smc: remote memory buffers (RMBs)

* allocate data RMB memory for sending and receiving
* size depends on the maximum socket send and receive buffers
* allocated RMBs are kept during life time of the owning link group
* map the allocated RMBs to DMA

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

1 files changed, 223 insertions, 1 deletions

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index b88a82918c82..e1b95728ca81 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -133,6 +133,7 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr,
 	struct smc_link *lnk;
 	u8 rndvec[3];
 	int rc = 0;
+	int i;
 
 	lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
 	if (!lgr) {
@@ -144,6 +145,12 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr,
 	lgr->daddr = peer_in_addr;
 	memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
 	lgr->vlan_id = vlan_id;
+	rwlock_init(&lgr->sndbufs_lock);
+	rwlock_init(&lgr->rmbs_lock);
+	for (i = 0; i < SMC_RMBE_SIZES; i++) {
+		INIT_LIST_HEAD(&lgr->sndbufs[i]);
+		INIT_LIST_HEAD(&lgr->rmbs[i]);
+	}
 	INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work);
 	lgr->conns_all = RB_ROOT;
 
@@ -164,6 +171,22 @@ out:
 	return rc;
 }
 
+static void smc_sndbuf_unuse(struct smc_connection *conn)
+{
+	if (conn->sndbuf_desc) {
+		conn->sndbuf_desc->used = 0;
+		conn->sndbuf_size = 0;
+	}
+}
+
+static void smc_rmb_unuse(struct smc_connection *conn)
+{
+	if (conn->rmb_desc) {
+		conn->rmb_desc->used = 0;
+		conn->rmbe_size = 0;
+	}
+}
+
 /* remove a finished connection from its link group */
 void smc_conn_free(struct smc_connection *conn)
 {
@@ -172,6 +195,8 @@ void smc_conn_free(struct smc_connection *conn)
 	if (!lgr)
 		return;
 	smc_lgr_unregister_conn(conn);
+	smc_rmb_unuse(conn);
+	smc_sndbuf_unuse(conn);
 }
 
 static void smc_link_clear(struct smc_link *lnk)
@@ -179,9 +204,39 @@ static void smc_link_clear(struct smc_link *lnk)
 	lnk->peer_qpn = 0;
 }
 
+static void smc_lgr_free_sndbufs(struct smc_link_group *lgr)
+{
+	struct smc_buf_desc *sndbuf_desc, *bf_desc;
+	int i;
+
+	for (i = 0; i < SMC_RMBE_SIZES; i++) {
+		list_for_each_entry_safe(sndbuf_desc, bf_desc, &lgr->sndbufs[i],
+					 list) {
+			kfree(sndbuf_desc->cpu_addr);
+			kfree(sndbuf_desc);
+		}
+	}
+}
+
+static void smc_lgr_free_rmbs(struct smc_link_group *lgr)
+{
+	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) {
+			kfree(rmb_desc->cpu_addr);
+			kfree(rmb_desc);
+		}
+	}
+}
+
 /* remove a link group */
 void smc_lgr_free(struct smc_link_group *lgr)
 {
+	smc_lgr_free_rmbs(lgr);
+	smc_lgr_free_sndbufs(lgr);
 	smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
 	kfree(lgr);
 }
@@ -300,7 +355,9 @@ int smc_conn_create(struct smc_sock *smc, __be32 peer_in_addr,
 			    sizeof(lcl->mac)) &&
 		    !lgr->sync_err &&
 		    (lgr->role == role) &&
-		    (lgr->vlan_id == vlan_id)) {
+		    (lgr->vlan_id == vlan_id) &&
+		    ((role == SMC_CLNT) ||
+		     (lgr->conns_num < SMC_RMBS_PER_LGR_MAX))) {
 			/* link group found */
 			local_contact = SMC_REUSE_CONTACT;
 			conn->lgr = lgr;
@@ -334,3 +391,168 @@ create:
 out:
 	return rc ? rc : local_contact;
 }
+
+/* try to reuse a sndbuf description slot of the sndbufs list for a certain
+ * buf_size; if not available, return NULL
+ */
+static inline
+struct smc_buf_desc *smc_sndbuf_get_slot(struct smc_link_group *lgr,
+					 int compressed_bufsize)
+{
+	struct smc_buf_desc *sndbuf_slot;
+
+	read_lock_bh(&lgr->sndbufs_lock);
+	list_for_each_entry(sndbuf_slot, &lgr->sndbufs[compressed_bufsize],
+			    list) {
+		if (cmpxchg(&sndbuf_slot->used, 0, 1) == 0) {
+			read_unlock_bh(&lgr->sndbufs_lock);
+			return sndbuf_slot;
+		}
+	}
+	read_unlock_bh(&lgr->sndbufs_lock);
+	return NULL;
+}
+
+/* try to reuse an rmb description slot of the rmbs list for a certain
+ * rmbe_size; if not available, return NULL
+ */
+static inline
+struct smc_buf_desc *smc_rmb_get_slot(struct smc_link_group *lgr,
+				      int compressed_bufsize)
+{
+	struct smc_buf_desc *rmb_slot;
+
+	read_lock_bh(&lgr->rmbs_lock);
+	list_for_each_entry(rmb_slot, &lgr->rmbs[compressed_bufsize],
+			    list) {
+		if (cmpxchg(&rmb_slot->used, 0, 1) == 0) {
+			read_unlock_bh(&lgr->rmbs_lock);
+			return rmb_slot;
+		}
+	}
+	read_unlock_bh(&lgr->rmbs_lock);
+	return NULL;
+}
+
+/* create the tx buffer for an SMC socket */
+int smc_sndbuf_create(struct smc_sock *smc)
+{
+	struct smc_connection *conn = &smc->conn;
+	struct smc_link_group *lgr = conn->lgr;
+	int tmp_bufsize, tmp_bufsize_short;
+	struct smc_buf_desc *sndbuf_desc;
+	int rc;
+
+	/* use socket send buffer size (w/o overhead) as start value */
+	for (tmp_bufsize_short = smc_compress_bufsize(smc->sk.sk_sndbuf / 2);
+	     tmp_bufsize_short >= 0; tmp_bufsize_short--) {
+		tmp_bufsize = smc_uncompress_bufsize(tmp_bufsize_short);
+		/* check for reusable sndbuf_slot in the link group */
+		sndbuf_desc = smc_sndbuf_get_slot(lgr, tmp_bufsize_short);
+		if (sndbuf_desc) {
+			memset(sndbuf_desc->cpu_addr, 0, tmp_bufsize);
+			break; /* found reusable slot */
+		}
+		/* try to alloc a new send buffer */
+		sndbuf_desc = kzalloc(sizeof(*sndbuf_desc), GFP_KERNEL);
+		if (!sndbuf_desc)
+			break; /* give up with -ENOMEM */
+		sndbuf_desc->cpu_addr = kzalloc(tmp_bufsize,
+						GFP_KERNEL | __GFP_NOWARN |
+						__GFP_NOMEMALLOC |
+						__GFP_NORETRY);
+		if (!sndbuf_desc->cpu_addr) {
+			kfree(sndbuf_desc);
+			/* if send buffer allocation has failed,
+			 * try a smaller one
+			 */
+			continue;
+		}
+		rc = smc_ib_buf_map(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+				    tmp_bufsize, sndbuf_desc,
+				    DMA_TO_DEVICE);
+		if (rc) {
+			kfree(sndbuf_desc->cpu_addr);
+			kfree(sndbuf_desc);
+			continue; /* if mapping failed, try smaller one */
+		}
+		sndbuf_desc->used = 1;
+		write_lock_bh(&lgr->sndbufs_lock);
+		list_add(&sndbuf_desc->list,
+			 &lgr->sndbufs[tmp_bufsize_short]);
+		write_unlock_bh(&lgr->sndbufs_lock);
+		break;
+	}
+	if (sndbuf_desc && sndbuf_desc->cpu_addr) {
+		conn->sndbuf_desc = sndbuf_desc;
+		conn->sndbuf_size = tmp_bufsize;
+		smc->sk.sk_sndbuf = tmp_bufsize * 2;
+		return 0;
+	} else {
+		return -ENOMEM;
+	}
+}
+
+/* create the RMB for an SMC socket (even though the SMC protocol
+ * allows more than one RMB-element per RMB, the Linux implementation
+ * uses just one RMB-element per RMB, i.e. uses an extra RMB for every
+ * connection in a link group
+ */
+int smc_rmb_create(struct smc_sock *smc)
+{
+	struct smc_connection *conn = &smc->conn;
+	struct smc_link_group *lgr = conn->lgr;
+	int tmp_bufsize, tmp_bufsize_short;
+	struct smc_buf_desc *rmb_desc;
+	int rc;
+
+	/* use socket recv buffer size (w/o overhead) as start value */
+	for (tmp_bufsize_short = smc_compress_bufsize(smc->sk.sk_rcvbuf / 2);
+	     tmp_bufsize_short >= 0; tmp_bufsize_short--) {
+		tmp_bufsize = smc_uncompress_bufsize(tmp_bufsize_short);
+		/* check for reusable rmb_slot in the link group */
+		rmb_desc = smc_rmb_get_slot(lgr, tmp_bufsize_short);
+		if (rmb_desc) {
+			memset(rmb_desc->cpu_addr, 0, tmp_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(tmp_bufsize,
+					     GFP_KERNEL | __GFP_NOWARN |
+					     __GFP_NOMEMALLOC |
+					     __GFP_NORETRY);
+		if (!rmb_desc->cpu_addr) {
+			kfree(rmb_desc);
+			/* if RMB allocation has failed,
+			 * try a smaller one
+			 */
+			continue;
+		}
+		rc = smc_ib_buf_map(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
+				    tmp_bufsize, rmb_desc,
+				    DMA_FROM_DEVICE);
+		if (rc) {
+			kfree(rmb_desc->cpu_addr);
+			kfree(rmb_desc);
+			continue; /* if mapping failed, try smaller one */
+		}
+		rmb_desc->used = 1;
+		write_lock_bh(&lgr->rmbs_lock);
+		list_add(&rmb_desc->list,
+			 &lgr->rmbs[tmp_bufsize_short]);
+		write_unlock_bh(&lgr->rmbs_lock);
+		break;
+	}
+	if (rmb_desc && rmb_desc->cpu_addr) {
+		conn->rmb_desc = rmb_desc;
+		conn->rmbe_size = tmp_bufsize;
+		conn->rmbe_size_short = tmp_bufsize_short;
+		smc->sk.sk_rcvbuf = tmp_bufsize * 2;
+		return 0;
+	} else {
+		return -ENOMEM;
+	}
+}