sched/umcg: add UMCG server/worker API (early RFC)

Implement UMCG server/worker API.

This is an early RFC patch - the code seems working, but
more testing is needed. Gaps I plan to address before this
is ready for a detailed review:

- preemption/interrupt handling;
- better documentation/comments;
- tracing;
- additional testing;
- corner cases like abnormal process/task termination;
- in some cases where I kill the task (umcg_segv), returning
an error may be more appropriate.

All in all, please focus more on the high-level approach
and less on things like variable names, (doc) comments, or indentation.

Signed-off-by: Peter Oskolkov <posk@google.com>

include/linux/mm_types.h

@@ -562,6 +562,11 @@ struct mm_struct {
 #ifdef CONFIG_IOMMU_SUPPORT
 		u32 pasid;
 #endif
+
+#ifdef CONFIG_UMCG
+	spinlock_t umcg_lock;
+	struct list_head umcg_groups;
+#endif
 	} __randomize_layout;
 
 	/*

include/linux/syscalls.h

@@ -1059,6 +1059,11 @@ asmlinkage long umcg_wait(u32 flags, const struct __kernel_timespec __user *time
 asmlinkage long umcg_wake(u32 flags, u32 next_tid);
 asmlinkage long umcg_swap(u32 wake_flags, u32 next_tid, u32 wait_flags,
 				const struct __kernel_timespec __user *timeout);
+asmlinkage long umcg_create_group(u32 api_version, u64, flags);
+asmlinkage long umcg_destroy_group(u32 group_id);
+asmlinkage long umcg_poll_worker(u32 flags, struct umcg_task __user **ut);
+asmlinkage long umcg_run_worker(u32 flags, u32 worker_tid,
+		struct umcg_task __user **ut);
 
 /*
  * Architecture-specific system calls

kernel/fork.c

@@ -1026,6 +1026,10 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
+#ifdef CONFIG_UMCG
+	spin_lock_init(&mm->umcg_lock);
+	INIT_LIST_HEAD(&mm->umcg_groups);
+#endif
 	mm->core_state = NULL;
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
@@ -1102,6 +1106,13 @@ static inline void __mmput(struct mm_struct *mm)
 		list_del(&mm->mmlist);
 		spin_unlock(&mmlist_lock);
 	}
+#ifdef CONFIG_UMCG
+	if (!list_empty(&mm->umcg_groups)) {
+		spin_lock(&mm->umcg_lock);
+		list_del(&mm->umcg_groups);
+		spin_unlock(&mm->umcg_lock);
+	}
+#endif
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
 	mmdrop(mm);

kernel/sched/core.c

@@ -26,6 +26,7 @@
 
 #include "pelt.h"
 #include "smp.h"
+#include "umcg.h"
 
 /*
  * Export tracepoints that act as a bare tracehook (ie: have no trace event
@@ -6012,10 +6013,20 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 */
 	if (blk_needs_flush_plug(tsk))
 		blk_schedule_flush_plug(tsk);
+
+#ifdef CONFIG_UMCG
+	if (rcu_access_pointer(tsk->umcg_task_data))
+		umcg_on_block();
+#endif
 }
 
 static void sched_update_worker(struct task_struct *tsk)
 {
+#ifdef CONFIG_UMCG
+	if (rcu_access_pointer(tsk->umcg_task_data))
+		umcg_on_wake();
+#endif
+
 	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
 		if (tsk->flags & PF_WQ_WORKER)
 			wq_worker_running(tsk);