[PATCH 1/6] xenbus: prepare data structures and parameter for xenwatch multithreading

[Dongli Zhang]

This is the 1st patch of a (6-patch) patch set.

This patch set of six patches introduces xenwatch multithreading (or
multithreaded xenwatch, abbreviated as 'mtwatch') to dom0 kernel. In
addition to the existing single xenwatch thread, each domU has its own
kernel thread ([xen-mtwatch-<domid>]) to process its xenwatch event.

A kernel parameter 'xen_mtwatch' is introduced to control whether the
feature is enabled or not during dom0 kernel boot. The feature is disabled
by default if 'xen_mtwatch' is not set in grub. In addition, this patch
also introduces the data structures to maintain the status of each per-domU
xenwatch thread. The status of each xenwatch thread (except the default
one) is maintained by a mtwatch domain.

The feature is available only on dom0.

Signed-off-by: Dongli Zhang <dongli.zhang@xxxxxxxxxx>
---
 Documentation/admin-guide/kernel-parameters.txt |  3 ++
 drivers/xen/xenbus/xenbus_xs.c                  | 31 ++++++++++++
 include/xen/xenbus.h                            | 65 +++++++++++++++++++++++++
 3 files changed, 99 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 64a3bf5..fc295ef 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4992,6 +4992,9 @@
 				the unplug protocol
 			never -- do not unplug even if version check succeeds
 
+	xen_mtwatch     [KNL,XEN]
+			Enables the multithreaded xenwatch (mtwatch).
+
 	xen_nopvspin	[X86,XEN]
 			Disables the ticketlock slowpath using Xen PV
 			optimizations.
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index 49a3874..3f137d2 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -95,6 +95,19 @@ static pid_t xenwatch_pid;
 static DEFINE_MUTEX(xenwatch_mutex);
 static DECLARE_WAIT_QUEUE_HEAD(watch_events_waitq);
 
+bool xen_mtwatch;
+EXPORT_SYMBOL_GPL(xen_mtwatch);
+
+struct mtwatch_info *mtwatch_info;
+
+static bool param_xen_mtwatch;
+static __init int xen_parse_mtwatch(char *arg)
+{
+	param_xen_mtwatch = true;
+	return 0;
+}
+early_param("xen_mtwatch", xen_parse_mtwatch);
+
 static void xs_suspend_enter(void)
 {
 	spin_lock(&xs_state_lock);
@@ -929,6 +942,24 @@ int xs_init(void)
 	if (err)
 		return err;
 
+	if (xen_initial_domain() && param_xen_mtwatch) {
+		int i;
+
+		mtwatch_info = kmalloc(sizeof(*mtwatch_info), GFP_KERNEL);
+
+		for (i = 0; i < MTWATCH_HASH_SIZE; i++)
+			INIT_HLIST_HEAD(&mtwatch_info->domain_hash[i]);
+		spin_lock_init(&mtwatch_info->domain_lock);
+		INIT_LIST_HEAD(&mtwatch_info->domain_list);
+
+		spin_lock_init(&mtwatch_info->purge_lock);
+		INIT_LIST_HEAD(&mtwatch_info->purge_list);
+
+		xen_mtwatch = true;
+
+		pr_info("xenwatch multithreading is enabled\n");
+	}
+
 	task = kthread_run(xenwatch_thread, NULL, "xenwatch");
 	if (IS_ERR(task))
 		return PTR_ERR(task);
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 869c816..e807114 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -62,6 +62,13 @@ struct xenbus_watch
 	/* Callback (executed in a process context with no locks held). */
 	void (*callback)(struct xenbus_watch *,
 			 const char *path, const char *token);
+
+	/* Callback to help calculate the domid the path belongs to */
+	domid_t (*get_domid)(struct xenbus_watch *watch,
+			     const char *path, const char *token);
+
+	/* The owner's domid if the watch is for a specific domain */
+	domid_t owner_id;
 };
 
 
@@ -93,6 +100,7 @@ struct xenbus_device_id
 struct xenbus_driver {
 	const char *name;       /* defaults to ids[0].devicetype */
 	const struct xenbus_device_id *ids;
+	bool use_mtwatch;
 	int (*probe)(struct xenbus_device *dev,
 		     const struct xenbus_device_id *id);
 	void (*otherend_changed)(struct xenbus_device *dev,
@@ -233,4 +241,61 @@ extern const struct file_operations xen_xenbus_fops;
 extern struct xenstore_domain_interface *xen_store_interface;
 extern int xen_store_evtchn;
 
+extern bool xen_mtwatch;
+
+#define MTWATCH_HASH_SIZE 256
+#define MTWATCH_HASH(_id) ((int)(_id)&(MTWATCH_HASH_SIZE-1))
+
+struct mtwatch_info {
+	/*
+	 * The mtwatch_domain is put on both a hash table and a list.
+	 * domain_list is used to optimize xenbus_watch un-registration.
+	 *
+	 * The mtwatch_domain is removed from domain_hash (with state set
+	 * to MTWATCH_DOMAIN_DOWN) when its refcnt is zero. However, it is
+	 * left on domain_list until all events belong to such
+	 * mtwatch_domain are processed in mtwatch_thread().
+	 *
+	 * While there may exist two mtwatch_domain with the same domid on
+	 * domain_list simultaneously, all mtwatch_domain on hash_hash
+	 * should have unique domid.
+	 */
+	spinlock_t domain_lock;
+	struct hlist_head domain_hash[MTWATCH_HASH_SIZE];
+	struct list_head domain_list;
+
+	/*
+	 * When a per-domU kthread is going to be destroyed, it is put
+	 * on the purge_list, and will be flushed by purge_work later.
+	 */
+	struct work_struct purge_work;
+	spinlock_t purge_lock;
+	struct list_head purge_list;
+};
+
+enum mtwatch_domain_state {
+	MTWATCH_DOMAIN_UP = 1,
+	MTWATCH_DOMAIN_DOWN = 2,
+};
+
+struct mtwatch_domain {
+	domid_t domid;
+	struct task_struct *task;
+	atomic_t refcnt;
+
+	pid_t pid;
+	struct mutex domain_mutex;
+	struct rcu_head rcu;
+
+	struct hlist_node hash_node;
+	struct list_head list_node;
+	struct list_head purge_node;
+
+	wait_queue_head_t events_wq;
+
+	spinlock_t events_lock;
+	struct list_head events;
+	enum mtwatch_domain_state state;
+};
+
 #endif /* _XEN_XENBUS_H */
-- 
2.7.4