_ple_window(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned int old = vmx->ple_window;
+
+	vmx->ple_window = __grow_ple_window(old, ple_window,
+					    ple_window_grow,
+					    ple_window_max);
+
+	if (vmx->ple_window != old) {
+		vmx->ple_window_dirty = true;
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    vmx->ple_window, old);
+	}
+}
+
+static void shrink_ple_window(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned int old = vmx->ple_window;
+
+	vmx->ple_window = __shrink_ple_window(old, ple_window,
+					      ple_window_shrink,
+					      ple_window);
+
+	if (vmx->ple_window != old) {
+		vmx->ple_window_dirty = true;
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    vmx->ple_window, old);
+	}
+}
+
 void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 			struct loaded_vmcs *buddy)
 {
@@ -1486,6 +1518,9 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
+		shrink_ple_window(vcpu);
+
 	vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
@@ -5897,38 +5932,6 @@ int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static void grow_ple_window(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned int old = vmx->ple_window;
-
-	vmx->ple_window = __grow_ple_window(old, ple_window,
-					    ple_window_grow,
-					    ple_window_max);
-
-	if (vmx->ple_window != old) {
-		vmx->ple_window_dirty = true;
-		trace_kvm_ple_window_update(vcpu->vcpu_id,
-					    vmx->ple_window, old);
-	}
-}
-
-static void shrink_ple_window(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned int old = vmx->ple_window;
-
-	vmx->ple_window = __shrink_ple_window(old, ple_window,
-					      ple_window_shrink,
-					      ple_window);
-
-	if (vmx->ple_window != old) {
-		vmx->ple_window_dirty = true;
-		trace_kvm_ple_window_update(vcpu->vcpu_id,
-					    vmx->ple_window, old);
-	}
-}
-
 /*
  * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
  * exiting, so only get here on cpu with PAUSE-Loop-Exiting.
@@ -6677,9 +6680,10 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 		bool flush_l1d;
 
 		/*
-		 * Clear the per-vcpu flush bit, it gets set again
+		 * Clear the per-vcpu flush bit, it gets set again if the vCPU
-		 * either from vcpu_run() or from one of the unsafe
+		 * is reloaded, i.e. if the vCPU is scheduled out or if KVM
-		 * VMEXIT handlers.
+		 * exits to userspace, or if KVM reaches one of the unsafe
+		 * VMEXIT handlers, e.g. if KVM calls into the emulator.
 		 */
 		flush_l1d = vcpu->arch.l1tf_flush_l1d;
 		vcpu->arch.l1tf_flush_l1d = false;
@@ -8179,12 +8183,6 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
 }
 #endif
 
-void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
-{
-	if (!kvm_pause_in_guest(vcpu->kvm))
-		shrink_ple_window(vcpu);
-}
-
 void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);

arch/x86/kvm/vmx/x86_ops.h

@@ -112,7 +112,6 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu);
 void vmx_write_tsc_offset(struct kvm_vcpu *vcpu);
 void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu);
 void vmx_request_immediate_exit(struct kvm_vcpu *vcpu);
-void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu);
 void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_X86_64
 int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,

arch/x86/kvm/x86.c

@@ -4998,6 +4998,15 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	vcpu->arch.l1tf_flush_l1d = true;
+
+	if (vcpu->scheduled_out && pmu->version && pmu->event_count) {
+		pmu->need_cleanup = true;
+		kvm_make_request(KVM_REQ_PMU, vcpu);
+	}
+
 	/* Address WBINVD may be executed by guest */
 	if (need_emulate_wbinvd(vcpu)) {
 		if (static_call(kvm_x86_has_wbinvd_exit)())
@@ -6546,9 +6555,6 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			goto split_irqchip_unlock;
 		if (kvm->created_vcpus)
 			goto split_irqchip_unlock;
-		r = kvm_setup_empty_irq_routing(kvm);
-		if (r)
-			goto split_irqchip_unlock;
 		/* Pairs with irqchip_in_kernel. */
 		smp_wmb();
 		kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT;
@@ -6695,7 +6701,9 @@ split_irqchip_unlock:
 			break;
 
 		mutex_lock(&kvm->lock);
-		if (kvm->arch.max_vcpu_ids == cap->args[0]) {
+		if (kvm->arch.bsp_vcpu_id > cap->args[0]) {
+			;
+		} else if (kvm->arch.max_vcpu_ids == cap->args[0]) {
 			r = 0;
 		} else if (!kvm->arch.max_vcpu_ids) {
 			kvm->arch.max_vcpu_ids = cap->args[0];
@@ -7216,6 +7224,9 @@ set_pit2_out:
 		mutex_lock(&kvm->lock);
 		if (kvm->created_vcpus)
 			r = -EBUSY;
+		else if (arg > KVM_MAX_VCPU_IDS ||
+			 (kvm->arch.max_vcpu_ids && arg > kvm->arch.max_vcpu_ids))
+			r = -EINVAL;
 		else
 			kvm->arch.bsp_vcpu_id = arg;
 		mutex_unlock(&kvm->lock);
@@ -11248,7 +11259,6 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	int r;
 
 	vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
-	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
 		/*
@@ -11398,7 +11408,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	kvm_vcpu_srcu_read_lock(vcpu);
 	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
-		if (kvm_run->immediate_exit) {
+		if (!vcpu->wants_to_run) {
 			r = -EINTR;
 			goto out;
 		}
@@ -11476,7 +11486,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		WARN_ON_ONCE(vcpu->mmio_needed);
 	}
 
-	if (kvm_run->immediate_exit) {
+	if (!vcpu->wants_to_run) {
 		r = -EINTR;
 		goto out;
 	}
@@ -12569,18 +12579,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 	return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
 }
 
-void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
-{
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-
-	vcpu->arch.l1tf_flush_l1d = true;
-	if (pmu->version && unlikely(pmu->event_count)) {
-		pmu->need_cleanup = true;
-		kvm_make_request(KVM_REQ_PMU, vcpu);
-	}
-	static_call(kvm_x86_sched_in)(vcpu, cpu);
-}
-
 void kvm_arch_free_vm(struct kvm *kvm)
 {
 #if IS_ENABLED(CONFIG_HYPERV)

include/linux/kvm_host.h

@@ -378,8 +378,10 @@ struct kvm_vcpu {
 		bool dy_eligible;
 	} spin_loop;
 #endif
+	bool wants_to_run;
 	bool preempted;
 	bool ready;
+	bool scheduled_out;
 	struct kvm_vcpu_arch arch;
 	struct kvm_vcpu_stat stat;
 	char stats_id[KVM_STATS_NAME_SIZE];
@@ -1494,8 +1496,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 					struct kvm_guest_debug *dbg);
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu);
 
-void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id);
@@ -1955,8 +1955,6 @@ struct _kvm_stats_desc {
 			HALT_POLL_HIST_COUNT),				       \
 	STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking)
 
-extern struct dentry *kvm_debugfs_dir;
-
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
 		       const struct _kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
@@ -2096,6 +2094,7 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			const struct kvm_irq_routing_entry *entries,
 			unsigned nr,
 			unsigned flags);
+int kvm_init_irq_routing(struct kvm *kvm);
 int kvm_set_routing_entry(struct kvm *kvm,
 			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue);
@@ -2105,6 +2104,11 @@ void kvm_free_irq_routing(struct kvm *kvm);
 
 static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
+static inline int kvm_init_irq_routing(struct kvm *kvm)
+{
+	return 0;
+}
+
 #endif
 
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);

include/uapi/linux/kvm.h

@@ -192,11 +192,24 @@ struct kvm_xen_exit {
 /* Flags that describe what fields in emulation_failure hold valid data. */
 #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0)
 
+/*
+ * struct kvm_run can be modified by userspace at any time, so KVM must be
+ * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM()
+ * renames fields in struct kvm_run from <symbol> to <symbol>__unsafe when
+ * compiled into the kernel, ensuring that any use within KVM is obvious and
+ * gets extra scrutiny.
+ */
+#ifdef __KERNEL__
+#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe
+#else
+#define HINT_UNSAFE_IN_KVM(_symbol) _symbol
+#endif
+
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
 	/* in */
 	__u8 request_interrupt_window;
-	__u8 immediate_exit;
+	__u8 HINT_UNSAFE_IN_KVM(immediate_exit);
 	__u8 padding1[6];
 
 	/* out */

tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c

@@ -26,19 +26,37 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(ret < 0,
 		    "Setting KVM_CAP_MAX_VCPU_ID beyond KVM cap should fail");
 
+	/* Test BOOT_CPU_ID interaction (MAX_VCPU_ID cannot be lower) */
+	if (kvm_has_cap(KVM_CAP_SET_BOOT_CPU_ID)) {
+		vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *)MAX_VCPU_ID);
+
+		/* Try setting KVM_CAP_MAX_VCPU_ID below BOOT_CPU_ID */
+		ret = __vm_enable_cap(vm, KVM_CAP_MAX_VCPU_ID, MAX_VCPU_ID - 1);
+		TEST_ASSERT(ret < 0,
+			    "Setting KVM_CAP_MAX_VCPU_ID below BOOT_CPU_ID should fail");
+	}
+
 	/* Set KVM_CAP_MAX_VCPU_ID */
 	vm_enable_cap(vm, KVM_CAP_MAX_VCPU_ID, MAX_VCPU_ID);
 
-
 	/* Try to set KVM_CAP_MAX_VCPU_ID again */
 	ret = __vm_enable_cap(vm, KVM_CAP_MAX_VCPU_ID, MAX_VCPU_ID + 1);
 	TEST_ASSERT(ret < 0,
 		    "Setting KVM_CAP_MAX_VCPU_ID multiple times should fail");
 
-	/* Create vCPU with id beyond KVM_CAP_MAX_VCPU_ID cap*/
+	/* Create vCPU with id beyond KVM_CAP_MAX_VCPU_ID cap */
 	ret = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)MAX_VCPU_ID);
 	TEST_ASSERT(ret < 0, "Creating vCPU with ID > MAX_VCPU_ID should fail");
 
+	/* Create vCPU with bits 63:32 != 0, but an otherwise valid id */
+	ret = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)(1L << 32));
+	TEST_ASSERT(ret < 0, "Creating vCPU with ID[63:32] != 0 should fail");
+
+	/* Create vCPU with id within bounds */
+	ret = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)0);
+	TEST_ASSERT(ret >= 0, "Creating vCPU with ID 0 should succeed");
+
+	close(ret);
 	kvm_vm_free(vm);
 	return 0;
 }

tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c

@@ -33,6 +33,20 @@ static void guest_not_bsp_vcpu(void *arg)
 	GUEST_DONE();
 }
 
+static void test_set_invalid_bsp(struct kvm_vm *vm)
+{
+	unsigned long max_vcpu_id = vm_check_cap(vm, KVM_CAP_MAX_VCPU_ID);
+	int r;
+
+	if (max_vcpu_id) {
+		r = __vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *)(max_vcpu_id + 1));
+		TEST_ASSERT(r == -1 && errno == EINVAL, "BSP with ID > MAX should fail");
+	}
+
+	r = __vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *)(1L << 32));
+	TEST_ASSERT(r == -1 && errno == EINVAL, "BSP with ID[63:32]!=0 should fail");
+}
+
 static void test_set_bsp_busy(struct kvm_vcpu *vcpu, const char *msg)
 {
 	int r = __vm_ioctl(vcpu->vm, KVM_SET_BOOT_CPU_ID,
@@ -80,6 +94,8 @@ static struct kvm_vm *create_vm(uint32_t nr_vcpus, uint32_t bsp_vcpu_id,
 
 	vm = vm_create(nr_vcpus);
 
+	test_set_invalid_bsp(vm);
+
 	vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *)(unsigned long)bsp_vcpu_id);
 
 	for (i = 0; i < nr_vcpus; i++)

virt/kvm/async_pf.c

@@ -80,7 +80,6 @@ static void async_pf_execute(struct work_struct *work)
 	spin_lock(&vcpu->async_pf.lock);
 	first = list_empty(&vcpu->async_pf.done);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
-	apf->vcpu = NULL;
 	spin_unlock(&vcpu->async_pf.lock);
 
 	/*
@@ -120,8 +119,6 @@ static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work)
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 {
-	spin_lock(&vcpu->async_pf.lock);
-
 	/* cancel outstanding work queue item */
 	while (!list_empty(&vcpu->async_pf.queue)) {
 		struct kvm_async_pf *work =
@@ -129,23 +126,15 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 					 typeof(*work), queue);
 		list_del(&work->queue);
 
-		/*
-		 * We know it's present in vcpu->async_pf.done, do
-		 * nothing here.
-		 */
-		if (!work->vcpu)
-			continue;
-
-		spin_unlock(&vcpu->async_pf.lock);
 #ifdef CONFIG_KVM_ASYNC_PF_SYNC
 		flush_work(&work->work);
 #else
 		if (cancel_work_sync(&work->work))
 			kmem_cache_free(async_pf_cache, work);
 #endif
-		spin_lock(&vcpu->async_pf.lock);
 	}
 
+	spin_lock(&vcpu->async_pf.lock);
 	while (!list_empty(&vcpu->async_pf.done)) {
 		struct kvm_async_pf *work =
 			list_first_entry(&vcpu->async_pf.done,

virt/kvm/irqchip.c

@@ -237,3 +237,27 @@ out:
 
 	return r;
 }
+
+/*
+ * Allocate empty IRQ routing by default so that additional setup isn't needed
+ * when userspace-driven IRQ routing is activated, and so that kvm->irq_routing
+ * is guaranteed to be non-NULL.
+ */
+int kvm_init_irq_routing(struct kvm *kvm)
+{
+	struct kvm_irq_routing_table *new;
+	int chip_size;
+
+	new = kzalloc(struct_size(new, map, 1), GFP_KERNEL_ACCOUNT);
+	if (!new)
+		return -ENOMEM;
+
+	new->nr_rt_entries = 1;
+
+	chip_size = sizeof(int) * KVM_NR_IRQCHIPS * KVM_IRQCHIP_NUM_PINS;
+	memset(new->chip, -1, chip_size);
+
+	RCU_INIT_POINTER(kvm->irq_routing, new);
+
+	return 0;
+}

virt/kvm/kvm_main.c

@@ -1,9 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Kernel-based Virtual Machine driver for Linux
+ * Kernel-based Virtual Machine (KVM) Hypervisor
- *
- * This module enables machines with Intel VT-x extensions to run virtual
- * machines without emulation or binary translation.
  *
  * Copyright (C) 2006 Qumranet, Inc.
  * Copyright 2010 Red Hat, Inc. and/or its affiliates.
@@ -74,6 +71,7 @@
 #define ITOA_MAX_LEN 12
 
 MODULE_AUTHOR("Qumranet");
+MODULE_DESCRIPTION("Kernel-based Virtual Machine (KVM) Hypervisor");
 MODULE_LICENSE("GPL");
 
 /* Architectures should define their poll value according to the halt latency */
@@ -91,8 +89,8 @@ unsigned int halt_poll_ns_grow_start = 10000; /* 10us */
 module_param(halt_poll_ns_grow_start, uint, 0644);
 EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start);
 
-/* Default resets per-vcpu halt_poll_ns . */
+/* Default halves per-vcpu halt_poll_ns. */
-unsigned int halt_poll_ns_shrink;
+unsigned int halt_poll_ns_shrink = 2;
 module_param(halt_poll_ns_shrink, uint, 0644);
 EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
 
@@ -110,8 +108,7 @@ static struct kmem_cache *kvm_vcpu_cache;
 static __read_mostly struct preempt_ops kvm_preempt_ops;
 static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu);
 
-struct dentry *kvm_debugfs_dir;
+static struct dentry *kvm_debugfs_dir;
-EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
 
 static const struct file_operations stat_fops_per_vm;
 
@@ -1145,8 +1142,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 {
 	struct kvm *kvm = kvm_arch_alloc_vm();
 	struct kvm_memslots *slots;
-	int r = -ENOMEM;
+	int r, i, j;
-	int i, j;
 
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
@@ -1183,12 +1179,18 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d",
 		 task_pid_nr(current));
 
+	r = -ENOMEM;
 	if (init_srcu_struct(&kvm->srcu))
 		goto out_err_no_srcu;
 	if (init_srcu_struct(&kvm->irq_srcu))
 		goto out_err_no_irq_srcu;
 
+	r = kvm_init_irq_routing(kvm);
+	if (r)
+		goto out_err_no_irq_routing;
+
 	refcount_set(&kvm->users_count, 1);
+
 	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		for (j = 0; j < 2; j++) {
 			slots = &kvm->__memslots[i][j];
@@ -1206,6 +1208,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 		rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]);
 	}
 
+	r = -ENOMEM;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		rcu_assign_pointer(kvm->buses[i],
 			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT));
@@ -1267,6 +1270,8 @@ out_err_no_arch_destroy_vm:
 	WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm_get_bus(kvm, i));
+	kvm_free_irq_routing(kvm);
+out_err_no_irq_routing:
 	cleanup_srcu_struct(&kvm->irq_srcu);
 out_err_no_irq_srcu:
 	cleanup_srcu_struct(&kvm->srcu);
@@ -4202,12 +4207,21 @@ static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 /*
  * Creates some virtual cpus.  Good luck creating more than one.
  */
-static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
+static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id)
 {
 	int r;
 	struct kvm_vcpu *vcpu;
 	struct page *page;
 
+	/*
+	 * KVM tracks vCPU IDs as 'int', be kind to userspace and reject
+	 * too-large values instead of silently truncating.
+	 *
+	 * Ensure KVM_MAX_VCPU_IDS isn't pushed above INT_MAX without first
+	 * changing the storage type (at the very least, IDs should be tracked
+	 * as unsigned ints).
+	 */
+	BUILD_BUG_ON(KVM_MAX_VCPU_IDS > INT_MAX);
 	if (id >= KVM_MAX_VCPU_IDS)
 		return -EINVAL;
 
@@ -4467,7 +4481,10 @@ static long kvm_vcpu_ioctl(struct file *filp,
 				synchronize_rcu();
 			put_pid(oldpid);
 		}
+		vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe);
 		r = kvm_arch_vcpu_ioctl_run(vcpu);
+		vcpu->wants_to_run = false;
+
 		trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
 		break;
 	}
@@ -6347,8 +6364,9 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
 	WRITE_ONCE(vcpu->ready, false);
 
 	__this_cpu_write(kvm_running_vcpu, vcpu);
-	kvm_arch_sched_in(vcpu, cpu);
 	kvm_arch_vcpu_load(vcpu, cpu);
+
+	WRITE_ONCE(vcpu->scheduled_out, false);
 }
 
 static void kvm_sched_out(struct preempt_notifier *pn,
@@ -6356,7 +6374,9 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
 
-	if (current->on_rq) {
+	WRITE_ONCE(vcpu->scheduled_out, true);
+
+	if (current->on_rq && vcpu->wants_to_run) {
 		WRITE_ONCE(vcpu->preempted, true);
 		WRITE_ONCE(vcpu->ready, true);
 	}