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

bonzini · bonzini · commit 86014c1e20fa · 2024-07-16T09:51:36.000-04:00
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
diff --git a/Documentation/virt/kvm/api.rst b/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
-Type: vm
-Parameters: args[0] is the fd of the source vm
-Returns: 0 on success
+:Architectures: x86 SEV enabled
+:Type: vm
+:Parameters: args[0] is the fd of the source vm
+: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.
diff --git a/Documentation/virt/kvm/halt-polling.rst b/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
-polling interval as well as the rate at which the polling interval is grown and
-shrunk. These variables are defined in include/linux/kvm_host.h and as module
-parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the
-powerpc kvm-hv case.
+The kvm module has 4 tunable module parameters to adjust the global max polling
+interval, the initial value (to grow from 0), and the rate at which the polling
+interval is grown and shrunk. These variables are defined in
+include/linux/kvm_host.h and as module parameters in virt/kvm/kvm_main.c, or
+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()	    |			      |
diff --git a/arch/arm64/include/asm/kvm_host.h b/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);
diff --git a/arch/arm64/kvm/arm.c b/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;
 	}
diff --git a/arch/loongarch/include/asm/kvm_host.h b/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) {}
diff --git a/arch/loongarch/kvm/vcpu.c b/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 */
diff --git a/arch/mips/include/asm/kvm_host.h b/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) {}
 
diff --git a/arch/mips/kvm/mips.c b/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);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/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) {}
 
diff --git a/arch/powerpc/kvm/powerpc.c b/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);
diff --git a/arch/riscv/include/asm/kvm_host.h b/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
 
diff --git a/arch/riscv/kvm/vcpu.c b/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;
 	}
diff --git a/arch/s390/include/asm/kvm_host.h b/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) {}
diff --git a/arch/s390/kvm/kvm-s390.c b/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) {
-			/* Set up dummy routing. */
-			memset(&routing, 0, sizeof(routing));
-			r = kvm_set_irq_routing(kvm, &routing, 0, 0);
-		}
+		if (kvm->arch.use_irqchip)
+			r = 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 ||
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/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)
diff --git a/arch/x86/include/asm/kvm_host.h b/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.
diff --git a/arch/x86/kvm/irq.h b/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);
diff --git a/arch/x86/kvm/irq_comm.c b/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))
diff --git a/arch/x86/kvm/pmu.c b/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
-	 * weren't accessed during the last vCPU time slice. kvm_arch_sched_in
-	 * triggers KVM_REQ_PMU if cleanup is needed.
+	 * Release unused perf_events if the corresponding guest MSRs weren't
+	 * accessed during the last vCPU time slice (need_cleanup is set when
+	 * the vCPU is scheduled back in).
 	 */
 	if (unlikely(pmu->need_cleanup))
 		kvm_pmu_cleanup(vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/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,
diff --git a/arch/x86/kvm/vmx/main.c b/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,
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/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
-		 * either from vcpu_run() or from one of the unsafe
-		 * VMEXIT handlers.
+		 * Clear the per-vcpu flush bit, it gets set again if the vCPU
+		 * is reloaded, i.e. if the vCPU is scheduled out or if KVM
+		 * 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);
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/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,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
diff --git a/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c b/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c

Original file line number	Diff line number	Diff line change
`@@ -1289,7 +1289,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void)`
`1289`	`1289`	`}`
`1290`	`1290`
`1291`	`1291`	`static inline void kvm_arch_sync_events(struct kvm *kvm) {}`
`1292`		`-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}`
`1293`	`1292`
`1294`	`1293`	`void kvm_arm_init_debug(void);`
`1295`	`1294`	`void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);`
Original file line number	Diff line number	Diff line change
`@@ -1138,7 +1138,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)`
`1138`	`1138`
`1139`	`1139`	`vcpu_load(vcpu);`
`1140`	`1140`
`1141`		`- if (run->immediate_exit) {`
	`1141`	`+ if (!vcpu->wants_to_run) {`
`1142`	`1142`	`ret = -EINTR;`
`1143`	`1143`	`goto out;`
`1144`	`1144`	`}`
Original file line number	Diff line number	Diff line change
`@@ -1416,7 +1416,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)`
`1416`	`1416`	`kvm_complete_iocsr_read(vcpu, run);`
`1417`	`1417`	`}`
`1418`	`1418`
`1419`		`- if (run->immediate_exit)`
	`1419`	`+ if (!vcpu->wants_to_run)`
`1420`	`1420`	`return r;`
`1421`	`1421`
`1422`	`1422`	`/* Clear exit_reason */`
Original file line number	Diff line number	Diff line change
`@@ -436,7 +436,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)`
`436`	`436`	`vcpu->mmio_needed = 0;`
`437`	`437`	`}`
`438`	`438`
`439`		`- if (vcpu->run->immediate_exit)`
	`439`	`+ if (!vcpu->wants_to_run)`
`440`	`440`	`goto out;`
`441`	`441`
`442`	`442`	`lose_fpu(1);`