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 @@ out_bmd:
 	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);
@@ -241,6 +241,27 @@ static void bio_map_put(struct bio *bio)
 	}
 }
 
+static struct bio *blk_rq_map_bio_alloc(struct request *rq,
+		unsigned int nr_vecs, gfp_t gfp_mask)
+{
+	struct bio *bio;
+
+	if (rq->cmd_flags & REQ_POLLED) {
+		blk_opf_t opf = rq->cmd_flags | REQ_ALLOC_CACHE;
+
+		bio = bio_alloc_bioset(NULL, nr_vecs, opf, gfp_mask,
+					&fs_bio_set);
+		if (!bio)
+			return NULL;
+	} else {
+		bio = bio_kmalloc(nr_vecs, gfp_mask);
+		if (!bio)
+			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)
 {
@@ -253,19 +274,9 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 	if (!iov_iter_count(iter))
 		return -EINVAL;
 
-	if (rq->cmd_flags & REQ_POLLED) {
-		blk_opf_t opf = rq->cmd_flags | REQ_ALLOC_CACHE;
-
-		bio = bio_alloc_bioset(NULL, nr_vecs, opf, gfp_mask,
-					&fs_bio_set);
-		if (!bio)
-			return -ENOMEM;
-	} else {
-		bio = bio_kmalloc(nr_vecs, gfp_mask);
-		if (!bio)
-			return -ENOMEM;
-		bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq));
-	}
+	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

@@ -510,25 +510,87 @@ retry:
 					alloc_time_ns);
 }
 
-struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
-		blk_mq_req_flags_t flags)
+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	= 1,
+		.nr_tags	= plug->nr_ios,
+		.cached_rq	= &plug->cached_rq,
 	};
 	struct request *rq;
-	int ret;
 
-	ret = blk_queue_enter(q, flags);
-	if (ret)
-		return ERR_PTR(ret);
+	if (blk_queue_enter(q, flags))
+		return NULL;
+
+	plug->nr_ios = 1;
 
 	rq = __blk_mq_alloc_requests(&data);
-	if (!rq)
-		goto out_queue_exit;
+	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,
+		};
+		int ret;
+
+		ret = blk_queue_enter(q, flags);
+		if (ret)
+			return ERR_PTR(ret);
+
+		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.
 	 */
-	req->bio = NULL;
-	req->__data_len = 0;
+	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)