Merge tag 'for-6.1/passthrough-2022-10-04' of git://git.kernel.dk/linux

Pull passthrough updates from Jens Axboe:
 "With these changes, passthrough NVMe support over io_uring now
  performs at the same level as block device O_DIRECT, and in many cases
  6-8% better.

  This contains:

   - Add support for fixed buffers for passthrough (Anuj, Kanchan)

   - Enable batched allocations and freeing on passthrough, similarly to
     what we support on the normal storage path (me)

   - Fix from Geert fixing an issue with !CONFIG_IO_URING"

* tag 'for-6.1/passthrough-2022-10-04' of git://git.kernel.dk/linux:
  io_uring: Add missing inline to io_uring_cmd_import_fixed() dummy
  nvme: wire up fixed buffer support for nvme passthrough
  nvme: pass ubuffer as an integer
  block: extend functionality to map bvec iterator
  block: factor out blk_rq_map_bio_alloc helper
  block: rename bio_map_put to blk_mq_map_bio_put
  nvme: refactor nvme_alloc_request
  nvme: refactor nvme_add_user_metadata
  nvme: Use blk_rq_map_user_io helper
  scsi: Use blk_rq_map_user_io helper
  block: add blk_rq_map_user_io
  io_uring: introduce fixed buffer support for io_uring_cmd
  io_uring: add io_uring_cmd_import_fixed
  nvme: enable batched completions of passthrough IO
  nvme: split out metadata vs non metadata end_io uring_cmd completions
  block: allow end_io based requests in the completion batch handling
  block: change request end_io handler to pass back a return value
  block: enable batched allocation for blk_mq_alloc_request()
  block: kill deprecated BUG_ON() in the flush handling

block/blk-flush.c

@@ -205,7 +205,6 @@ static void blk_flush_complete_seq(struct request *rq,
 		 * flush data request completion path.  Restore @rq for
 		 * normal completion and end it.
 		 */
-		BUG_ON(!list_empty(&rq->queuelist));
 		list_del_init(&rq->flush.list);
 		blk_flush_restore_request(rq);
 		blk_mq_end_request(rq, error);
@@ -218,7 +217,8 @@ static void blk_flush_complete_seq(struct request *rq,
 	blk_kick_flush(q, fq, cmd_flags);
 }
 
-static void flush_end_io(struct request *flush_rq, blk_status_t error)
+static enum rq_end_io_ret flush_end_io(struct request *flush_rq,
+				       blk_status_t error)
 {
 	struct request_queue *q = flush_rq->q;
 	struct list_head *running;
@@ -232,7 +232,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	if (!req_ref_put_and_test(flush_rq)) {
 		fq->rq_status = error;
 		spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
-		return;
+		return RQ_END_IO_NONE;
 	}
 
 	blk_account_io_flush(flush_rq);
@@ -269,6 +269,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	}
 
 	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
+	return RQ_END_IO_NONE;
 }
 
 bool is_flush_rq(struct request *rq)
@@ -354,7 +355,8 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	blk_flush_queue_rq(flush_rq, false);
 }
 
-static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
+static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq,
+					       blk_status_t error)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
@@ -376,6 +378,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
 	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 
 	blk_mq_sched_restart(hctx);
+	return RQ_END_IO_NONE;
 }
 
 /**

block/blk-map.c

@@ -231,7 +231,7 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 	return ret;
 }
 
-static void bio_map_put(struct bio *bio)
+static void blk_mq_map_bio_put(struct bio *bio)
 {
 	if (bio->bi_opf & REQ_ALLOC_CACHE) {
 		bio_put(bio);
@@ -241,17 +241,10 @@ static void bio_map_put(struct bio *bio)
 	}
 }
 
-static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
-		gfp_t gfp_mask)
+static struct bio *blk_rq_map_bio_alloc(struct request *rq,
+		unsigned int nr_vecs, gfp_t gfp_mask)
 {
-	unsigned int max_sectors = queue_max_hw_sectors(rq->q);
-	unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS);
 	struct bio *bio;
-	int ret;
-	int j;
-
-	if (!iov_iter_count(iter))
-		return -EINVAL;
 
 	if (rq->cmd_flags & REQ_POLLED) {
 		blk_opf_t opf = rq->cmd_flags | REQ_ALLOC_CACHE;
@@ -259,13 +252,31 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 		bio = bio_alloc_bioset(NULL, nr_vecs, opf, gfp_mask,
 					&fs_bio_set);
 		if (!bio)
-			return -ENOMEM;
+			return NULL;
 	} else {
 		bio = bio_kmalloc(nr_vecs, gfp_mask);
 		if (!bio)
-			return -ENOMEM;
+			return NULL;
 		bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq));
 	}
+	return bio;
+}
+
+static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
+		gfp_t gfp_mask)
+{
+	unsigned int max_sectors = queue_max_hw_sectors(rq->q);
+	unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS);
+	struct bio *bio;
+	int ret;
+	int j;
+
+	if (!iov_iter_count(iter))
+		return -EINVAL;
+
+	bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask);
+	if (bio == NULL)
+		return -ENOMEM;
 
 	while (iov_iter_count(iter)) {
 		struct page **pages, *stack_pages[UIO_FASTIOV];
@@ -331,7 +342,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 
  out_unmap:
 	bio_release_pages(bio, false);
-	bio_map_put(bio);
+	blk_mq_map_bio_put(bio);
 	return ret;
 }
 
@@ -537,6 +548,62 @@ int blk_rq_append_bio(struct request *rq, struct bio *bio)
 }
 EXPORT_SYMBOL(blk_rq_append_bio);
 
+/* Prepare bio for passthrough IO given ITER_BVEC iter */
+static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
+{
+	struct request_queue *q = rq->q;
+	size_t nr_iter = iov_iter_count(iter);
+	size_t nr_segs = iter->nr_segs;
+	struct bio_vec *bvecs, *bvprvp = NULL;
+	struct queue_limits *lim = &q->limits;
+	unsigned int nsegs = 0, bytes = 0;
+	struct bio *bio;
+	size_t i;
+
+	if (!nr_iter || (nr_iter >> SECTOR_SHIFT) > queue_max_hw_sectors(q))
+		return -EINVAL;
+	if (nr_segs > queue_max_segments(q))
+		return -EINVAL;
+
+	/* no iovecs to alloc, as we already have a BVEC iterator */
+	bio = blk_rq_map_bio_alloc(rq, 0, GFP_KERNEL);
+	if (bio == NULL)
+		return -ENOMEM;
+
+	bio_iov_bvec_set(bio, (struct iov_iter *)iter);
+	blk_rq_bio_prep(rq, bio, nr_segs);
+
+	/* loop to perform a bunch of sanity checks */
+	bvecs = (struct bio_vec *)iter->bvec;
+	for (i = 0; i < nr_segs; i++) {
+		struct bio_vec *bv = &bvecs[i];
+
+		/*
+		 * If the queue doesn't support SG gaps and adding this
+		 * offset would create a gap, fallback to copy.
+		 */
+		if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv->bv_offset)) {
+			blk_mq_map_bio_put(bio);
+			return -EREMOTEIO;
+		}
+		/* check full condition */
+		if (nsegs >= nr_segs || bytes > UINT_MAX - bv->bv_len)
+			goto put_bio;
+		if (bytes + bv->bv_len > nr_iter)
+			goto put_bio;
+		if (bv->bv_offset + bv->bv_len > PAGE_SIZE)
+			goto put_bio;
+
+		nsegs++;
+		bytes += bv->bv_len;
+		bvprvp = bv;
+	}
+	return 0;
+put_bio:
+	blk_mq_map_bio_put(bio);
+	return -EINVAL;
+}
+
 /**
  * blk_rq_map_user_iov - map user data to a request, for passthrough requests
  * @q:		request queue where request should be inserted
@@ -556,24 +623,35 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			struct rq_map_data *map_data,
 			const struct iov_iter *iter, gfp_t gfp_mask)
 {
-	bool copy = false;
+	bool copy = false, map_bvec = false;
 	unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
 	struct bio *bio = NULL;
 	struct iov_iter i;
 	int ret = -EINVAL;
 
-	if (!iter_is_iovec(iter))
-		goto fail;
-
 	if (map_data)
 		copy = true;
 	else if (blk_queue_may_bounce(q))
 		copy = true;
 	else if (iov_iter_alignment(iter) & align)
 		copy = true;
+	else if (iov_iter_is_bvec(iter))
+		map_bvec = true;
+	else if (!iter_is_iovec(iter))
+		copy = true;
 	else if (queue_virt_boundary(q))
 		copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter);
 
+	if (map_bvec) {
+		ret = blk_rq_map_user_bvec(rq, iter);
+		if (!ret)
+			return 0;
+		if (ret != -EREMOTEIO)
+			goto fail;
+		/* fall back to copying the data on limits mismatches */
+		copy = true;
+	}
+
 	i = *iter;
 	do {
 		if (copy)
@@ -611,6 +689,42 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(blk_rq_map_user);
 
+int blk_rq_map_user_io(struct request *req, struct rq_map_data *map_data,
+		void __user *ubuf, unsigned long buf_len, gfp_t gfp_mask,
+		bool vec, int iov_count, bool check_iter_count, int rw)
+{
+	int ret = 0;
+
+	if (vec) {
+		struct iovec fast_iov[UIO_FASTIOV];
+		struct iovec *iov = fast_iov;
+		struct iov_iter iter;
+
+		ret = import_iovec(rw, ubuf, iov_count ? iov_count : buf_len,
+				UIO_FASTIOV, &iov, &iter);
+		if (ret < 0)
+			return ret;
+
+		if (iov_count) {
+			/* SG_IO howto says that the shorter of the two wins */
+			iov_iter_truncate(&iter, buf_len);
+			if (check_iter_count && !iov_iter_count(&iter)) {
+				kfree(iov);
+				return -EINVAL;
+			}
+		}
+
+		ret = blk_rq_map_user_iov(req->q, req, map_data, &iter,
+				gfp_mask);
+		kfree(iov);
+	} else if (buf_len) {
+		ret = blk_rq_map_user(req->q, req, map_data, ubuf, buf_len,
+				gfp_mask);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(blk_rq_map_user_io);
+
 /**
  * blk_rq_unmap_user - unmap a request with user data
  * @bio:	       start of bio list
@@ -636,7 +750,7 @@ int blk_rq_unmap_user(struct bio *bio)
 
 		next_bio = bio;
 		bio = bio->bi_next;
-		bio_map_put(next_bio);
+		blk_mq_map_bio_put(next_bio);
 	}
 
 	return ret;

block/blk-mq.c

@@ -510,16 +510,77 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 					alloc_time_ns);
 }
 
+static struct request *blk_mq_rq_cache_fill(struct request_queue *q,
+					    struct blk_plug *plug,
+					    blk_opf_t opf,
+					    blk_mq_req_flags_t flags)
+{
+	struct blk_mq_alloc_data data = {
+		.q		= q,
+		.flags		= flags,
+		.cmd_flags	= opf,
+		.nr_tags	= plug->nr_ios,
+		.cached_rq	= &plug->cached_rq,
+	};
+	struct request *rq;
+
+	if (blk_queue_enter(q, flags))
+		return NULL;
+
+	plug->nr_ios = 1;
+
+	rq = __blk_mq_alloc_requests(&data);
+	if (unlikely(!rq))
+		blk_queue_exit(q);
+	return rq;
+}
+
+static struct request *blk_mq_alloc_cached_request(struct request_queue *q,
+						   blk_opf_t opf,
+						   blk_mq_req_flags_t flags)
+{
+	struct blk_plug *plug = current->plug;
+	struct request *rq;
+
+	if (!plug)
+		return NULL;
+	if (rq_list_empty(plug->cached_rq)) {
+		if (plug->nr_ios == 1)
+			return NULL;
+		rq = blk_mq_rq_cache_fill(q, plug, opf, flags);
+		if (rq)
+			goto got_it;
+		return NULL;
+	}
+	rq = rq_list_peek(&plug->cached_rq);
+	if (!rq || rq->q != q)
+		return NULL;
+
+	if (blk_mq_get_hctx_type(opf) != rq->mq_hctx->type)
+		return NULL;
+	if (op_is_flush(rq->cmd_flags) != op_is_flush(opf))
+		return NULL;
+
+	plug->cached_rq = rq_list_next(rq);
+got_it:
+	rq->cmd_flags = opf;
+	INIT_LIST_HEAD(&rq->queuelist);
+	return rq;
+}
+
 struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
 		blk_mq_req_flags_t flags)
 {
+	struct request *rq;
+
+	rq = blk_mq_alloc_cached_request(q, opf, flags);
+	if (!rq) {
 		struct blk_mq_alloc_data data = {
 			.q		= q,
 			.flags		= flags,
 			.cmd_flags	= opf,
 			.nr_tags	= 1,
 		};
-	struct request *rq;
 		int ret;
 
 		ret = blk_queue_enter(q, flags);
@@ -529,6 +590,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
 		rq = __blk_mq_alloc_requests(&data);
 		if (!rq)
 			goto out_queue_exit;
+	}
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
@@ -761,8 +823,10 @@ static void blk_complete_request(struct request *req)
 	 * can find how many bytes remain in the request
 	 * later.
 	 */
+	if (!req->end_io) {
 		req->bio = NULL;
 		req->__data_len = 0;
+	}
 }
 
 /**
@@ -939,7 +1003,8 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 
 	if (rq->end_io) {
 		rq_qos_done(rq->q, rq);
-		rq->end_io(rq, error);
+		if (rq->end_io(rq, error) == RQ_END_IO_FREE)
+			blk_mq_free_request(rq);
 	} else {
 		blk_mq_free_request(rq);
 	}
@@ -992,6 +1057,13 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob)
 
 		rq_qos_done(rq->q, rq);
 
+		/*
+		 * If end_io handler returns NONE, then it still has
+		 * ownership of the request.
+		 */
+		if (rq->end_io && rq->end_io(rq, 0) == RQ_END_IO_NONE)
+			continue;
+
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
 		if (!req_ref_put_and_test(rq))
 			continue;
@@ -1233,12 +1305,13 @@ struct blk_rq_wait {
 	blk_status_t ret;
 };
 
-static void blk_end_sync_rq(struct request *rq, blk_status_t ret)
+static enum rq_end_io_ret blk_end_sync_rq(struct request *rq, blk_status_t ret)
 {
 	struct blk_rq_wait *wait = rq->end_io_data;
 
 	wait->ret = ret;
 	complete(&wait->done);
+	return RQ_END_IO_NONE;
 }
 
 bool blk_rq_is_poll(struct request *rq)
@@ -1472,10 +1545,12 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 
 void blk_mq_put_rq_ref(struct request *rq)
 {
-	if (is_flush_rq(rq))
-		rq->end_io(rq, 0);
-	else if (req_ref_put_and_test(rq))
+	if (is_flush_rq(rq)) {
+		if (rq->end_io(rq, 0) == RQ_END_IO_FREE)
+			blk_mq_free_request(rq);
+	} else if (req_ref_put_and_test(rq)) {
 		__blk_mq_free_request(rq);
+	}
 }
 
 static bool blk_mq_check_expired(struct request *rq, void *priv)

drivers/md/dm-rq.c

@@ -292,11 +292,13 @@ static void dm_kill_unmapped_request(struct request *rq, blk_status_t error)
 	dm_complete_request(rq, error);
 }
 
-static void end_clone_request(struct request *clone, blk_status_t error)
+static enum rq_end_io_ret end_clone_request(struct request *clone,
+					    blk_status_t error)
 {
 	struct dm_rq_target_io *tio = clone->end_io_data;
 
 	dm_complete_request(tio->orig, error);
+	return RQ_END_IO_NONE;
 }
 
 static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,

drivers/nvme/host/core.c

@@ -1172,7 +1172,8 @@ static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ / 2);
 }
 
-static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
+static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
+						 blk_status_t status)
 {
 	struct nvme_ctrl *ctrl = rq->end_io_data;
 	unsigned long flags;
@@ -1184,7 +1185,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
 		dev_err(ctrl->device,
 			"failed nvme_keep_alive_end_io error=%d\n",
 				status);
-		return;
+		return RQ_END_IO_NONE;
 	}
 
 	ctrl->comp_seen = false;
@@ -1195,6 +1196,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (startka)
 		nvme_queue_keep_alive_work(ctrl);
+	return RQ_END_IO_NONE;
 }
 
 static void nvme_keep_alive_work(struct work_struct *work)

drivers/nvme/host/pci.c

@@ -1268,7 +1268,7 @@ static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid)
 	return adapter_delete_queue(dev, nvme_admin_delete_sq, sqid);
 }
 
-static void abort_endio(struct request *req, blk_status_t error)
+static enum rq_end_io_ret abort_endio(struct request *req, blk_status_t error)
 {
 	struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
 
@@ -1276,6 +1276,7 @@ static void abort_endio(struct request *req, blk_status_t error)
 		 "Abort status: 0x%x", nvme_req(req)->status);
 	atomic_inc(&nvmeq->dev->ctrl.abort_limit);
 	blk_mq_free_request(req);
+	return RQ_END_IO_NONE;
 }
 
 static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
@@ -2447,22 +2448,25 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	return result;
 }
 
-static void nvme_del_queue_end(struct request *req, blk_status_t error)
+static enum rq_end_io_ret nvme_del_queue_end(struct request *req,
+					     blk_status_t error)
 {
 	struct nvme_queue *nvmeq = req->end_io_data;
 
 	blk_mq_free_request(req);
 	complete(&nvmeq->delete_done);
+	return RQ_END_IO_NONE;
 }
 
-static void nvme_del_cq_end(struct request *req, blk_status_t error)
+static enum rq_end_io_ret nvme_del_cq_end(struct request *req,
+					  blk_status_t error)
 {
 	struct nvme_queue *nvmeq = req->end_io_data;
 
 	if (error)
 		set_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags);
 
-	nvme_del_queue_end(req, error);
+	return nvme_del_queue_end(req, error);
 }
 
 static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)

drivers/nvme/target/passthru.c

@@ -245,7 +245,7 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
 		nvme_passthru_end(ctrl, effects, req->cmd, status);
 }
 
-static void nvmet_passthru_req_done(struct request *rq,
+static enum rq_end_io_ret nvmet_passthru_req_done(struct request *rq,
 						  blk_status_t blk_status)
 {
 	struct nvmet_req *req = rq->end_io_data;
@@ -253,6 +253,7 @@ static void nvmet_passthru_req_done(struct request *rq,
 	req->cqe->result = nvme_req(rq)->result;
 	nvmet_req_complete(req, nvme_req(rq)->status);
 	blk_mq_free_request(rq);
+	return RQ_END_IO_NONE;
 }
 
 static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)

drivers/scsi/scsi_error.c

@@ -2004,9 +2004,11 @@ enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *scmd)
 	}
 }
 
-static void eh_lock_door_done(struct request *req, blk_status_t status)
+static enum rq_end_io_ret eh_lock_door_done(struct request *req,
+					    blk_status_t status)
 {
 	blk_mq_free_request(req);
+	return RQ_END_IO_NONE;
 }
 
 /**

drivers/scsi/scsi_ioctl.c

@@ -449,25 +449,9 @@ static int sg_io(struct scsi_device *sdev, struct sg_io_hdr *hdr, fmode_t mode)
 	if (ret < 0)
 		goto out_put_request;
 
-	ret = 0;
-	if (hdr->iovec_count && hdr->dxfer_len) {
-		struct iov_iter i;
-		struct iovec *iov = NULL;
-
-		ret = import_iovec(rq_data_dir(rq), hdr->dxferp,
-				   hdr->iovec_count, 0, &iov, &i);
-		if (ret < 0)
-			goto out_put_request;
-
-		/* SG_IO howto says that the shorter of the two wins */
-		iov_iter_truncate(&i, hdr->dxfer_len);
-
-		ret = blk_rq_map_user_iov(rq->q, rq, NULL, &i, GFP_KERNEL);
-		kfree(iov);
-	} else if (hdr->dxfer_len)
-		ret = blk_rq_map_user(rq->q, rq, NULL, hdr->dxferp,
-				      hdr->dxfer_len, GFP_KERNEL);
-
+	ret = blk_rq_map_user_io(rq, NULL, hdr->dxferp, hdr->dxfer_len,
+			GFP_KERNEL, hdr->iovec_count && hdr->dxfer_len,
+			hdr->iovec_count, 0, rq_data_dir(rq));
 	if (ret)
 		goto out_put_request;
 

drivers/scsi/sg.c

@@ -177,7 +177,7 @@ typedef struct sg_device { /* holds the state of each scsi generic device */
 } Sg_device;
 
 /* tasklet or soft irq callback */
-static void sg_rq_end_io(struct request *rq, blk_status_t status);
+static enum rq_end_io_ret sg_rq_end_io(struct request *rq, blk_status_t status);
 static int sg_start_req(Sg_request *srp, unsigned char *cmd);
 static int sg_finish_rem_req(Sg_request * srp);
 static int sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size);
@@ -1311,7 +1311,7 @@ sg_rq_end_io_usercontext(struct work_struct *work)
  * This function is a "bottom half" handler that is called by the mid
  * level when a command is completed (or has failed).
  */
-static void
+static enum rq_end_io_ret
 sg_rq_end_io(struct request *rq, blk_status_t status)
 {
 	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq);
@@ -1324,11 +1324,11 @@ sg_rq_end_io(struct request *rq, blk_status_t status)
 	int result, resid, done = 1;
 
 	if (WARN_ON(srp->done != 0))
-		return;
+		return RQ_END_IO_NONE;
 
 	sfp = srp->parentfp;
 	if (WARN_ON(sfp == NULL))
-		return;
+		return RQ_END_IO_NONE;
 
 	sdp = sfp->parentdp;
 	if (unlikely(atomic_read(&sdp->detaching)))
@@ -1406,6 +1406,7 @@ sg_rq_end_io(struct request *rq, blk_status_t status)
 		INIT_WORK(&srp->ew.work, sg_rq_end_io_usercontext);
 		schedule_work(&srp->ew.work);
 	}
+	return RQ_END_IO_NONE;
 }
 
 static const struct file_operations sg_fops = {
@@ -1803,26 +1804,8 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 			md->from_user = 0;
 	}
 
-	if (iov_count) {
-		struct iovec *iov = NULL;
-		struct iov_iter i;
-
-		res = import_iovec(rw, hp->dxferp, iov_count, 0, &iov, &i);
-		if (res < 0)
-			return res;
-
-		iov_iter_truncate(&i, hp->dxfer_len);
-		if (!iov_iter_count(&i)) {
-			kfree(iov);
-			return -EINVAL;
-		}
-
-		res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC);
-		kfree(iov);
-	} else
-		res = blk_rq_map_user(q, rq, md, hp->dxferp,
-				      hp->dxfer_len, GFP_ATOMIC);
-
+	res = blk_rq_map_user_io(rq, md, hp->dxferp, hp->dxfer_len,
+			GFP_ATOMIC, iov_count, iov_count, 1, rw);
 	if (!res) {
 		srp->bio = rq->bio;
 

drivers/scsi/st.c

@@ -512,7 +512,8 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
 	atomic64_dec(&STp->stats->in_flight);
 }
 
-static void st_scsi_execute_end(struct request *req, blk_status_t status)
+static enum rq_end_io_ret st_scsi_execute_end(struct request *req,
+					      blk_status_t status)
 {
 	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
 	struct st_request *SRpnt = req->end_io_data;
@@ -532,6 +533,7 @@ static void st_scsi_execute_end(struct request *req, blk_status_t status)
 
 	blk_rq_unmap_user(tmp);
 	blk_mq_free_request(req);
+	return RQ_END_IO_NONE;
 }
 
 static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,

drivers/target/target_core_pscsi.c

@@ -39,7 +39,7 @@ static inline struct pscsi_dev_virt *PSCSI_DEV(struct se_device *dev)
 }
 
 static sense_reason_t pscsi_execute_cmd(struct se_cmd *cmd);
-static void pscsi_req_done(struct request *, blk_status_t);
+static enum rq_end_io_ret pscsi_req_done(struct request *, blk_status_t);
 
 /*	pscsi_attach_hba():
  *
@@ -1002,7 +1002,8 @@ static sector_t pscsi_get_blocks(struct se_device *dev)
 	return 0;
 }
 
-static void pscsi_req_done(struct request *req, blk_status_t status)
+static enum rq_end_io_ret pscsi_req_done(struct request *req,
+					 blk_status_t status)
 {
 	struct se_cmd *cmd = req->end_io_data;
 	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
@@ -1029,6 +1030,7 @@ static void pscsi_req_done(struct request *req, blk_status_t status)
 	}
 
 	blk_mq_free_request(req);
+	return RQ_END_IO_NONE;
 }
 
 static const struct target_backend_ops pscsi_ops = {

drivers/ufs/core/ufshpb.c

@@ -613,14 +613,17 @@ static void ufshpb_activate_subregion(struct ufshpb_lu *hpb,
 	srgn->srgn_state = HPB_SRGN_VALID;
 }
 
-static void ufshpb_umap_req_compl_fn(struct request *req, blk_status_t error)
+static enum rq_end_io_ret ufshpb_umap_req_compl_fn(struct request *req,
+						   blk_status_t error)
 {
 	struct ufshpb_req *umap_req = (struct ufshpb_req *)req->end_io_data;
 
 	ufshpb_put_req(umap_req->hpb, umap_req);
+	return RQ_END_IO_NONE;
 }
 
-static void ufshpb_map_req_compl_fn(struct request *req, blk_status_t error)
+static enum rq_end_io_ret ufshpb_map_req_compl_fn(struct request *req,
+						  blk_status_t error)
 {
 	struct ufshpb_req *map_req = (struct ufshpb_req *) req->end_io_data;
 	struct ufshpb_lu *hpb = map_req->hpb;
@@ -636,6 +639,7 @@ static void ufshpb_map_req_compl_fn(struct request *req, blk_status_t error)
 	spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
 
 	ufshpb_put_map_req(map_req->hpb, map_req);
+	return RQ_END_IO_NONE;
 }
 
 static void ufshpb_set_unmap_cmd(unsigned char *cdb, struct ufshpb_region *rgn)

include/linux/blk-mq.h

@@ -14,7 +14,12 @@ struct blk_flush_queue;
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_DEFAULT_RQ	128
 
-typedef void (rq_end_io_fn)(struct request *, blk_status_t);
+enum rq_end_io_ret {
+	RQ_END_IO_NONE,
+	RQ_END_IO_FREE,
+};
+
+typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t);
 
 /*
  * request flags */
@@ -848,8 +853,9 @@ static inline bool blk_mq_add_to_batch(struct request *req,
 				       struct io_comp_batch *iob, int ioerror,
 				       void (*complete)(struct io_comp_batch *))
 {
-	if (!iob || (req->rq_flags & RQF_ELV) || req->end_io || ioerror)
+	if (!iob || (req->rq_flags & RQF_ELV) || ioerror)
 		return false;
+
 	if (!iob->complete)
 		iob->complete = complete;
 	else if (iob->complete != complete)
@@ -979,6 +985,8 @@ struct rq_map_data {
 
 int blk_rq_map_user(struct request_queue *, struct request *,
 		struct rq_map_data *, void __user *, unsigned long, gfp_t);
+int blk_rq_map_user_io(struct request *, struct rq_map_data *,
+		void __user *, unsigned long, gfp_t, bool, int, bool, int);
 int blk_rq_map_user_iov(struct request_queue *, struct request *,
 		struct rq_map_data *, const struct iov_iter *, gfp_t);
 int blk_rq_unmap_user(struct bio *);

include/linux/io_uring.h

@@ -4,6 +4,7 @@
 
 #include <linux/sched.h>
 #include <linux/xarray.h>
+#include <uapi/linux/io_uring.h>
 
 enum io_uring_cmd_flags {
 	IO_URING_F_COMPLETE_DEFER	= 1,
@@ -27,11 +28,13 @@ struct io_uring_cmd {
 		void *cookie;
 	};
 	u32		cmd_op;
-	u32		pad;
+	u32		flags;
 	u8		pdu[32]; /* available inline for free use */
 };
 
 #if defined(CONFIG_IO_URING)
+int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter, void *ioucmd);
 void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2);
 void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
 			void (*task_work_cb)(struct io_uring_cmd *));
@@ -59,6 +62,11 @@ static inline void io_uring_free(struct task_struct *tsk)
 		__io_uring_free(tsk);
 }
 #else
+static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter, void *ioucmd)
+{
+	return -EOPNOTSUPP;
+}
 static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
 		ssize_t ret2)
 {

include/uapi/linux/io_uring.h

@@ -56,6 +56,7 @@ struct io_uring_sqe {
 		__u32		hardlink_flags;
 		__u32		xattr_flags;
 		__u32		msg_ring_flags;
+		__u32		uring_cmd_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -219,6 +220,14 @@ enum io_uring_op {
 	IORING_OP_LAST,
 };
 
+/*
+ * sqe->uring_cmd_flags
+ * IORING_URING_CMD_FIXED	use registered buffer; pass thig flag
+ *				along with setting sqe->buf_index.
+ */
+#define IORING_URING_CMD_FIXED	(1U << 0)
+
+
 /*
  * sqe->fsync_flags
  */

io_uring/uring_cmd.c

@@ -4,10 +4,12 @@
 #include <linux/file.h>
 #include <linux/io_uring.h>
 #include <linux/security.h>
+#include <linux/nospec.h>
 
 #include <uapi/linux/io_uring.h>
 
 #include "io_uring.h"
+#include "rsrc.h"
 #include "uring_cmd.h"
 
 static void io_uring_cmd_work(struct io_kiocb *req, bool *locked)
@@ -76,8 +78,24 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
 
-	if (sqe->rw_flags || sqe->__pad1)
+	if (sqe->__pad1)
 		return -EINVAL;
+
+	ioucmd->flags = READ_ONCE(sqe->uring_cmd_flags);
+	if (ioucmd->flags & ~IORING_URING_CMD_FIXED)
+		return -EINVAL;
+
+	if (ioucmd->flags & IORING_URING_CMD_FIXED) {
+		struct io_ring_ctx *ctx = req->ctx;
+		u16 index;
+
+		req->buf_index = READ_ONCE(sqe->buf_index);
+		if (unlikely(req->buf_index >= ctx->nr_user_bufs))
+			return -EFAULT;
+		index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
+		req->imu = ctx->user_bufs[index];
+		io_req_set_rsrc_node(req, ctx, 0);
+	}
 	ioucmd->cmd = sqe->cmd;
 	ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
 	return 0;
@@ -129,3 +147,12 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 
 	return IOU_ISSUE_SKIP_COMPLETE;
 }
+
+int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter, void *ioucmd)
+{
+	struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
+
+	return io_import_fixed(rw, iter, req->imu, ubuf, len);
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed);