xen: branch for v5.11-rc4

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQRTLbB6QfY48x44uB6AXGG7T9hjvgUCYAGllQAKCRCAXGG7T9hj
 vqEtAP9uws/W/JPcnsohK76hMcFAVxZCVdX7C3HvfW5tp6hqMgEAg9ic8sYiuHhn
 6FouRu/ZXHJEg3PpS5W66yKNIYPvGgw=
 =rR+L
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-5.11-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen fixes from Juergen Gross:

 - A series to fix a regression when running as a fully virtualized
   guest on an old Xen hypervisor not supporting PV interrupt callbacks
   for HVM guests.

 - A patch to add support to query Xen resource sizes (setting was
   possible already) from user mode.

* tag 'for-linus-5.11-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  x86/xen: Fix xen_hvm_smp_init() when vector callback not available
  x86/xen: Don't register Xen IPIs when they aren't going to be used
  x86/xen: Add xen_no_vector_callback option to test PCI INTX delivery
  xen: Set platform PCI device INTX affinity to CPU0
  xen: Fix event channel callback via INTX/GSI
  xen/privcmd: allow fetching resource sizes

Documentation/admin-guide/kernel-parameters.txt

@@ -5972,6 +5972,10 @@
 			This option is obsoleted by the "nopv" option, which
 			has equivalent effect for XEN platform.
 
+	xen_no_vector_callback
+			[KNL,X86,XEN] Disable the vector callback for Xen
+			event channel interrupts.
+
 	xen_scrub_pages=	[XEN]
 			Boolean option to control scrubbing pages before giving them back
 			to Xen, for use by other domains. Can be also changed at runtime

arch/arm/xen/enlighten.c

@@ -371,7 +371,7 @@ static int __init xen_guest_init(void)
 	}
 	gnttab_init();
 	if (!xen_initial_domain())
-		xenbus_probe(NULL);
+		xenbus_probe();
 
 	/*
 	 * Making sure board specific code will not set up ops for

arch/x86/xen/enlighten_hvm.c

@@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu)
 	else
 		per_cpu(xen_vcpu_id, cpu) = cpu;
 	rc = xen_vcpu_setup(cpu);
-	if (rc)
+	if (rc || !xen_have_vector_callback)
 		return rc;
 
-	if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock))
+	if (xen_feature(XENFEAT_hvm_safe_pvclock))
 		xen_setup_timer(cpu);
 
 	rc = xen_smp_intr_init(cpu);
@@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu)
        return 0;
 }
 
+static bool no_vector_callback __initdata;
+
 static void __init xen_hvm_guest_init(void)
 {
 	if (xen_pv_domain())
@@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void)
 
 	xen_panic_handler_init();
 
-	if (xen_feature(XENFEAT_hvm_callback_vector))
+	if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
 
 	xen_hvm_smp_init();
@@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg)
 }
 early_param("xen_nopv", xen_parse_nopv);
 
+static __init int xen_parse_no_vector_callback(char *arg)
+{
+	no_vector_callback = true;
+	return 0;
+}
+early_param("xen_no_vector_callback", xen_parse_no_vector_callback);
+
 bool __init xen_hvm_need_lapic(void)
 {
 	if (xen_pv_domain())

arch/x86/xen/smp_hvm.c

@@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 	int cpu;
 
 	native_smp_prepare_cpus(max_cpus);
-	WARN_ON(xen_smp_intr_init(0));
 
-	xen_init_lock_cpu(0);
+	if (xen_have_vector_callback) {
+		WARN_ON(xen_smp_intr_init(0));
+		xen_init_lock_cpu(0);
+	}
 
 	for_each_possible_cpu(cpu) {
 		if (cpu == 0)
@@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 static void xen_hvm_cpu_die(unsigned int cpu)
 {
 	if (common_cpu_die(cpu) == 0) {
-		xen_smp_intr_free(cpu);
-		xen_uninit_lock_cpu(cpu);
-		xen_teardown_timer(cpu);
+		if (xen_have_vector_callback) {
+			xen_smp_intr_free(cpu);
+			xen_uninit_lock_cpu(cpu);
+			xen_teardown_timer(cpu);
+		}
 	}
 }
 #else
@@ -64,14 +68,17 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 
 void __init xen_hvm_smp_init(void)
 {
-	if (!xen_have_vector_callback)
-		return;
-
+	smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
 	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
-	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
+	smp_ops.smp_cpus_done = xen_smp_cpus_done;
 	smp_ops.cpu_die = xen_hvm_cpu_die;
+
+	if (!xen_have_vector_callback) {
+		nopvspin = true;
+		return;
+	}
+
+	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
 	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
 	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
-	smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
-	smp_ops.smp_cpus_done = xen_smp_cpus_done;
 }

drivers/xen/events/events_base.c

@@ -2060,16 +2060,6 @@ static struct irq_chip xen_percpu_chip __read_mostly = {
 	.irq_ack		= ack_dynirq,
 };
 
-int xen_set_callback_via(uint64_t via)
-{
-	struct xen_hvm_param a;
-	a.domid = DOMID_SELF;
-	a.index = HVM_PARAM_CALLBACK_IRQ;
-	a.value = via;
-	return HYPERVISOR_hvm_op(HVMOP_set_param, &a);
-}
-EXPORT_SYMBOL_GPL(xen_set_callback_via);
-
 #ifdef CONFIG_XEN_PVHVM
 /* Vector callbacks are better than PCI interrupts to receive event
  * channel notifications because we can receive vector callbacks on any

drivers/xen/platform-pci.c

@@ -132,6 +132,13 @@ static int platform_pci_probe(struct pci_dev *pdev,
 			dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret);
 			goto out;
 		}
+		/*
+		 * It doesn't strictly *have* to run on CPU0 but it sure
+		 * as hell better process the event channel ports delivered
+		 * to CPU0.
+		 */
+		irq_set_affinity(pdev->irq, cpumask_of(0));
+
 		callback_via = get_callback_via(pdev);
 		ret = xen_set_callback_via(callback_via);
 		if (ret) {
@@ -149,7 +156,6 @@ static int platform_pci_probe(struct pci_dev *pdev,
 	ret = gnttab_init();
 	if (ret)
 		goto grant_out;
-	xenbus_probe(NULL);
 	return 0;
 grant_out:
 	gnttab_free_auto_xlat_frames();

drivers/xen/privcmd.c

@@ -717,14 +717,15 @@ static long privcmd_ioctl_restrict(struct file *file, void __user *udata)
 	return 0;
 }
 
-static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
+static long privcmd_ioctl_mmap_resource(struct file *file,
+				struct privcmd_mmap_resource __user *udata)
 {
 	struct privcmd_data *data = file->private_data;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	struct privcmd_mmap_resource kdata;
 	xen_pfn_t *pfns = NULL;
-	struct xen_mem_acquire_resource xdata;
+	struct xen_mem_acquire_resource xdata = { };
 	int rc;
 
 	if (copy_from_user(&kdata, udata, sizeof(kdata)))
@@ -734,6 +735,22 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
 	if (data->domid != DOMID_INVALID && data->domid != kdata.dom)
 		return -EPERM;
 
+	/* Both fields must be set or unset */
+	if (!!kdata.addr != !!kdata.num)
+		return -EINVAL;
+
+	xdata.domid = kdata.dom;
+	xdata.type = kdata.type;
+	xdata.id = kdata.id;
+
+	if (!kdata.addr && !kdata.num) {
+		/* Query the size of the resource. */
+		rc = HYPERVISOR_memory_op(XENMEM_acquire_resource, &xdata);
+		if (rc)
+			return rc;
+		return __put_user(xdata.nr_frames, &udata->num);
+	}
+
 	mmap_write_lock(mm);
 
 	vma = find_vma(mm, kdata.addr);
@@ -768,10 +785,6 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
 	} else
 		vma->vm_private_data = PRIV_VMA_LOCKED;
 
-	memset(&xdata, 0, sizeof(xdata));
-	xdata.domid = kdata.dom;
-	xdata.type = kdata.type;
-	xdata.id = kdata.id;
 	xdata.frame = kdata.idx;
 	xdata.nr_frames = kdata.num;
 	set_xen_guest_handle(xdata.frame_list, pfns);

drivers/xen/xenbus/xenbus.h

@@ -115,6 +115,7 @@ int xenbus_probe_node(struct xen_bus_type *bus,
 		      const char *type,
 		      const char *nodename);
 int xenbus_probe_devices(struct xen_bus_type *bus);
+void xenbus_probe(void);
 
 void xenbus_dev_changed(const char *node, struct xen_bus_type *bus);
 

drivers/xen/xenbus/xenbus_comms.c

@@ -57,16 +57,8 @@ DEFINE_MUTEX(xs_response_mutex);
 static int xenbus_irq;
 static struct task_struct *xenbus_task;
 
-static DECLARE_WORK(probe_work, xenbus_probe);
-
-
 static irqreturn_t wake_waiting(int irq, void *unused)
 {
-	if (unlikely(xenstored_ready == 0)) {
-		xenstored_ready = 1;
-		schedule_work(&probe_work);
-	}
-
 	wake_up(&xb_waitq);
 	return IRQ_HANDLED;
 }

drivers/xen/xenbus/xenbus_probe.c

@@ -683,29 +683,76 @@ void unregister_xenstore_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_xenstore_notifier);
 
-void xenbus_probe(struct work_struct *unused)
+void xenbus_probe(void)
 {
 	xenstored_ready = 1;
 
+	/*
+	 * In the HVM case, xenbus_init() deferred its call to
+	 * xs_init() in case callbacks were not operational yet.
+	 * So do it now.
+	 */
+	if (xen_store_domain_type == XS_HVM)
+		xs_init();
+
 	/* Notify others that xenstore is up */
 	blocking_notifier_call_chain(&xenstore_chain, 0, NULL);
 }
-EXPORT_SYMBOL_GPL(xenbus_probe);
+
+/*
+ * Returns true when XenStore init must be deferred in order to
+ * allow the PCI platform device to be initialised, before we
+ * can actually have event channel interrupts working.
+ */
+static bool xs_hvm_defer_init_for_callback(void)
+{
+#ifdef CONFIG_XEN_PVHVM
+	return xen_store_domain_type == XS_HVM &&
+		!xen_have_vector_callback;
+#else
+	return false;
+#endif
+}
 
 static int __init xenbus_probe_initcall(void)
 {
-	if (!xen_domain())
-		return -ENODEV;
+	/*
+	 * Probe XenBus here in the XS_PV case, and also XS_HVM unless we
+	 * need to wait for the platform PCI device to come up.
+	 */
+	if (xen_store_domain_type == XS_PV ||
+	    (xen_store_domain_type == XS_HVM &&
+	     !xs_hvm_defer_init_for_callback()))
+		xenbus_probe();
 
-	if (xen_initial_domain() || xen_hvm_domain())
-		return 0;
-
-	xenbus_probe(NULL);
 	return 0;
 }
-
 device_initcall(xenbus_probe_initcall);
 
+int xen_set_callback_via(uint64_t via)
+{
+	struct xen_hvm_param a;
+	int ret;
+
+	a.domid = DOMID_SELF;
+	a.index = HVM_PARAM_CALLBACK_IRQ;
+	a.value = via;
+
+	ret = HYPERVISOR_hvm_op(HVMOP_set_param, &a);
+	if (ret)
+		return ret;
+
+	/*
+	 * If xenbus_probe_initcall() deferred the xenbus_probe()
+	 * due to the callback not functioning yet, we can do it now.
+	 */
+	if (!xenstored_ready && xs_hvm_defer_init_for_callback())
+		xenbus_probe();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xen_set_callback_via);
+
 /* Set up event channel for xenstored which is run as a local process
  * (this is normally used only in dom0)
  */
@@ -818,11 +865,17 @@ static int __init xenbus_init(void)
 		break;
 	}
 
-	/* Initialize the interface to xenstore. */
-	err = xs_init();
-	if (err) {
-		pr_warn("Error initializing xenstore comms: %i\n", err);
-		goto out_error;
+	/*
+	 * HVM domains may not have a functional callback yet. In that
+	 * case let xs_init() be called from xenbus_probe(), which will
+	 * get invoked at an appropriate time.
+	 */
+	if (xen_store_domain_type != XS_HVM) {
+		err = xs_init();
+		if (err) {
+			pr_warn("Error initializing xenstore comms: %i\n", err);
+			goto out_error;
+		}
 	}
 
 	if ((xen_store_domain_type != XS_LOCAL) &&

include/xen/xenbus.h

@@ -192,7 +192,7 @@ void xs_suspend_cancel(void);
 
 struct work_struct;
 
-void xenbus_probe(struct work_struct *);
+void xenbus_probe(void);
 
 #define XENBUS_IS_ERR_READ(str) ({			\
 	if (!IS_ERR(str) && strlen(str) == 0) {		\