block: add a struct io_comp_batch argument to fops->iopoll()

struct io_comp_batch contains a list head and a completion handler, which
will allow completions to more effciently completed batches of IO.

For now, no functional changes in this patch, we just define the
io_comp_batch structure and add the argument to the file_operations iopoll
handler.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-core.c

@@ -1078,7 +1078,7 @@ EXPORT_SYMBOL(submit_bio);
  * Note: the caller must either be the context that submitted @bio, or
  * be in a RCU critical section to prevent freeing of @bio.
  */
-int bio_poll(struct bio *bio, unsigned int flags)
+int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 {
 	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
 	blk_qc_t cookie = READ_ONCE(bio->bi_cookie);
@@ -1096,7 +1096,7 @@ int bio_poll(struct bio *bio, unsigned int flags)
 	if (WARN_ON_ONCE(!queue_is_mq(q)))
 		ret = 0;	/* not yet implemented, should not happen */
 	else
-		ret = blk_mq_poll(q, cookie, flags);
+		ret = blk_mq_poll(q, cookie, iob, flags);
 	blk_queue_exit(q);
 	return ret;
 }
@@ -1106,7 +1106,8 @@ EXPORT_SYMBOL_GPL(bio_poll);
  * Helper to implement file_operations.iopoll.  Requires the bio to be stored
  * in iocb->private, and cleared before freeing the bio.
  */
-int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags)
+int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
+		    unsigned int flags)
 {
 	struct bio *bio;
 	int ret = 0;
@@ -1134,7 +1135,7 @@ int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags)
 	rcu_read_lock();
 	bio = READ_ONCE(kiocb->private);
 	if (bio && bio->bi_bdev)
-		ret = bio_poll(bio, flags);
+		ret = bio_poll(bio, iob, flags);
 	rcu_read_unlock();
 
 	return ret;

block/blk-exec.c

@@ -77,7 +77,7 @@ static bool blk_rq_is_poll(struct request *rq)
 static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
 {
 	do {
-		bio_poll(rq->bio, 0);
+		bio_poll(rq->bio, NULL, 0);
 		cond_resched();
 	} while (!completion_done(wait));
 }

block/blk-mq.c

@@ -4174,14 +4174,14 @@ static bool blk_mq_poll_hybrid(struct request_queue *q, blk_qc_t qc)
 }
 
 static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
-		unsigned int flags)
+			       struct io_comp_batch *iob, unsigned int flags)
 {
 	struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, cookie);
 	long state = get_current_state();
 	int ret;
 
 	do {
-		ret = q->mq_ops->poll(hctx);
+		ret = q->mq_ops->poll(hctx, iob);
 		if (ret > 0) {
 			__set_current_state(TASK_RUNNING);
 			return ret;
@@ -4201,14 +4201,15 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
 	return 0;
 }
 
-int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags)
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
+		unsigned int flags)
 {
 	if (!(flags & BLK_POLL_NOSLEEP) &&
 	    q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
 		if (blk_mq_poll_hybrid(q, cookie))
 			return 1;
 	}
-	return blk_mq_poll_classic(q, cookie, flags);
+	return blk_mq_poll_classic(q, cookie, iob, flags);
 }
 
 unsigned int blk_mq_rq_cpu(struct request *rq)

block/blk-mq.h

@@ -31,7 +31,8 @@ struct blk_mq_ctx {
 } ____cacheline_aligned_in_smp;
 
 void blk_mq_submit_bio(struct bio *bio);
-int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags);
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
+		unsigned int flags);
 void blk_mq_exit_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);

block/fops.c

@@ -105,7 +105,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		if (!READ_ONCE(bio.bi_private))
 			break;
-		if (!(iocb->ki_flags & IOCB_HIPRI) || !bio_poll(&bio, 0))
+		if (!(iocb->ki_flags & IOCB_HIPRI) || !bio_poll(&bio, NULL, 0))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -291,7 +291,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		if (!READ_ONCE(dio->waiter))
 			break;
 
-		if (!do_poll || !bio_poll(bio, 0))
+		if (!do_poll || !bio_poll(bio, NULL, 0))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);

drivers/block/rnbd/rnbd-clt.c

@@ -1176,7 +1176,7 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
-static int rnbd_rdma_poll(struct blk_mq_hw_ctx *hctx)
+static int rnbd_rdma_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct rnbd_queue *q = hctx->driver_data;
 	struct rnbd_clt_dev *dev = q->dev;

drivers/nvme/host/pci.c

@@ -1092,7 +1092,7 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
 	enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
 }
 
-static int nvme_poll(struct blk_mq_hw_ctx *hctx)
+static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct nvme_queue *nvmeq = hctx->driver_data;
 	bool found;
@@ -1274,7 +1274,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	 * Did we miss an interrupt?
 	 */
 	if (test_bit(NVMEQ_POLLED, &nvmeq->flags))
-		nvme_poll(req->mq_hctx);
+		nvme_poll(req->mq_hctx, NULL);
 	else
 		nvme_poll_irqdisable(nvmeq);
 

drivers/nvme/host/rdma.c

@@ -2106,7 +2106,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
-static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx)
+static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct nvme_rdma_queue *queue = hctx->driver_data;
 

drivers/nvme/host/tcp.c

@@ -2429,7 +2429,7 @@ static int nvme_tcp_map_queues(struct blk_mq_tag_set *set)
 	return 0;
 }
 
-static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx)
+static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct nvme_tcp_queue *queue = hctx->driver_data;
 	struct sock *sk = queue->sock->sk;

drivers/scsi/scsi_lib.c

@@ -1784,7 +1784,7 @@ static void scsi_mq_exit_request(struct blk_mq_tag_set *set, struct request *rq,
 }
 
 
-static int scsi_mq_poll(struct blk_mq_hw_ctx *hctx)
+static int scsi_mq_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct Scsi_Host *shost = hctx->driver_data;
 

fs/io_uring.c

@@ -2483,7 +2483,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		if (!list_empty(&done))
 			break;
 
-		ret = kiocb->ki_filp->f_op->iopoll(kiocb, poll_flags);
+		ret = kiocb->ki_filp->f_op->iopoll(kiocb, NULL, poll_flags);
 		if (unlikely(ret < 0))
 			return ret;
 		else if (ret)

fs/iomap/direct-io.c

@@ -630,7 +630,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 				break;
 
 			if (!dio->submit.poll_bio ||
-			    !bio_poll(dio->submit.poll_bio, 0))
+			    !bio_poll(dio->submit.poll_bio, NULL, 0))
 				blk_io_schedule();
 		}
 		__set_current_state(TASK_RUNNING);

include/linux/blk-mq.h

@@ -532,7 +532,7 @@ struct blk_mq_ops {
 	/**
 	 * @poll: Called to poll for completion of a specific tag.
 	 */
-	int (*poll)(struct blk_mq_hw_ctx *);
+	int (*poll)(struct blk_mq_hw_ctx *, struct io_comp_batch *);
 
 	/**
 	 * @complete: Mark the request as complete.

include/linux/blkdev.h

@@ -569,8 +569,9 @@ blk_status_t errno_to_blk_status(int errno);
 #define BLK_POLL_ONESHOT		(1 << 0)
 /* do not sleep to wait for the expected completion time */
 #define BLK_POLL_NOSLEEP		(1 << 1)
-int bio_poll(struct bio *bio, unsigned int flags);
-int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags);
+int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags);
+int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
+			unsigned int flags);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
@@ -1298,6 +1299,14 @@ int fsync_bdev(struct block_device *bdev);
 int freeze_bdev(struct block_device *bdev);
 int thaw_bdev(struct block_device *bdev);
 
+struct io_comp_batch {
+	struct request *req_list;
+	bool need_ts;
+	void (*complete)(struct io_comp_batch *);
+};
+
+#define DEFINE_IO_COMP_BATCH(name)	struct io_comp_batch name = { }
+
 #define rq_list_add(listptr, rq)	do {		\
 	(rq)->rq_next = *(listptr);			\
 	*(listptr) = rq;				\

include/linux/fs.h

@@ -48,6 +48,7 @@
 struct backing_dev_info;
 struct bdi_writeback;
 struct bio;
+struct io_comp_batch;
 struct export_operations;
 struct fiemap_extent_info;
 struct hd_geometry;
@@ -2071,7 +2072,8 @@ struct file_operations {
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
-	int (*iopoll)(struct kiocb *kiocb, unsigned int flags);
+	int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *,
+			unsigned int flags);
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);

mm/page_io.c

@@ -424,7 +424,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		if (!READ_ONCE(bio->bi_private))
 			break;
 
-		if (!bio_poll(bio, 0))
+		if (!bio_poll(bio, NULL, 0))
 			blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);