[PATCH 02/15] sched: call into io_uring when a PF_IO_HANDOFF task blocks

[Jens Axboe <axboe@kernel.dk>]

Add PF_IO_HANDOFF, set by io_uring on a task for the duration of an
inline request issue that may block, and have sched_submit_work() call
io_uring_task_sleeping() when such a task blocks. Placeholder for now.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring.h | 5 +++++
 include/linux/sched.h    | 2 +-
 kernel/fork.c            | 3 ++-
 kernel/sched/core.c      | 3 +++
 4 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index d1aa4edfc2a5..969de22c3d0f 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -60,4 +60,9 @@ static inline int io_uring_fork(struct task_struct *tsk)
 }
 #endif
 
+/* called from sched_submit_work() when a PF_IO_HANDOFF task blocks */
+static inline void io_uring_task_sleeping(struct task_struct *tsk)
+{
+}
+
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8b3d47a325cc..310310865029 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1816,7 +1816,7 @@ extern struct pid *cad_pid;
 						 * I am cleaning dirty pages from some other bdi. */
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
-#define PF__HOLE__00800000	0x00800000
+#define PF_IO_HANDOFF		0x00800000	/* io_uring: hand identity off if the task blocks */
 #define PF__HOLE__01000000	0x01000000
 #define PF__HOLE__02000000	0x02000000
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
diff --git a/kernel/fork.c b/kernel/fork.c
index 416758c8a3d4..510c8a9aa870 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2190,7 +2190,8 @@ __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_cleanup_count;
 
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
-	p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY);
+	p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE |
+		      PF_NO_SETAFFINITY | PF_IO_HANDOFF);
 	p->flags |= PF_FORKNOEXEC;
 	INIT_LIST_HEAD(&p->children);
 	INIT_LIST_HEAD(&p->sibling);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index eeb55367c0c6..bba1c3b26b7e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -96,6 +96,7 @@
 
 #include "../workqueue_internal.h"
 #include "../../io_uring/io-wq.h"
+#include <linux/io_uring.h>
 #include <linux/thread_handoff.h>
 #include "../smpboot.h"
 #include "../locking/mutex.h"
@@ -7352,6 +7353,8 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		wq_worker_sleeping(tsk);
 	else if (task_flags & PF_IO_WORKER)
 		io_wq_worker_sleeping(tsk);
+	else if (task_flags & PF_IO_HANDOFF)
+		io_uring_task_sleeping(tsk);
 
 	/*
 	 * spinlock and rwlock must not flush block requests.  This will
-- 
2.55.0