cifs: Build the RDMA SGE list directly from an iterator

In the depths of the cifs RDMA code, extract part of an iov iterator
directly into an SGE list without going through an intermediate
scatterlist.

Note that this doesn't support extraction from an IOBUF- or UBUF-type
iterator (ie. user-supplied buffer). The assumption is that the higher
layers will extract those to a BVEC-type iterator first and do whatever is
required to stop the pages from going away.

Signed-off-by: David Howells <[e-mail]>
cc: Steve French <[e-mail]>
cc: Shyam Prasad N <[e-mail]>
cc: Rohith Surabattula <[e-mail]>
cc: Tom Talpey <[e-mail]>
cc: Jeff Layton <[e-mail]>
cc: [e-mail]
cc: [e-mail]

Link: https://lore.kernel.org/r/[e-mail]/ # rfc
Link: https://lore.kernel.org/r/[e-mail]/ # rfc
Signed-off-by: Steve French <[e-mail]>

fs/cifs/smbdirect.c

···
 	return rc;
 }
 
-static int smbd_post_send_sgl(struct smbd_connection *info,
-	struct scatterlist *sgl, int data_length, int remaining_data_length)
+static int smbd_post_send_iter(struct smbd_connection *info,
+			       struct iov_iter *iter,
+			       int *_remaining_data_length)
 {
-	int num_sgs;
 	int i, rc;
 	int header_length;
+	int data_length;
 	struct smbd_request *request;
 	struct smbd_data_transfer *packet;
 	int new_credits;
-	struct scatterlist *sg;
 
 wait_credit:
 	/* Wait for send credits. A SMBD packet needs one credit */
···
 	}
 
 	request->info = info;
+	memset(request->sge, 0, sizeof(request->sge));
+
+	/* Fill in the data payload to find out how much data we can add */
+	if (iter) {
+		struct smb_extract_to_rdma extract = {
+			.nr_sge		= 1,
+			.max_sge	= SMBDIRECT_MAX_SEND_SGE,
+			.sge		= request->sge,
+			.device		= info->id->device,
+			.local_dma_lkey	= info->pd->local_dma_lkey,
+			.direction	= DMA_TO_DEVICE,
+		};
+
+		rc = smb_extract_iter_to_rdma(iter, *_remaining_data_length,
+					      &extract);
+		if (rc < 0)
+			goto err_dma;
+		data_length = rc;
+		request->num_sge = extract.nr_sge;
+		*_remaining_data_length -= data_length;
+	} else {
+		data_length = 0;
+		request->num_sge = 1;
+	}
 
 	/* Fill in the packet header */
 	packet = smbd_request_payload(request);
···
 	else
 		packet->data_offset = cpu_to_le32(24);
 	packet->data_length = cpu_to_le32(data_length);
-	packet->remaining_data_length = cpu_to_le32(remaining_data_length);
+	packet->remaining_data_length = cpu_to_le32(*_remaining_data_length);
 	packet->padding = 0;
 
 	log_outgoing(INFO, "credits_requested=%d credits_granted=%d data_offset=%d data_length=%d remaining_data_length=%d\n",
···
 	if (!data_length)
 		header_length = offsetof(struct smbd_data_transfer, padding);
 
-	request->num_sge = 1;
 	request->sge[0].addr = ib_dma_map_single(info->id->device,
 						 (void *)packet,
 						 header_length,
···
 
 	request->sge[0].length = header_length;
 	request->sge[0].lkey = info->pd->local_dma_lkey;
-
-	/* Fill in the packet data payload */
-	num_sgs = sgl ? sg_nents(sgl) : 0;
-	for_each_sg(sgl, sg, num_sgs, i) {
-		request->sge[i+1].addr =
-			ib_dma_map_page(info->id->device, sg_page(sg),
-			       sg->offset, sg->length, DMA_TO_DEVICE);
-		if (ib_dma_mapping_error(
-				info->id->device, request->sge[i+1].addr)) {
-			rc = -EIO;
-			request->sge[i+1].addr = 0;
-			goto err_dma;
-		}
-		request->sge[i+1].length = sg->length;
-		request->sge[i+1].lkey = info->pd->local_dma_lkey;
-		request->num_sge++;
-	}
 
 	rc = smbd_post_send(info, request);
 	if (!rc)
···
  */
 static int smbd_post_send_empty(struct smbd_connection *info)
 {
+	int remaining_data_length = 0;
+
 	info->count_send_empty++;
-	return smbd_post_send_sgl(info, NULL, 0, 0);
+	return smbd_post_send_iter(info, NULL, &remaining_data_length);
 }
 
 /*
···
 }
 
 /*
- * Send the contents of an iterator
- * @iter: The iterator to send
- * @_remaining_data_length: remaining data to send in this payload
- */
-static int smbd_post_send_iter(struct smbd_connection *info,
-			       struct iov_iter *iter,
-			       int *_remaining_data_length)
-{
-	struct scatterlist sgl[SMBDIRECT_MAX_SEND_SGE - 1];
-	unsigned int max_payload = info->max_send_size - sizeof(struct smbd_data_transfer);
-	ssize_t rc;
-
-	/* We're not expecting a user-backed iter */
-	WARN_ON(iov_iter_extract_will_pin(iter));
-
-	do {
-		struct sg_table sgtable = { .sgl = sgl };
-		size_t maxlen = min_t(size_t, *_remaining_data_length, max_payload);
-
-		sg_init_table(sgtable.sgl, ARRAY_SIZE(sgl));
-		rc = netfs_extract_iter_to_sg(iter, maxlen,
-					      &sgtable, ARRAY_SIZE(sgl), 0);
-		if (rc < 0)
-			break;
-		if (WARN_ON_ONCE(sgtable.nents == 0))
-			return -EIO;
-
-		sg_mark_end(&sgl[sgtable.nents - 1]);
-		*_remaining_data_length -= rc;
-		rc = smbd_post_send_sgl(info, sgl, rc, *_remaining_data_length);
-	} while (rc == 0 && iov_iter_count(iter) > 0);
-
-	return rc;
-}
-
-/*
  * Send data to transport
  * Each rqst is transported as a SMBDirect payload
  * rqst: the data to write
···
 	cancel_work_sync(&info->mr_recovery_work);
 	list_for_each_entry_safe(mr, tmp, &info->mr_list, list) {
 		if (mr->state == MR_INVALIDATED)
-			ib_dma_unmap_sg(info->id->device, mr->sgl,
-				mr->sgl_count, mr->dir);
+			ib_dma_unmap_sg(info->id->device, mr->sgt.sgl,
+				mr->sgt.nents, mr->dir);
 		ib_dereg_mr(mr->mr);
-		kfree(mr->sgl);
+		kfree(mr->sgt.sgl);
 		kfree(mr);
 	}
 }
···
 				    info->mr_type, info->max_frmr_depth);
 			goto out;
 		}
-		smbdirect_mr->sgl = kcalloc(
-					info->max_frmr_depth,
-					sizeof(struct scatterlist),
-					GFP_KERNEL);
-		if (!smbdirect_mr->sgl) {
+		smbdirect_mr->sgt.sgl = kcalloc(info->max_frmr_depth,
+						sizeof(struct scatterlist),
+						GFP_KERNEL);
+		if (!smbdirect_mr->sgt.sgl) {
 			log_rdma_mr(ERR, "failed to allocate sgl\n");
 			ib_dereg_mr(smbdirect_mr->mr);
 			goto out;
···
 	list_for_each_entry_safe(smbdirect_mr, tmp, &info->mr_list, list) {
 		list_del(&smbdirect_mr->list);
 		ib_dereg_mr(smbdirect_mr->mr);
-		kfree(smbdirect_mr->sgl);
+		kfree(smbdirect_mr->sgt.sgl);
 		kfree(smbdirect_mr);
 	}
 	return -ENOMEM;
···
 
 /*
  * Transcribe the pages from an iterator into an MR scatterlist.
- * @iter: The iterator to transcribe
- * @_remaining_data_length: remaining data to send in this payload
  */
 static int smbd_iter_to_mr(struct smbd_connection *info,
 			   struct iov_iter *iter,
-			   struct scatterlist *sgl,
-			   unsigned int num_pages)
+			   struct sg_table *sgt,
+			   unsigned int max_sg)
 {
-	struct sg_table sgtable = { .sgl = sgl };
 	int ret;
 
-	sg_init_table(sgl, num_pages);
+	memset(sgt->sgl, 0, max_sg * sizeof(struct scatterlist));
 
-	ret = netfs_extract_iter_to_sg(iter, iov_iter_count(iter),
-				       &sgtable, num_pages, 0);
+	ret = netfs_extract_iter_to_sg(iter, iov_iter_count(iter), sgt, max_sg, 0);
 	WARN_ON(ret < 0);
+	if (sgt->nents > 0)
+		sg_mark_end(&sgt->sgl[sgt->nents - 1]);
 	return ret;
 }
 
···
 	dir = writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 	smbdirect_mr->dir = dir;
 	smbdirect_mr->need_invalidate = need_invalidate;
-	smbdirect_mr->sgl_count = num_pages;
+	smbdirect_mr->sgt.nents = 0;
+	smbdirect_mr->sgt.orig_nents = 0;
 
-	log_rdma_mr(INFO, "num_pages=0x%x count=0x%zx\n",
-		    num_pages, iov_iter_count(iter));
-	smbd_iter_to_mr(info, iter, smbdirect_mr->sgl, num_pages);
+	log_rdma_mr(INFO, "num_pages=0x%x count=0x%zx depth=%u\n",
+		    num_pages, iov_iter_count(iter), info->max_frmr_depth);
+	smbd_iter_to_mr(info, iter, &smbdirect_mr->sgt, info->max_frmr_depth);
 
-	rc = ib_dma_map_sg(info->id->device, smbdirect_mr->sgl, num_pages, dir);
+	rc = ib_dma_map_sg(info->id->device, smbdirect_mr->sgt.sgl,
+			   smbdirect_mr->sgt.nents, dir);
 	if (!rc) {
 		log_rdma_mr(ERR, "ib_dma_map_sg num_pages=%x dir=%x rc=%x\n",
 			num_pages, dir, rc);
 		goto dma_map_error;
 	}
 
-	rc = ib_map_mr_sg(smbdirect_mr->mr, smbdirect_mr->sgl, num_pages,
-		NULL, PAGE_SIZE);
-	if (rc != num_pages) {
+	rc = ib_map_mr_sg(smbdirect_mr->mr, smbdirect_mr->sgt.sgl,
+			  smbdirect_mr->sgt.nents, NULL, PAGE_SIZE);
+	if (rc != smbdirect_mr->sgt.nents) {
 		log_rdma_mr(ERR,
-			"ib_map_mr_sg failed rc = %d num_pages = %x\n",
-			rc, num_pages);
+			"ib_map_mr_sg failed rc = %d nents = %x\n",
+			rc, smbdirect_mr->sgt.nents);
 		goto map_mr_error;
 	}
 
···
 
 	/* If all failed, attempt to recover this MR by setting it MR_ERROR*/
 map_mr_error:
-	ib_dma_unmap_sg(info->id->device, smbdirect_mr->sgl,
-		smbdirect_mr->sgl_count, smbdirect_mr->dir);
+	ib_dma_unmap_sg(info->id->device, smbdirect_mr->sgt.sgl,
+			smbdirect_mr->sgt.nents, smbdirect_mr->dir);
 
 dma_map_error:
 	smbdirect_mr->state = MR_ERROR;
···
 
 	if (smbdirect_mr->state == MR_INVALIDATED) {
 		ib_dma_unmap_sg(
-			info->id->device, smbdirect_mr->sgl,
-			smbdirect_mr->sgl_count,
+			info->id->device, smbdirect_mr->sgt.sgl,
+			smbdirect_mr->sgt.nents,
 			smbdirect_mr->dir);
 		smbdirect_mr->state = MR_READY;
 		if (atomic_inc_return(&info->mr_ready_count) == 1)

fs/cifs/smbdirect.h

···
 	struct list_head	list;
 	enum mr_state		state;
 	struct ib_mr		*mr;
-	struct scatterlist	*sgl;
-	int			sgl_count;
+	struct sg_table		sgt;
 	enum dma_data_direction	dir;
 	union {
 		struct ib_reg_wr	wr;