[PATCH net-next 02/10] net/smc: add pnetid support

[Ursula Braun <ubraun@linux.ibm.com>]

s390 hardware supports the definition of a so-call Physical NETwork
IDentifier (short PNETID) per network device port. These PNETIDS
can be used to identify network devices that are attached to the same
physical network (broadcast domain).

On s390 try to use the PNETID of the ethernet device port used for
initial connecting, and derive the IB device port used for SMC RDMA
traffic.

On platforms without PNETID support fall back to the existing
solution of a configured pnet table.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
---
 include/net/smc.h  |   2 +
 net/smc/smc_ib.c   |   6 ++-
 net/smc/smc_ib.h   |   3 ++
 net/smc/smc_pnet.c | 109 +++++++++++++++++++++++++++++++++++++++++++----------
 net/smc/smc_pnet.h |  14 +++++++
 5 files changed, 114 insertions(+), 20 deletions(-)

diff --git a/include/net/smc.h b/include/net/smc.h
index 8381d163fefa..2173932fab9d 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -11,6 +11,8 @@
 #ifndef _SMC_H
 #define _SMC_H
 
+#define SMC_MAX_PNETID_LEN	16	/* Max. length of PNET id */
+
 struct smc_hashinfo {
 	rwlock_t lock;
 	struct hlist_head ht;
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index f8b159ced032..36de2fd76170 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -504,8 +504,12 @@ static void smc_ib_add_dev(struct ib_device *ibdev)
 	port_cnt = smcibdev->ibdev->phys_port_cnt;
 	for (i = 0;
 	     i < min_t(size_t, port_cnt, SMC_MAX_PORTS);
-	     i++)
+	     i++) {
 		set_bit(i, &smcibdev->port_event_mask);
+		/* determine pnetids of the port */
+		smc_pnetid_by_dev_port(ibdev->dev.parent, i,
+				       smcibdev->pnetid[i]);
+	}
 	schedule_work(&smcibdev->port_event_work);
 }
 
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 2c480b352928..7c1223c91229 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -15,6 +15,7 @@
 #include <linux/interrupt.h>
 #include <linux/if_ether.h>
 #include <rdma/ib_verbs.h>
+#include <net/smc.h>
 
 #define SMC_MAX_PORTS			2	/* Max # of ports */
 #define SMC_GID_SIZE			sizeof(union ib_gid)
@@ -40,6 +41,8 @@ struct smc_ib_device {				/* ib-device infos for smc */
 	char			mac[SMC_MAX_PORTS][ETH_ALEN];
 						/* mac address per port*/
 	union ib_gid		gid[SMC_MAX_PORTS]; /* gid per port */
+	u8			pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN];
+						/* pnetid per port */
 	u8			initialized : 1; /* ib dev CQ, evthdl done */
 	struct work_struct	port_event_work;
 	unsigned long		port_event_mask;
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index a82a5cad0282..cdc6e23b6ce1 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -23,12 +23,10 @@
 #include "smc_pnet.h"
 #include "smc_ib.h"
 
-#define SMC_MAX_PNET_ID_LEN	16	/* Max. length of PNET id */
-
 static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
 	[SMC_PNETID_NAME] = {
 		.type = NLA_NUL_STRING,
-		.len = SMC_MAX_PNET_ID_LEN - 1
+		.len = SMC_MAX_PNETID_LEN - 1
 	},
 	[SMC_PNETID_ETHNAME] = {
 		.type = NLA_NUL_STRING,
@@ -65,7 +63,7 @@ static struct smc_pnettable {
  */
 struct smc_pnetentry {
 	struct list_head list;
-	char pnet_name[SMC_MAX_PNET_ID_LEN + 1];
+	char pnet_name[SMC_MAX_PNETID_LEN + 1];
 	struct net_device *ndev;
 	struct smc_ib_device *smcibdev;
 	u8 ib_port;
@@ -209,7 +207,7 @@ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid)
 		return false;
 	while (--end >= bf && isspace(*end))
 		;
-	if (end - bf >= SMC_MAX_PNET_ID_LEN)
+	if (end - bf >= SMC_MAX_PNETID_LEN)
 		return false;
 	while (bf <= end) {
 		if (!isalnum(*bf))
@@ -512,26 +510,70 @@ void smc_pnet_exit(void)
 	genl_unregister_family(&smc_pnet_nl_family);
 }
 
-/* PNET table analysis for a given sock:
- * determine ib_device and port belonging to used internal TCP socket
- * ethernet interface.
+/* Determine one base device for stacked net devices.
+ * If the lower device level contains more than one devices
+ * (for instance with bonding slaves), just the first device
+ * is used to reach a base device.
  */
-void smc_pnet_find_roce_resource(struct sock *sk,
-				 struct smc_ib_device **smcibdev, u8 *ibport)
+static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
 {
-	struct dst_entry *dst = sk_dst_get(sk);
-	struct smc_pnetentry *pnetelem;
+	int i, nest_lvl;
 
-	*smcibdev = NULL;
-	*ibport = 0;
+	rtnl_lock();
+	nest_lvl = dev_get_nest_level(ndev);
+	for (i = 0; i < nest_lvl; i++) {
+		struct list_head *lower = &ndev->adj_list.lower;
+
+		if (list_empty(lower))
+			break;
+		lower = lower->next;
+		ndev = netdev_lower_get_next(ndev, &lower);
+	}
+	rtnl_unlock();
+	return ndev;
+}
+
+/* Determine the corresponding IB device port based on the hardware PNETID.
+ * Searching stops at the first matching active IB device port.
+ */
+static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
+					 struct smc_ib_device **smcibdev,
+					 u8 *ibport)
+{
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+	struct smc_ib_device *ibdev;
+	int i;
+
+	ndev = pnet_find_base_ndev(ndev);
+	if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+				   ndev_pnetid))
+		return; /* pnetid could not be determined */
+
+	spin_lock(&smc_ib_devices.lock);
+	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+		for (i = 1; i <= SMC_MAX_PORTS; i++) {
+			if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid,
+				    SMC_MAX_PNETID_LEN) &&
+			    smc_ib_port_active(ibdev, i)) {
+				*smcibdev = ibdev;
+				*ibport = i;
+				break;
+			}
+		}
+	}
+	spin_unlock(&smc_ib_devices.lock);
+}
+
+/* Lookup of coupled ib_device via SMC pnet table */
+static void smc_pnet_find_roce_by_table(struct net_device *netdev,
+					struct smc_ib_device **smcibdev,
+					u8 *ibport)
+{
+	struct smc_pnetentry *pnetelem;
 
-	if (!dst)
-		return;
-	if (!dst->dev)
-		goto out_rel;
 	read_lock(&smc_pnettable.lock);
 	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
-		if (dst->dev == pnetelem->ndev) {
+		if (netdev == pnetelem->ndev) {
 			if (smc_ib_port_active(pnetelem->smcibdev,
 					       pnetelem->ib_port)) {
 				*smcibdev = pnetelem->smcibdev;
@@ -541,6 +583,35 @@ void smc_pnet_find_roce_resource(struct sock *sk,
 		}
 	}
 	read_unlock(&smc_pnettable.lock);
+}
+
+/* PNET table analysis for a given sock:
+ * determine ib_device and port belonging to used internal TCP socket
+ * ethernet interface.
+ */
+void smc_pnet_find_roce_resource(struct sock *sk,
+				 struct smc_ib_device **smcibdev, u8 *ibport)
+{
+	struct dst_entry *dst = sk_dst_get(sk);
+
+	*smcibdev = NULL;
+	*ibport = 0;
+
+	if (!dst)
+		goto out;
+	if (!dst->dev)
+		goto out_rel;
+
+	/* if possible, lookup via hardware-defined pnetid */
+	smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport);
+	if (*smcibdev)
+		goto out_rel;
+
+	/* lookup via SMC PNET table */
+	smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport);
+
 out_rel:
 	dst_release(dst);
+out:
+	return;
 }
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 5a29519db976..ad4455cde9e7 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -12,8 +12,22 @@
 #ifndef _SMC_PNET_H
 #define _SMC_PNET_H
 
+#if IS_ENABLED(CONFIG_HAVE_PNETID)
+#include <asm/pnet.h>
+#endif
+
 struct smc_ib_device;
 
+static inline int smc_pnetid_by_dev_port(struct device *dev,
+					 unsigned short port, u8 *pnetid)
+{
+#if IS_ENABLED(CONFIG_HAVE_PNETID)
+	return pnet_id_by_dev_port(dev, port, pnetid);
+#else
+	return -ENOENT;
+#endif
+}
+
 int smc_pnet_init(void) __init;
 void smc_pnet_exit(void);
 int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev);
-- 
2.16.4