net/smc: introduce sg-logic for RMBs

The follow-on patch makes use of ib_map_mr_sg() when introducing
separate memory regions for RMBs. This function is based on
scatterlists; thus this patch introduces scatterlists for RMBs.

Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: Ursula Braun

net/smc/smc_clc.c

@@ -204,13 +204,13 @@ int smc_clc_send_confirm(struct smc_sock *smc)
 	memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
 	hton24(cclc.qpn, link->roce_qp->qp_num);
 	cclc.rmb_rkey =
-		htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
+		htonl(link->roce_pd->unsafe_global_rkey);
 	cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */
 	cclc.rmbe_alert_token = htonl(conn->alert_token_local);
 	cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
 	cclc.rmbe_size = conn->rmbe_size_short;
-	cclc.rmb_dma_addr =
-		cpu_to_be64((u64)conn->rmb_desc->dma_addr[SMC_SINGLE_LINK]);
+	cclc.rmb_dma_addr = cpu_to_be64(
+		(u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
 	hton24(cclc.psn, link->psn_initial);
 
 	memcpy(cclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
@@ -256,13 +256,13 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
 	memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
 	hton24(aclc.qpn, link->roce_qp->qp_num);
 	aclc.rmb_rkey =
-		htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
+		htonl(link->roce_pd->unsafe_global_rkey);
 	aclc.conn_idx = 1;			/* as long as 1 RMB = 1 RMBE */
 	aclc.rmbe_alert_token = htonl(conn->alert_token_local);
 	aclc.qp_mtu = link->path_mtu;
 	aclc.rmbe_size = conn->rmbe_size_short,
-	aclc.rmb_dma_addr =
-		cpu_to_be64((u64)conn->rmb_desc->dma_addr[SMC_SINGLE_LINK]);
+	aclc.rmb_dma_addr = cpu_to_be64(
+		(u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
 	hton24(aclc.psn, link->psn_initial);
 	memcpy(aclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 

net/smc/smc_core.c

@@ -266,17 +266,16 @@ static void smc_lgr_free_sndbufs(struct smc_link_group *lgr)
 
 static void smc_lgr_free_rmbs(struct smc_link_group *lgr)
 {
-	struct smc_buf_desc *rmb_desc, *bf_desc;
 	struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+	struct smc_buf_desc *rmb_desc, *bf_desc;
 	int i;
 
 	for (i = 0; i < SMC_RMBE_SIZES; i++) {
 		list_for_each_entry_safe(rmb_desc, bf_desc, &lgr->rmbs[i],
 					 list) {
 			list_del(&rmb_desc->list);
-			smc_ib_buf_unmap(lnk->smcibdev,
-					 smc_uncompress_bufsize(i),
-					 rmb_desc, DMA_FROM_DEVICE);
+			smc_ib_buf_unmap_sg(lnk->smcibdev, rmb_desc,
+					    DMA_FROM_DEVICE);
 			kfree(rmb_desc->cpu_addr);
 			kfree(rmb_desc);
 		}
@@ -580,38 +579,54 @@ int smc_rmb_create(struct smc_sock *smc)
 	for (bufsize_short = smc_compress_bufsize(smc->sk.sk_rcvbuf / 2);
 	     bufsize_short >= 0; bufsize_short--) {
 		bufsize = smc_uncompress_bufsize(bufsize_short);
+		if ((1 << get_order(bufsize)) > SG_MAX_SINGLE_ALLOC)
+			continue;
+
 		/* check for reusable rmb_slot in the link group */
 		rmb_desc = smc_rmb_get_slot(lgr, bufsize_short);
 		if (rmb_desc) {
 			memset(rmb_desc->cpu_addr, 0, bufsize);
 			break; /* found reusable slot */
 		}
+
 		/* try to alloc a new RMB */
 		rmb_desc = kzalloc(sizeof(*rmb_desc), GFP_KERNEL);
 		if (!rmb_desc)
 			break; /* give up with -ENOMEM */
-		rmb_desc->cpu_addr = kzalloc(bufsize,
-					     GFP_KERNEL | __GFP_NOWARN |
-					     __GFP_NOMEMALLOC |
-					     __GFP_NORETRY);
+		rmb_desc->cpu_addr =
+			(void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN |
+						 __GFP_NOMEMALLOC |
+						 __GFP_NORETRY | __GFP_ZERO,
+						 get_order(bufsize));
 		if (!rmb_desc->cpu_addr) {
 			kfree(rmb_desc);
 			rmb_desc = NULL;
-			/* if RMB allocation has failed,
-			 * try a smaller one
-			 */
 			continue;
 		}
-		rc = smc_ib_buf_map(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
-				    bufsize, rmb_desc, DMA_FROM_DEVICE);
+		rmb_desc->order = get_order(bufsize);
+
+		rc = sg_alloc_table(&rmb_desc->sgt[SMC_SINGLE_LINK], 1,
+				    GFP_KERNEL);
 		if (rc) {
-			kfree(rmb_desc->cpu_addr);
+			free_pages((unsigned long)rmb_desc->cpu_addr,
+				   rmb_desc->order);
+			kfree(rmb_desc);
+			rmb_desc = NULL;
+			continue;
+		}
+		sg_set_buf(rmb_desc->sgt[SMC_SINGLE_LINK].sgl,
+			   rmb_desc->cpu_addr, bufsize);
+
+		rc = smc_ib_buf_map_sg(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+				       rmb_desc, DMA_FROM_DEVICE);
+		if (rc != 1)  {
+			sg_free_table(&rmb_desc->sgt[SMC_SINGLE_LINK]);
+			free_pages((unsigned long)rmb_desc->cpu_addr,
+				   rmb_desc->order);
 			kfree(rmb_desc);
 			rmb_desc = NULL;
 			continue; /* if mapping failed, try smaller one */
 		}
-		rmb_desc->rkey[SMC_SINGLE_LINK] =
-			lgr->lnk[SMC_SINGLE_LINK].roce_pd->unsafe_global_rkey;
 		rmb_desc->used = 1;
 		write_lock_bh(&lgr->rmbs_lock);
 		list_add(&rmb_desc->list, &lgr->rmbs[bufsize_short]);

net/smc/smc_core.h

@@ -93,10 +93,8 @@ struct smc_buf_desc {
 	u64			dma_addr[SMC_LINKS_PER_LGR_MAX];
 						/* mapped address of buffer */
 	void			*cpu_addr;	/* virtual address of buffer */
-	u32			rkey[SMC_LINKS_PER_LGR_MAX];
-						/* for rmb only:
-						 * rkey provided to peer
-						 */
+	struct sg_table		sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */
+	u32			order;		/* allocation order */
 	u32			used;		/* currently used / unused */
 };
 

net/smc/smc_ib.c

@@ -283,6 +283,37 @@ void smc_ib_buf_unmap(struct smc_ib_device *smcibdev, int buf_size,
 	buf_slot->dma_addr[SMC_SINGLE_LINK] = 0;
 }
 
+/* Map a new TX or RX buffer SG-table to DMA */
+int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev,
+		      struct smc_buf_desc *buf_slot,
+		      enum dma_data_direction data_direction)
+{
+	int mapped_nents;
+
+	mapped_nents = ib_dma_map_sg(smcibdev->ibdev,
+				     buf_slot->sgt[SMC_SINGLE_LINK].sgl,
+				     buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
+				     data_direction);
+	if (!mapped_nents)
+		return -ENOMEM;
+
+	return mapped_nents;
+}
+
+void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
+			 struct smc_buf_desc *buf_slot,
+			 enum dma_data_direction data_direction)
+{
+	if (!buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address)
+		return; /* already unmapped */
+
+	ib_dma_unmap_sg(smcibdev->ibdev,
+			buf_slot->sgt[SMC_SINGLE_LINK].sgl,
+			buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
+			data_direction);
+	buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address = 0;
+}
+
 static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
 {
 	struct net_device *ndev;

net/smc/smc_ib.h

@@ -57,6 +57,12 @@ int smc_ib_buf_map(struct smc_ib_device *smcibdev, int buf_size,
 void smc_ib_buf_unmap(struct smc_ib_device *smcibdev, int bufsize,
 		      struct smc_buf_desc *buf_slot,
 		      enum dma_data_direction data_direction);
+int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev,
+		      struct smc_buf_desc *buf_slot,
+		      enum dma_data_direction data_direction);
+void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
+			 struct smc_buf_desc *buf_slot,
+			 enum dma_data_direction data_direction);
 void smc_ib_dealloc_protection_domain(struct smc_link *lnk);
 int smc_ib_create_protection_domain(struct smc_link *lnk);
 void smc_ib_destroy_queue_pair(struct smc_link *lnk);