net/smc: synchronize buffer usage with device

Usage of send buffer "sndbuf" is synced
(a) before filling sndbuf for cpu access
(b) after filling sndbuf for device access

Usage of receive buffer "RMB" is synced
(a) before reading RMB content for cpu access
(b) after reading RMB content for device access
Signed-off-by: NUrsula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

net/smc/af_smc.c

@@ -474,6 +474,7 @@ static int smc_connect_rdma(struct smc_sock *smc)
 			}
 		}
 	}
+	smc_rmb_sync_sg_for_device(&smc->conn);
 
 	rc = smc_clc_send_confirm(smc);
 	if (rc)
@@ -832,6 +833,7 @@ static void smc_listen_work(struct work_struct *work)
 			}
 		}
 	}
+	smc_rmb_sync_sg_for_device(&new_smc->conn);
 
 	rc = smc_clc_send_accept(new_smc, local_contact);
 	if (rc)

net/smc/smc_core.c

@@ -615,6 +615,38 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb)
 	return 0;
 }
 
+void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+			       conn->sndbuf_desc, DMA_TO_DEVICE);
+}
+
+void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+				  conn->sndbuf_desc, DMA_TO_DEVICE);
+}
+
+void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+			       conn->rmb_desc, DMA_FROM_DEVICE);
+}
+
+void smc_rmb_sync_sg_for_device(struct smc_connection *conn)
+{
+	struct smc_link_group *lgr = conn->lgr;
+
+	smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+				  conn->rmb_desc, DMA_FROM_DEVICE);
+}
+
 /* create the send and receive buffer for an SMC socket;
  * receive buffers are called RMBs;
  * (even though the SMC protocol allows more than one RMB-element per RMB,

net/smc/smc_core.h

@@ -189,4 +189,8 @@ void smc_lgr_terminate(struct smc_link_group *lgr);
 int smc_buf_create(struct smc_sock *smc);
 int smc_rmb_rtoken_handling(struct smc_connection *conn,
 			    struct smc_clc_msg_accept_confirm *clc);
+void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn);
+void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
+void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
+void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
 #endif

net/smc/smc_ib.c

@@ -13,6 +13,7 @@
 
 #include <linux/random.h>
 #include <linux/workqueue.h>
+#include <linux/scatterlist.h>
 #include <rdma/ib_verbs.h>
 
 #include "smc_pnet.h"
@@ -295,6 +296,46 @@ int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
 	return 0;
 }
 
+/* synchronize buffer usage for cpu access */
+void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
+			    struct smc_buf_desc *buf_slot,
+			    enum dma_data_direction data_direction)
+{
+	struct scatterlist *sg;
+	unsigned int i;
+
+	/* for now there is just one DMA address */
+	for_each_sg(buf_slot->sgt[SMC_SINGLE_LINK].sgl, sg,
+		    buf_slot->sgt[SMC_SINGLE_LINK].nents, i) {
+		if (!sg_dma_len(sg))
+			break;
+		ib_dma_sync_single_for_cpu(smcibdev->ibdev,
+					   sg_dma_address(sg),
+					   sg_dma_len(sg),
+					   data_direction);
+	}
+}
+
+/* synchronize buffer usage for device access */
+void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
+			       struct smc_buf_desc *buf_slot,
+			       enum dma_data_direction data_direction)
+{
+	struct scatterlist *sg;
+	unsigned int i;
+
+	/* for now there is just one DMA address */
+	for_each_sg(buf_slot->sgt[SMC_SINGLE_LINK].sgl, sg,
+		    buf_slot->sgt[SMC_SINGLE_LINK].nents, i) {
+		if (!sg_dma_len(sg))
+			break;
+		ib_dma_sync_single_for_device(smcibdev->ibdev,
+					      sg_dma_address(sg),
+					      sg_dma_len(sg),
+					      data_direction);
+	}
+}
+
 /* 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,

net/smc/smc_ib.h

@@ -68,4 +68,10 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
 int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
 			     struct smc_buf_desc *buf_slot);
 void smc_ib_put_memory_region(struct ib_mr *mr);
+void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
+			    struct smc_buf_desc *buf_slot,
+			    enum dma_data_direction data_direction);
+void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
+			       struct smc_buf_desc *buf_slot,
+			       enum dma_data_direction data_direction);
 #endif

net/smc/smc_rx.c

@@ -170,6 +170,7 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
 				  copylen, conn->rmbe_size - cons.count);
 		chunk_len_sum = chunk_len;
 		chunk_off = cons.count;
+		smc_rmb_sync_sg_for_cpu(conn);
 		for (chunk = 0; chunk < 2; chunk++) {
 			if (!(flags & MSG_TRUNC)) {
 				rc = memcpy_to_msg(msg, rcvbuf_base + chunk_off,
@@ -177,6 +178,7 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
 				if (rc) {
 					if (!read_done)
 						read_done = -EFAULT;
+					smc_rmb_sync_sg_for_device(conn);
 					goto out;
 				}
 			}
@@ -190,6 +192,7 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
 			chunk_len_sum += chunk_len;
 			chunk_off = 0; /* modulo offset in recv ring buffer */
 		}
+		smc_rmb_sync_sg_for_device(conn);
 
 		/* update cursors */
 		if (!(flags & MSG_PEEK)) {

net/smc/smc_tx.c

@@ -174,10 +174,12 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 				  copylen, conn->sndbuf_size - tx_cnt_prep);
 		chunk_len_sum = chunk_len;
 		chunk_off = tx_cnt_prep;
+		smc_sndbuf_sync_sg_for_cpu(conn);
 		for (chunk = 0; chunk < 2; chunk++) {
 			rc = memcpy_from_msg(sndbuf_base + chunk_off,
 					     msg, chunk_len);
 			if (rc) {
+				smc_sndbuf_sync_sg_for_device(conn);
 				if (send_done)
 					return send_done;
 				goto out_err;
@@ -192,6 +194,7 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 			chunk_len_sum += chunk_len;
 			chunk_off = 0; /* modulo offset in send ring buffer */
 		}
+		smc_sndbuf_sync_sg_for_device(conn);
 		/* update cursors */
 		smc_curs_add(conn->sndbuf_size, &prep, copylen);
 		smc_curs_write(&conn->tx_curs_prep,