io-wq: small threadpool implementation for io_uring

This adds support for io-wq, a smaller and specialized thread pool
implementation. This is meant to replace workqueues for io_uring. Among
the reasons for this addition are:

- We can assign memory context smarter and more persistently if we
  manage the life time of threads.

- We can drop various work-arounds we have in io_uring, like the
  async_list.

- We can implement hashed work insertion, to manage concurrency of
  buffered writes without needing a) an extra workqueue, or b)
  needlessly making the concurrency of said workqueue very low
  which hurts performance of multiple buffered file writers.

- We can implement cancel through signals, for cancelling
  interruptible work like read/write (or send/recv) to/from sockets.

- We need the above cancel for being able to assign and use file tables
  from a process.

- We can implement a more thorough cancel operation in general.

- We need it to move towards a syslet/threadlet model for even faster
  async execution. For that we need to take ownership of the used
  threads.

This list is just off the top of my head. Performance should be the
same, or better, at least that's what I've seen in my testing. io-wq
supports basic NUMA functionality, setting up a pool per node.

io-wq hooks up to the scheduler schedule in/out just like workqueue
and uses that to drive the need for more/less workers.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/Kconfig

@@ -322,4 +322,7 @@ source "fs/nls/Kconfig"
 source "fs/dlm/Kconfig"
 source "fs/unicode/Kconfig"
 
+config IO_WQ
+	bool
+
 endmenu

fs/Makefile

@@ -32,6 +32,7 @@ obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_USERFAULTFD)	+= userfaultfd.o
 obj-$(CONFIG_AIO)               += aio.o
 obj-$(CONFIG_IO_URING)		+= io_uring.o
+obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FS_VERITY)		+= verity/

fs/io-wq.h

+#ifndef INTERNAL_IO_WQ_H
+#define INTERNAL_IO_WQ_H
+
+struct io_wq;
+
+enum {
+	IO_WQ_WORK_CANCEL	= 1,
+	IO_WQ_WORK_HAS_MM	= 2,
+	IO_WQ_WORK_HASHED	= 4,
+	IO_WQ_WORK_NEEDS_USER	= 8,
+
+	IO_WQ_HASH_SHIFT	= 24,	/* upper 8 bits are used for hash key */
+};
+
+enum io_wq_cancel {
+	IO_WQ_CANCEL_OK,	/* cancelled before started */
+	IO_WQ_CANCEL_RUNNING,	/* found, running, and attempted cancelled */
+	IO_WQ_CANCEL_NOTFOUND,	/* work not found */
+};
+
+struct io_wq_work {
+	struct list_head list;
+	void (*func)(struct io_wq_work **);
+	unsigned flags;
+};
+
+#define INIT_IO_WORK(work, _func)			\
+	do {						\
+		(work)->func = _func;			\
+		(work)->flags = 0;			\
+	} while (0)					\
+
+struct io_wq *io_wq_create(unsigned concurrency, struct mm_struct *mm);
+void io_wq_destroy(struct io_wq *wq);
+
+void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
+void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val);
+void io_wq_flush(struct io_wq *wq);
+
+void io_wq_cancel_all(struct io_wq *wq);
+enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
+
+#if defined(CONFIG_IO_WQ)
+extern void io_wq_worker_sleeping(struct task_struct *);
+extern void io_wq_worker_running(struct task_struct *);
+#else
+static inline void io_wq_worker_sleeping(struct task_struct *tsk)
+{
+}
+static inline void io_wq_worker_running(struct task_struct *tsk)
+{
+}
+#endif
+
+#endif

include/linux/sched.h

@@ -1468,6 +1468,7 @@ extern struct pid *cad_pid;
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MEMALLOC_NOCMA	0x10000000	/* All allocation request will have _GFP_MOVABLE cleared */
+#define PF_IO_WORKER		0x20000000	/* Task is an IO worker */
 #define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
 #define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
 

kernel/sched/core.c

@@ -16,6 +16,7 @@
 #include <asm/tlb.h>
 
 #include "../workqueue_internal.h"
+#include "../../fs/io-wq.h"
 #include "../smpboot.h"
 
 #include "pelt.h"
@@ -4103,9 +4104,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * we disable preemption to avoid it calling schedule() again
 	 * in the possible wakeup of a kworker.
 	 */
-	if (tsk->flags & PF_WQ_WORKER) {
+	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
 		preempt_disable();
-		wq_worker_sleeping(tsk);
+		if (tsk->flags & PF_WQ_WORKER)
+			wq_worker_sleeping(tsk);
+		else
+			io_wq_worker_sleeping(tsk);
 		preempt_enable_no_resched();
 	}
 
@@ -4122,8 +4126,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 
 static void sched_update_worker(struct task_struct *tsk)
 {
-	if (tsk->flags & PF_WQ_WORKER)
-		wq_worker_running(tsk);
+	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
+		if (tsk->flags & PF_WQ_WORKER)
+			wq_worker_running(tsk);
+		else
+			io_wq_worker_running(tsk);
+	}
 }
 
 asmlinkage __visible void __sched schedule(void)