net/smc: add common buffer size in send and receive buffer descriptors

In addition to the buffer references, SMC currently stores the sizes of
the receive and send buffers in each connection as separate variables.
This patch introduces a buffer length variable in the common buffer
descriptor and uses this length instead.

Signed-off-by: Hans Wippel <[email protected]>
Signed-off-by: Ursula Braun <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: Hans Wippel

net/smc/af_smc.c

@@ -1421,7 +1421,7 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		/* output queue size (not send + not acked) */
 		if (smc->sk.sk_state == SMC_LISTEN)
 			return -EINVAL;
-		answ = smc->conn.sndbuf_size -
+		answ = smc->conn.sndbuf_desc->len -
 					atomic_read(&smc->conn.sndbuf_space);
 		break;
 	case SIOCOUTQNSD:

net/smc/smc.h

@@ -126,9 +126,7 @@ struct smc_connection {
 	int			rtoken_idx;	/* idx to peer RMB rkey/addr */
 
 	struct smc_buf_desc	*sndbuf_desc;	/* send buffer descriptor */
-	int			sndbuf_size;	/* sndbuf size <== sock wmem */
 	struct smc_buf_desc	*rmb_desc;	/* RMBE descriptor */
-	int			rmbe_size;	/* RMBE size <== sock rmem */
 	int			rmbe_size_short;/* compressed notation */
 	int			rmbe_update_limit;
 						/* lower limit for consumer

net/smc/smc_cdc.c

@@ -44,13 +44,13 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 	smc = container_of(cdcpend->conn, struct smc_sock, conn);
 	bh_lock_sock(&smc->sk);
 	if (!wc_status) {
-		diff = smc_curs_diff(cdcpend->conn->sndbuf_size,
+		diff = smc_curs_diff(cdcpend->conn->sndbuf_desc->len,
 				     &cdcpend->conn->tx_curs_fin,
 				     &cdcpend->cursor);
 		/* sndbuf_space is decreased in smc_sendmsg */
 		smp_mb__before_atomic();
 		atomic_add(diff, &cdcpend->conn->sndbuf_space);
-		/* guarantee 0 <= sndbuf_space <= sndbuf_size */
+		/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
 		smp_mb__after_atomic();
 		smc_curs_write(&cdcpend->conn->tx_curs_fin,
 			       smc_curs_read(&cdcpend->cursor, cdcpend->conn),
@@ -198,13 +198,13 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 		smp_mb__after_atomic();
 	}
 
-	diff_prod = smc_curs_diff(conn->rmbe_size, &prod_old,
+	diff_prod = smc_curs_diff(conn->rmb_desc->len, &prod_old,
 				  &conn->local_rx_ctrl.prod);
 	if (diff_prod) {
 		/* bytes_to_rcv is decreased in smc_recvmsg */
 		smp_mb__before_atomic();
 		atomic_add(diff_prod, &conn->bytes_to_rcv);
-		/* guarantee 0 <= bytes_to_rcv <= rmbe_size */
+		/* guarantee 0 <= bytes_to_rcv <= rmb_desc->len */
 		smp_mb__after_atomic();
 		smc->sk.sk_data_ready(&smc->sk);
 	} else if ((conn->local_rx_ctrl.prod_flags.write_blocked) ||

net/smc/smc_core.c

@@ -236,15 +236,12 @@ static int smc_lgr_create(struct smc_sock *smc,
 
 static void smc_buf_unuse(struct smc_connection *conn)
 {
-	if (conn->sndbuf_desc) {
+	if (conn->sndbuf_desc)
 		conn->sndbuf_desc->used = 0;
-		conn->sndbuf_size = 0;
-	}
 	if (conn->rmb_desc) {
 		if (!conn->rmb_desc->regerr) {
 			conn->rmb_desc->reused = 1;
 			conn->rmb_desc->used = 0;
-			conn->rmbe_size = 0;
 		} else {
 			/* buf registration failed, reuse not possible */
 			struct smc_link_group *lgr = conn->lgr;
@@ -616,6 +613,7 @@ static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr,
 		}
 	}
 
+	buf_desc->len = bufsize;
 	return buf_desc;
 }
 
@@ -675,14 +673,12 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb)
 
 	if (is_rmb) {
 		conn->rmb_desc = buf_desc;
-		conn->rmbe_size = bufsize;
 		conn->rmbe_size_short = bufsize_short;
 		smc->sk.sk_rcvbuf = bufsize * 2;
 		atomic_set(&conn->bytes_to_rcv, 0);
 		conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize);
 	} else {
 		conn->sndbuf_desc = buf_desc;
-		conn->sndbuf_size = bufsize;
 		smc->sk.sk_sndbuf = bufsize * 2;
 		atomic_set(&conn->sndbuf_space, bufsize);
 	}

net/smc/smc_core.h

@@ -124,6 +124,7 @@ struct smc_buf_desc {
 	struct list_head	list;
 	void			*cpu_addr;	/* virtual address of buffer */
 	struct page		*pages;
+	int			len;		/* length of buffer */
 	struct sg_table		sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */
 	struct ib_mr		*mr_rx[SMC_LINKS_PER_LGR_MAX];
 						/* for rmb only: memory region

net/smc/smc_diag.c

@@ -101,8 +101,9 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 		struct smc_connection *conn = &smc->conn;
 		struct smc_diag_conninfo cinfo = {
 			.token = conn->alert_token_local,
-			.sndbuf_size = conn->sndbuf_size,
-			.rmbe_size = conn->rmbe_size,
+			.sndbuf_size = conn->sndbuf_desc ?
+				conn->sndbuf_desc->len : 0,
+			.rmbe_size = conn->rmb_desc ? conn->rmb_desc->len : 0,
 			.peer_rmbe_size = conn->peer_rmbe_size,
 
 			.rx_prod.wrap = conn->local_rx_ctrl.prod.wrap,

net/smc/smc_rx.c

@@ -51,7 +51,7 @@ static void smc_rx_wake_up(struct sock *sk)
 static void smc_rx_update_consumer(struct smc_connection *conn,
 				   union smc_host_cursor cons, size_t len)
 {
-	smc_curs_add(conn->rmbe_size, &cons, len);
+	smc_curs_add(conn->rmb_desc->len, &cons, len);
 	smc_curs_write(&conn->local_tx_ctrl.cons, smc_curs_read(&cons, conn),
 		       conn);
 	/* send consumer cursor update if required */
@@ -288,11 +288,11 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
 			       conn);
 		/* subsequent splice() calls pick up where previous left */
 		if (splbytes)
-			smc_curs_add(conn->rmbe_size, &cons, splbytes);
+			smc_curs_add(conn->rmb_desc->len, &cons, splbytes);
 		/* determine chunks where to read from rcvbuf */
 		/* either unwrapped case, or 1st chunk of wrapped case */
-		chunk_len = min_t(size_t,
-				  copylen, conn->rmbe_size - cons.count);
+		chunk_len = min_t(size_t, copylen, conn->rmb_desc->len -
+				  cons.count);
 		chunk_len_sum = chunk_len;
 		chunk_off = cons.count;
 		smc_rmb_sync_sg_for_cpu(conn);
@@ -331,7 +331,7 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
 			/* increased in recv tasklet smc_cdc_msg_rcv() */
 			smp_mb__before_atomic();
 			atomic_sub(copylen, &conn->bytes_to_rcv);
-			/* guarantee 0 <= bytes_to_rcv <= rmbe_size */
+			/* guarantee 0 <= bytes_to_rcv <= rmb_desc->len */
 			smp_mb__after_atomic();
 			if (msg)
 				smc_rx_update_consumer(conn, cons, copylen);

net/smc/smc_tx.c

@@ -180,8 +180,8 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 		tx_cnt_prep = prep.count;
 		/* determine chunks where to write into sndbuf */
 		/* either unwrapped case, or 1st chunk of wrapped case */
-		chunk_len = min_t(size_t,
-				  copylen, conn->sndbuf_size - tx_cnt_prep);
+		chunk_len = min_t(size_t, copylen, conn->sndbuf_desc->len -
+				  tx_cnt_prep);
 		chunk_len_sum = chunk_len;
 		chunk_off = tx_cnt_prep;
 		smc_sndbuf_sync_sg_for_cpu(conn);
@@ -206,21 +206,21 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 		}
 		smc_sndbuf_sync_sg_for_device(conn);
 		/* update cursors */
-		smc_curs_add(conn->sndbuf_size, &prep, copylen);
+		smc_curs_add(conn->sndbuf_desc->len, &prep, copylen);
 		smc_curs_write(&conn->tx_curs_prep,
 			       smc_curs_read(&prep, conn),
 			       conn);
 		/* increased in send tasklet smc_cdc_tx_handler() */
 		smp_mb__before_atomic();
 		atomic_sub(copylen, &conn->sndbuf_space);
-		/* guarantee 0 <= sndbuf_space <= sndbuf_size */
+		/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
 		smp_mb__after_atomic();
 		/* since we just produced more new data into sndbuf,
 		 * trigger sndbuf consumer: RDMA write into peer RMBE and CDC
 		 */
 		if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) &&
 		    (atomic_read(&conn->sndbuf_space) >
-						(conn->sndbuf_size >> 1)))
+						(conn->sndbuf_desc->len >> 1)))
 			/* for a corked socket defer the RDMA writes if there
 			 * is still sufficient sndbuf_space available
 			 */
@@ -286,7 +286,7 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn,
 	atomic_sub(len, &conn->peer_rmbe_space);
 	/* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */
 	smp_mb__after_atomic();
-	smc_curs_add(conn->sndbuf_size, sent, len);
+	smc_curs_add(conn->sndbuf_desc->len, sent, len);
 }
 
 /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit;
@@ -309,7 +309,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 	smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn);
 	smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn);
 	/* cf. wmem_alloc - (snd_max - snd_una) */
-	to_send = smc_curs_diff(conn->sndbuf_size, &sent, &prep);
+	to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
 	if (to_send <= 0)
 		return 0;
 
@@ -351,12 +351,12 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 	dst_len_sum = dst_len;
 	src_off = sent.count;
 	/* dst_len determines the maximum src_len */
-	if (sent.count + dst_len <= conn->sndbuf_size) {
+	if (sent.count + dst_len <= conn->sndbuf_desc->len) {
 		/* unwrapped src case: single chunk of entire dst_len */
 		src_len = dst_len;
 	} else {
 		/* wrapped src case: 2 chunks of sum dst_len; start with 1st: */
-		src_len = conn->sndbuf_size - sent.count;
+		src_len = conn->sndbuf_desc->len - sent.count;
 	}
 	src_len_sum = src_len;
 	dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
@@ -368,8 +368,8 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 			sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
 			num_sges++;
 			src_off += src_len;
-			if (src_off >= conn->sndbuf_size)
-				src_off -= conn->sndbuf_size;
+			if (src_off >= conn->sndbuf_desc->len)
+				src_off -= conn->sndbuf_desc->len;
 						/* modulo in send ring */
 			if (src_len_sum == dst_len)
 				break; /* either on 1st or 2nd iteration */
@@ -387,7 +387,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 		dst_len = len - dst_len; /* remainder */
 		dst_len_sum += dst_len;
 		src_len = min_t(int,
-				dst_len, conn->sndbuf_size - sent.count);
+				dst_len, conn->sndbuf_desc->len - sent.count);
 		src_len_sum = src_len;
 	}
 
@@ -484,11 +484,11 @@ void smc_tx_consumer_update(struct smc_connection *conn)
 	smc_curs_write(&cfed,
 		       smc_curs_read(&conn->rx_curs_confirmed, conn),
 		       conn);
-	to_confirm = smc_curs_diff(conn->rmbe_size, &cfed, &cons);
+	to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
 
 	if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
 	    ((to_confirm > conn->rmbe_update_limit) &&
-	     ((to_confirm > (conn->rmbe_size / 2)) ||
+	     ((to_confirm > (conn->rmb_desc->len / 2)) ||
 	      conn->local_rx_ctrl.prod_flags.write_blocked))) {
 		if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
 		    conn->alert_token_local) { /* connection healthy */

net/smc/smc_tx.h

@@ -24,7 +24,7 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn)
 
 	smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn);
 	smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn);
-	return smc_curs_diff(conn->sndbuf_size, &sent, &prep);
+	return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
 }
 
 void smc_tx_work(struct work_struct *work);