Merge tag 'for-linus-6.5a-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen fixes from Juergen Gross:

 - A fix for a performance problem in QubesOS, adding a way to drain the
   queue of grants experiencing delayed unmaps faster

 - A patch enabling the use of static event channels from user mode,
   which was omitted when introducing supporting static event channels

 - A fix for a problem where Xen related code didn't check properly for
   running in a Xen environment, resulting in a WARN splat

* tag 'for-linus-6.5a-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: speed up grant-table reclaim
  xen/evtchn: Introduce new IOCTL to bind static evtchn
  xenbus: check xen_domain in xenbus_probe_initcall

Author: torvalds

Documentation/ABI/testing/sysfs-module

@@ -60,3 +60,14 @@ Description:	Module taint flags:
 			C   staging driver module
 			E   unsigned module
 			==  =====================
+
+What:		/sys/module/grant_table/parameters/free_per_iteration
+Date:		July 2023
+KernelVersion:	6.5 but backported to all supported stable branches
+Contact:	Xen developer discussion <[email protected]>
+Description:	Read and write number of grant entries to attempt to free per iteration.
+
+		Note: Future versions of Xen and Linux may provide a better
+		interface for controlling the rate of deferred grant reclaim
+		or may not need it at all.
+Users:		Qubes OS (https://www.qubes-os.org)

drivers/xen/events/events_base.c

@@ -112,6 +112,7 @@ struct irq_info {
 	unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */
 	u64 eoi_time;           /* Time in jiffies when to EOI. */
 	raw_spinlock_t lock;
+	bool is_static;           /* Is event channel static */
 
 	union {
 		unsigned short virq;
@@ -815,15 +816,6 @@ static void xen_free_irq(unsigned irq)
 	irq_free_desc(irq);
 }
 
-static void xen_evtchn_close(evtchn_port_t port)
-{
-	struct evtchn_close close;
-
-	close.port = port;
-	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
-		BUG();
-}
-
 /* Not called for lateeoi events. */
 static void event_handler_exit(struct irq_info *info)
 {
@@ -982,7 +974,8 @@ static void __unbind_from_irq(unsigned int irq)
 		unsigned int cpu = cpu_from_irq(irq);
 		struct xenbus_device *dev;
 
-		xen_evtchn_close(evtchn);
+		if (!info->is_static)
+			xen_evtchn_close(evtchn);
 
 		switch (type_from_irq(irq)) {
 		case IRQT_VIRQ:
@@ -1574,7 +1567,7 @@ int xen_set_irq_priority(unsigned irq, unsigned priority)
 }
 EXPORT_SYMBOL_GPL(xen_set_irq_priority);
 
-int evtchn_make_refcounted(evtchn_port_t evtchn)
+int evtchn_make_refcounted(evtchn_port_t evtchn, bool is_static)
 {
 	int irq = get_evtchn_to_irq(evtchn);
 	struct irq_info *info;
@@ -1590,6 +1583,7 @@ int evtchn_make_refcounted(evtchn_port_t evtchn)
 	WARN_ON(info->refcnt != -1);
 
 	info->refcnt = 1;
+	info->is_static = is_static;
 
 	return 0;
 }

drivers/xen/evtchn.c

@@ -366,10 +366,10 @@ static int evtchn_resize_ring(struct per_user_data *u)
 	return 0;
 }
 
-static int evtchn_bind_to_user(struct per_user_data *u, evtchn_port_t port)
+static int evtchn_bind_to_user(struct per_user_data *u, evtchn_port_t port,
+			       bool is_static)
 {
 	struct user_evtchn *evtchn;
-	struct evtchn_close close;
 	int rc = 0;
 
 	/*
@@ -402,14 +402,14 @@ static int evtchn_bind_to_user(struct per_user_data *u, evtchn_port_t port)
 	if (rc < 0)
 		goto err;
 
-	rc = evtchn_make_refcounted(port);
+	rc = evtchn_make_refcounted(port, is_static);
 	return rc;
 
 err:
 	/* bind failed, should close the port now */
-	close.port = port;
-	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
-		BUG();
+	if (!is_static)
+		xen_evtchn_close(port);
+
 	del_evtchn(u, evtchn);
 	return rc;
 }
@@ -456,7 +456,7 @@ static long evtchn_ioctl(struct file *file,
 		if (rc != 0)
 			break;
 
-		rc = evtchn_bind_to_user(u, bind_virq.port);
+		rc = evtchn_bind_to_user(u, bind_virq.port, false);
 		if (rc == 0)
 			rc = bind_virq.port;
 		break;
@@ -482,7 +482,7 @@ static long evtchn_ioctl(struct file *file,
 		if (rc != 0)
 			break;
 
-		rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
+		rc = evtchn_bind_to_user(u, bind_interdomain.local_port, false);
 		if (rc == 0)
 			rc = bind_interdomain.local_port;
 		break;
@@ -507,7 +507,7 @@ static long evtchn_ioctl(struct file *file,
 		if (rc != 0)
 			break;
 
-		rc = evtchn_bind_to_user(u, alloc_unbound.port);
+		rc = evtchn_bind_to_user(u, alloc_unbound.port, false);
 		if (rc == 0)
 			rc = alloc_unbound.port;
 		break;
@@ -536,6 +536,23 @@ static long evtchn_ioctl(struct file *file,
 		break;
 	}
 
+	case IOCTL_EVTCHN_BIND_STATIC: {
+		struct ioctl_evtchn_bind bind;
+		struct user_evtchn *evtchn;
+
+		rc = -EFAULT;
+		if (copy_from_user(&bind, uarg, sizeof(bind)))
+			break;
+
+		rc = -EISCONN;
+		evtchn = find_evtchn(u, bind.port);
+		if (evtchn)
+			break;
+
+		rc = evtchn_bind_to_user(u, bind.port, true);
+		break;
+	}
+
 	case IOCTL_EVTCHN_NOTIFY: {
 		struct ioctl_evtchn_notify notify;
 		struct user_evtchn *evtchn;

drivers/xen/grant-table.c

@@ -498,14 +498,21 @@ static LIST_HEAD(deferred_list);
 static void gnttab_handle_deferred(struct timer_list *);
 static DEFINE_TIMER(deferred_timer, gnttab_handle_deferred);
 
+static atomic64_t deferred_count;
+static atomic64_t leaked_count;
+static unsigned int free_per_iteration = 10;
+module_param(free_per_iteration, uint, 0600);
+
 static void gnttab_handle_deferred(struct timer_list *unused)
 {
-	unsigned int nr = 10;
+	unsigned int nr = READ_ONCE(free_per_iteration);
+	const bool ignore_limit = nr == 0;
 	struct deferred_entry *first = NULL;
 	unsigned long flags;
+	size_t freed = 0;
 
 	spin_lock_irqsave(&gnttab_list_lock, flags);
-	while (nr--) {
+	while ((ignore_limit || nr--) && !list_empty(&deferred_list)) {
 		struct deferred_entry *entry
 			= list_first_entry(&deferred_list,
 					   struct deferred_entry, list);
@@ -515,10 +522,14 @@ static void gnttab_handle_deferred(struct timer_list *unused)
 		list_del(&entry->list);
 		spin_unlock_irqrestore(&gnttab_list_lock, flags);
 		if (_gnttab_end_foreign_access_ref(entry->ref)) {
+			uint64_t ret = atomic64_dec_return(&deferred_count);
+
 			put_free_entry(entry->ref);
-			pr_debug("freeing g.e. %#x (pfn %#lx)\n",
-				 entry->ref, page_to_pfn(entry->page));
+			pr_debug("freeing g.e. %#x (pfn %#lx), %llu remaining\n",
+				 entry->ref, page_to_pfn(entry->page),
+				 (unsigned long long)ret);
 			put_page(entry->page);
+			freed++;
 			kfree(entry);
 			entry = NULL;
 		} else {
@@ -530,21 +541,22 @@ static void gnttab_handle_deferred(struct timer_list *unused)
 		spin_lock_irqsave(&gnttab_list_lock, flags);
 		if (entry)
 			list_add_tail(&entry->list, &deferred_list);
-		else if (list_empty(&deferred_list))
-			break;
 	}
-	if (!list_empty(&deferred_list) && !timer_pending(&deferred_timer)) {
+	if (list_empty(&deferred_list))
+		WARN_ON(atomic64_read(&deferred_count));
+	else if (!timer_pending(&deferred_timer)) {
 		deferred_timer.expires = jiffies + HZ;
 		add_timer(&deferred_timer);
 	}
 	spin_unlock_irqrestore(&gnttab_list_lock, flags);
+	pr_debug("Freed %zu references", freed);
 }
 
 static void gnttab_add_deferred(grant_ref_t ref, struct page *page)
 {
 	struct deferred_entry *entry;
 	gfp_t gfp = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL;
-	const char *what = KERN_WARNING "leaking";
+	uint64_t leaked, deferred;
 
 	entry = kmalloc(sizeof(*entry), gfp);
 	if (!page) {
@@ -567,10 +579,16 @@ static void gnttab_add_deferred(grant_ref_t ref, struct page *page)
 			add_timer(&deferred_timer);
 		}
 		spin_unlock_irqrestore(&gnttab_list_lock, flags);
-		what = KERN_DEBUG "deferring";
+		deferred = atomic64_inc_return(&deferred_count);
+		leaked = atomic64_read(&leaked_count);
+		pr_debug("deferring g.e. %#x (pfn %#lx) (total deferred %llu, total leaked %llu)\n",
+			 ref, page ? page_to_pfn(page) : -1, deferred, leaked);
+	} else {
+		deferred = atomic64_read(&deferred_count);
+		leaked = atomic64_inc_return(&leaked_count);
+		pr_warn("leaking g.e. %#x (pfn %#lx) (total deferred %llu, total leaked %llu)\n",
+			ref, page ? page_to_pfn(page) : -1, deferred, leaked);
 	}
-	printk("%s g.e. %#x (pfn %#lx)\n",
-	       what, ref, page ? page_to_pfn(page) : -1);
 }
 
 int gnttab_try_end_foreign_access(grant_ref_t ref)

drivers/xen/xenbus/xenbus_probe.c

@@ -811,6 +811,9 @@ static int xenbus_probe_thread(void *unused)
 
 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 or

include/uapi/xen/evtchn.h

@@ -101,4 +101,13 @@ struct ioctl_evtchn_restrict_domid {
 	domid_t domid;
 };
 
+/*
+ * Bind statically allocated @port.
+ */
+#define IOCTL_EVTCHN_BIND_STATIC			\
+	_IOC(_IOC_NONE, 'E', 7, sizeof(struct ioctl_evtchn_bind))
+struct ioctl_evtchn_bind {
+	unsigned int port;
+};
+
 #endif /* __LINUX_PUBLIC_EVTCHN_H__ */

include/xen/events.h

@@ -69,7 +69,7 @@ int xen_set_irq_priority(unsigned irq, unsigned priority);
 /*
  * Allow extra references to event channels exposed to userspace by evtchn
  */
-int evtchn_make_refcounted(evtchn_port_t evtchn);
+int evtchn_make_refcounted(evtchn_port_t evtchn, bool is_static);
 int evtchn_get(evtchn_port_t evtchn);
 void evtchn_put(evtchn_port_t evtchn);
 
@@ -141,4 +141,13 @@ void xen_init_IRQ(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
+static inline void xen_evtchn_close(evtchn_port_t port)
+{
+	struct evtchn_close close;
+
+	close.port = port;
+	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
+		BUG();
+}
+
 #endif	/* _XEN_EVENTS_H */