[PATCH] sched: arch preempt notifier mechanism

This adds a general mechanism whereby a task can request the scheduler to
notify it whenever it is preempted or scheduled back in.  This allows the
task to swap any special-purpose registers like the fpu or Intel's VT
registers.

Signed-off-by: Avi Kivity <avi@qumranet.com>
[ mingo@elte.hu: fixes, cleanups ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 123 insertions, 2 deletions

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index d0926d63406c..484988ed301e 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -8,6 +8,7 @@
 
 #include <linux/thread_info.h>
 #include <linux/linkage.h>
+#include <linux/list.h>
 
 #ifdef CONFIG_DEBUG_PREEMPT
   extern void fastcall add_preempt_count(int val);
@@ -60,4 +61,47 @@ do { \
 
 #endif
 
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+
+struct preempt_notifier;
+
+/**
+ * preempt_ops - notifiers called when a task is preempted and rescheduled
+ * @sched_in: we're about to be rescheduled:
+ *    notifier: struct preempt_notifier for the task being scheduled
+ *    cpu:  cpu we're scheduled on
+ * @sched_out: we've just been preempted
+ *    notifier: struct preempt_notifier for the task being preempted
+ *    next: the task that's kicking us out
+ */
+struct preempt_ops {
+        void (*sched_in)(struct preempt_notifier *notifier, int cpu);
+        void (*sched_out)(struct preempt_notifier *notifier,
+                          struct task_struct *next);
+};
+
+/**
+ * preempt_notifier - key for installing preemption notifiers
+ * @link: internal use
+ * @ops: defines the notifier functions to be called
+ *
+ * Usually used in conjunction with container_of().
+ */
+struct preempt_notifier {
+        struct hlist_node link;
+        struct preempt_ops *ops;
+};
+
+void preempt_notifier_register(struct preempt_notifier *notifier);
+void preempt_notifier_unregister(struct preempt_notifier *notifier);
+
+static inline void preempt_notifier_init(struct preempt_notifier *notifier,
+                                     struct preempt_ops *ops)
+{
+        INIT_HLIST_NODE(&notifier->link);
+        notifier->ops = ops;
+}
+
+#endif
+
 #endif /* __LINUX_PREEMPT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7c61b50823fa..7a4de8768748 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -935,6 +935,11 @@ struct task_struct {
         struct sched_class *sched_class;
         struct sched_entity se;
 
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+        /* list of struct preempt_notifier: */
+        struct hlist_head preempt_notifiers;
+#endif
+
         unsigned short ioprio;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
         unsigned int btrace_seq;
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index c64ce9c14207..6b066632e40c 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -63,3 +63,6 @@ config PREEMPT_BKL
           Say Y here if you are building a kernel for a desktop system.
           Say N if you are unsure.
 
+config PREEMPT_NOTIFIERS
+        bool
+
diff --git a/kernel/sched.c b/kernel/sched.c
index 93cf241cfbe9..e901aa59f206 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1592,6 +1592,10 @@ static void __sched_fork(struct task_struct *p)
         INIT_LIST_HEAD(&p->run_list);
         p->se.on_rq = 0;
 
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+        INIT_HLIST_HEAD(&p->preempt_notifiers);
+#endif
+
         /*
          * We mark the process as running here, but have not actually
          * inserted it onto the runqueue yet. This guarantees that
@@ -1673,6 +1677,63 @@ void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
         task_rq_unlock(rq, &flags);
 }
 
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+
+/**
+ * preempt_notifier_register - tell me when current is being being preempted
+ *                         and rescheduled
+ */
+void preempt_notifier_register(struct preempt_notifier *notifier)
+{
+        hlist_add_head(&notifier->link, &current->preempt_notifiers);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_register);
+
+/**
+ * preempt_notifier_unregister - no longer interested in preemption notifications
+ *
+ * This is safe to call from within a preemption notifier.
+ */
+void preempt_notifier_unregister(struct preempt_notifier *notifier)
+{
+        hlist_del(&notifier->link);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
+
+static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+        struct preempt_notifier *notifier;
+        struct hlist_node *node;
+
+        hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+                notifier->ops->sched_in(notifier, raw_smp_processor_id());
+}
+
+static void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+                                 struct task_struct *next)
+{
+        struct preempt_notifier *notifier;
+        struct hlist_node *node;
+
+        hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+                notifier->ops->sched_out(notifier, next);
+}
+
+#else
+
+static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+}
+
+static void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+                                 struct task_struct *next)
+{
+}
+
+#endif
+
 /**
  * prepare_task_switch - prepare to switch tasks
  * @rq: the runqueue preparing to switch
@@ -1685,8 +1746,11 @@ void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
  * prepare_task_switch sets up locking and calls architecture specific
  * hooks.
  */
-static inline void prepare_task_switch(struct rq *rq, struct task_struct *next)
+static inline void
+prepare_task_switch(struct rq *rq, struct task_struct *prev,
+                    struct task_struct *next)
 {
+        fire_sched_out_preempt_notifiers(prev, next);
         prepare_lock_switch(rq, next);
         prepare_arch_switch(next);
 }
@@ -1728,6 +1792,7 @@ static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
         prev_state = prev->state;
         finish_arch_switch(prev);
         finish_lock_switch(rq, prev);
+        fire_sched_in_preempt_notifiers(current);
         if (mm)
                 mmdrop(mm);
         if (unlikely(prev_state == TASK_DEAD)) {
@@ -1768,7 +1833,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 {
         struct mm_struct *mm, *oldmm;
 
-        prepare_task_switch(rq, next);
+        prepare_task_switch(rq, prev, next);
         mm = next->mm;
         oldmm = prev->active_mm;
         /*
@@ -6335,6 +6400,10 @@ void __init sched_init(void)
 
         set_load_weight(&init_task);
 
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+        INIT_HLIST_HEAD(&init_task.preempt_notifiers);
+#endif
+
 #ifdef CONFIG_SMP
         nr_cpu_ids = highest_cpu + 1;
         open_softirq(SCHED_SOFTIRQ, run_rebalance_domains, NULL);