xen: features and fixes for 4.13-rc1

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQEcBAABAgAGBQJZXdVXAAoJELDendYovxMvVA0IAITmvH21SDTFiilKCOrxhCv0
 W3q3cOhZA4D+UtTqqIm/os/et08n72864s0mUFoY4PxETaUsb1jBav7z7Tod2c6B
 wh26UgIAhVO3ZewFSmpdPYoW0l3elC5JUMkVMfwSvHkROaU+YDEYUsLWGuIHZiiy
 V/kIskcKe08HLObU//BMjfFusmMHmQSg+TruyqRWodlWj4Rwm7q5fNZ/xaap1UCM
 O7GcHyq1k699w5YYTlIEkLWsX/pGM+auGSlT1xdjJEc2bpjH8ps0xbvAn6dsAKsE
 yoDyxQWtX2wBUXCqF0hXYAB2r1iFx2aFfLQjwc7p+V6BvxpWwSsC7Ur4QIDnm3E=
 =OLb7
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-4.13-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:
 "Other than fixes and cleanups it contains:

   - support > 32 VCPUs at domain restore

   - support for new sysfs nodes related to Xen

   - some performance tuning for Linux running as Xen guest"

* tag 'for-linus-4.13-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  x86/xen: allow userspace access during hypercalls
  x86: xen: remove unnecessary variable in xen_foreach_remap_area()
  xen: allocate page for shared info page from low memory
  xen: avoid deadlock in xenbus driver
  xen: add sysfs node for hypervisor build id
  xen: sync include/xen/interface/version.h
  xen: add sysfs node for guest type
  doc,xen: document hypervisor sysfs nodes for xen
  xen/vcpu: Handle xen_vcpu_setup() failure at boot
  xen/vcpu: Handle xen_vcpu_setup() failure in hotplug
  xen/pv: Fix OOPS on restore for a PV, !SMP domain
  xen/pvh*: Support > 32 VCPUs at domain restore
  xen/vcpu: Simplify xen_vcpu related code
  xen-evtchn: Bind dyn evtchn:qemu-dm interrupt to next online VCPU
  xen: avoid type warning in xchg_xen_ulong
  xen: fix HYPERVISOR_dm_op() prototype
  xen: don't print error message in case of missing Xenstore entry
  arm/xen: Adjust one function call together with a variable assignment
  arm/xen: Delete an error message for a failed memory allocation in __set_phys_to_machine_multi()
  arm/xen: Improve a size determination in __set_phys_to_machine_multi()

drivers/xen/events/events_base.c

@@ -1303,10 +1303,9 @@ void rebind_evtchn_irq(int evtchn, int irq)
 }
 
 /* Rebind an evtchn so that it gets delivered to a specific cpu */
-static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
+int xen_rebind_evtchn_to_cpu(int evtchn, unsigned tcpu)
 {
 	struct evtchn_bind_vcpu bind_vcpu;
-	int evtchn = evtchn_from_irq(irq);
 	int masked;
 
 	if (!VALID_EVTCHN(evtchn))
@@ -1338,12 +1337,13 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(xen_rebind_evtchn_to_cpu);
 
 static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 			    bool force)
 {
 	unsigned tcpu = cpumask_first_and(dest, cpu_online_mask);
-	int ret = rebind_irq_to_cpu(data->irq, tcpu);
+	int ret = xen_rebind_evtchn_to_cpu(evtchn_from_irq(data->irq), tcpu);
 
 	if (!ret)
 		irq_data_update_effective_affinity(data, cpumask_of(tcpu));

drivers/xen/evtchn.c

@@ -421,6 +421,36 @@ static void evtchn_unbind_from_user(struct per_user_data *u,
 	del_evtchn(u, evtchn);
 }
 
+static DEFINE_PER_CPU(int, bind_last_selected_cpu);
+
+static void evtchn_bind_interdom_next_vcpu(int evtchn)
+{
+	unsigned int selected_cpu, irq;
+	struct irq_desc *desc;
+	unsigned long flags;
+
+	irq = irq_from_evtchn(evtchn);
+	desc = irq_to_desc(irq);
+
+	if (!desc)
+		return;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	selected_cpu = this_cpu_read(bind_last_selected_cpu);
+	selected_cpu = cpumask_next_and(selected_cpu,
+			desc->irq_common_data.affinity, cpu_online_mask);
+
+	if (unlikely(selected_cpu >= nr_cpu_ids))
+		selected_cpu = cpumask_first_and(desc->irq_common_data.affinity,
+				cpu_online_mask);
+
+	this_cpu_write(bind_last_selected_cpu, selected_cpu);
+
+	/* unmask expects irqs to be disabled */
+	xen_rebind_evtchn_to_cpu(evtchn, selected_cpu);
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+}
+
 static long evtchn_ioctl(struct file *file,
 			 unsigned int cmd, unsigned long arg)
 {
@@ -478,8 +508,10 @@ static long evtchn_ioctl(struct file *file,
 			break;
 
 		rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
-		if (rc == 0)
+		if (rc == 0) {
 			rc = bind_interdomain.local_port;
+			evtchn_bind_interdom_next_vcpu(rc);
+		}
 		break;
 	}
 

drivers/xen/manage.c

@@ -278,8 +278,16 @@ static void sysrq_handler(struct xenbus_watch *watch, const char *path,
 	err = xenbus_transaction_start(&xbt);
 	if (err)
 		return;
-	if (xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key) < 0) {
-		pr_err("Unable to read sysrq code in control/sysrq\n");
+	err = xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key);
+	if (err < 0) {
+		/*
+		 * The Xenstore watch fires directly after registering it and
+		 * after a suspend/resume cycle. So ENOENT is no error but
+		 * might happen in those cases.
+		 */
+		if (err != -ENOENT)
+			pr_err("Error %d reading sysrq code in control/sysrq\n",
+			       err);
 		xenbus_transaction_end(xbt, 1);
 		return;
 	}

drivers/xen/sys-hypervisor.c

@@ -50,6 +50,35 @@ static int __init xen_sysfs_type_init(void)
 	return sysfs_create_file(hypervisor_kobj, &type_attr.attr);
 }
 
+static ssize_t guest_type_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	const char *type;
+
+	switch (xen_domain_type) {
+	case XEN_NATIVE:
+		/* ARM only. */
+		type = "Xen";
+		break;
+	case XEN_PV_DOMAIN:
+		type = "PV";
+		break;
+	case XEN_HVM_DOMAIN:
+		type = xen_pvh_domain() ? "PVH" : "HVM";
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sprintf(buffer, "%s\n", type);
+}
+
+HYPERVISOR_ATTR_RO(guest_type);
+
+static int __init xen_sysfs_guest_type_init(void)
+{
+	return sysfs_create_file(hypervisor_kobj, &guest_type_attr.attr);
+}
+
 /* xen version attributes */
 static ssize_t major_show(struct hyp_sysfs_attr *attr, char *buffer)
 {
@@ -327,12 +356,40 @@ static ssize_t features_show(struct hyp_sysfs_attr *attr, char *buffer)
 
 HYPERVISOR_ATTR_RO(features);
 
+static ssize_t buildid_show(struct hyp_sysfs_attr *attr, char *buffer)
+{
+	ssize_t ret;
+	struct xen_build_id *buildid;
+
+	ret = HYPERVISOR_xen_version(XENVER_build_id, NULL);
+	if (ret < 0) {
+		if (ret == -EPERM)
+			ret = sprintf(buffer, "<denied>");
+		return ret;
+	}
+
+	buildid = kmalloc(sizeof(*buildid) + ret, GFP_KERNEL);
+	if (!buildid)
+		return -ENOMEM;
+
+	buildid->len = ret;
+	ret = HYPERVISOR_xen_version(XENVER_build_id, buildid);
+	if (ret > 0)
+		ret = sprintf(buffer, "%s", buildid->buf);
+	kfree(buildid);
+
+	return ret;
+}
+
+HYPERVISOR_ATTR_RO(buildid);
+
 static struct attribute *xen_properties_attrs[] = {
 	&capabilities_attr.attr,
 	&changeset_attr.attr,
 	&virtual_start_attr.attr,
 	&pagesize_attr.attr,
 	&features_attr.attr,
+	&buildid_attr.attr,
 	NULL
 };
 
@@ -471,6 +528,9 @@ static int __init hyper_sysfs_init(void)
 	ret = xen_sysfs_type_init();
 	if (ret)
 		goto out;
+	ret = xen_sysfs_guest_type_init();
+	if (ret)
+		goto guest_type_out;
 	ret = xen_sysfs_version_init();
 	if (ret)
 		goto version_out;
@@ -502,6 +562,8 @@ uuid_out:
 comp_out:
 	sysfs_remove_group(hypervisor_kobj, &version_group);
 version_out:
+	sysfs_remove_file(hypervisor_kobj, &guest_type_attr.attr);
+guest_type_out:
 	sysfs_remove_file(hypervisor_kobj, &type_attr.attr);
 out:
 	return ret;

drivers/xen/xenbus/xenbus_comms.c

@@ -299,17 +299,7 @@ static int process_msg(void)
 		mutex_lock(&xb_write_mutex);
 		list_for_each_entry(req, &xs_reply_list, list) {
 			if (req->msg.req_id == state.msg.req_id) {
-				if (req->state == xb_req_state_wait_reply) {
-					req->msg.type = state.msg.type;
-					req->msg.len = state.msg.len;
-					req->body = state.body;
-					req->state = xb_req_state_got_reply;
-					list_del(&req->list);
-					req->cb(req);
-				} else {
-					list_del(&req->list);
-					kfree(req);
-				}
+				list_del(&req->list);
 				err = 0;
 				break;
 			}
@@ -317,6 +307,15 @@ static int process_msg(void)
 		mutex_unlock(&xb_write_mutex);
 		if (err)
 			goto out;
+
+		if (req->state == xb_req_state_wait_reply) {
+			req->msg.type = state.msg.type;
+			req->msg.len = state.msg.len;
+			req->body = state.body;
+			req->state = xb_req_state_got_reply;
+			req->cb(req);
+		} else
+			kfree(req);
 	}
 
 	mutex_unlock(&xs_response_mutex);