[PATCH net-next 0/6] net/smc: patches 2019-02-21

[PATCH net-next 0/6] net/smc: patches 2019-02-21

[Ursula Braun]

Dave,

here are patches for SMC:
* patch 1 is a cleanup without functional change
* patches 2-6 enhance SMC pnetid support

Thanks, Ursula

Hans Wippel (5):
  s390/net: convert pnetids to ascii
  net/smc: rework pnet table
  net/smc: add smcd support to the pnet table
  net/smc: add pnet table namespace support
  net/smc: allow PCI IDs as ib device names in the pnet table

Ursula Braun (1):
  net/smc: cleanup for smcr_tx_sndbuf_nonempty

 arch/s390/net/pnet.c |   3 +
 include/net/smc.h    |   1 +
 net/smc/af_smc.c     |  28 +++
 net/smc/smc_ib.c     |   1 -
 net/smc/smc_ib.h     |   2 +
 net/smc/smc_netns.h  |  20 ++
 net/smc/smc_pnet.c   | 629 +++++++++++++++++++++++++++++++++------------------
 net/smc/smc_pnet.h   |  13 +-
 net/smc/smc_tx.c     |   5 +-
 9 files changed, 477 insertions(+), 225 deletions(-)
 create mode 100644 net/smc/smc_netns.h

-- 
2.16.4

[PATCH net-next 1/6] net/smc: cleanup for smcr_tx_sndbuf_nonempty

[Ursula Braun]

Use local variable pflags from the beginning of function
smcr_tx_sndbuf_nonempty

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
---
 net/smc/smc_tx.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index a3bff08ff8c8..f0de323d15d6 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -483,7 +483,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn,
  */
 static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
 {
-	struct smc_cdc_producer_flags *pflags;
+	struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags;
 	struct smc_rdma_wr *wr_rdma_buf;
 	struct smc_cdc_tx_pend *pend;
 	struct smc_wr_buf *wr_buf;
@@ -506,7 +506,7 @@ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
 	}
 
 	spin_lock_bh(&conn->send_lock);
-	if (!conn->local_tx_ctrl.prod_flags.urg_data_present) {
+	if (!pflags->urg_data_present) {
 		rc = smc_tx_rdma_writes(conn, wr_rdma_buf);
 		if (rc) {
 			smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK],
@@ -516,7 +516,6 @@ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
 	}
 
 	rc = smc_cdc_msg_send(conn, wr_buf, pend);
-	pflags = &conn->local_tx_ctrl.prod_flags;
 	if (!rc && pflags->urg_data_present) {
 		pflags->urg_data_pending = 0;
 		pflags->urg_data_present = 0;
-- 
2.16.4

[PATCH net-next 2/6] s390/net: convert pnetids to ascii

[Ursula Braun]

From: Hans Wippel <hwippel@linux.ibm.com>

Pnetids are retrieved from the underlying hardware as EBCDIC. This patch
converts pnetids to ASCII.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
---
 arch/s390/net/pnet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/s390/net/pnet.c b/arch/s390/net/pnet.c
index 9ecdbdf59781..79211bec0fc8 100644
--- a/arch/s390/net/pnet.c
+++ b/arch/s390/net/pnet.c
@@ -12,6 +12,7 @@
 #include <asm/ccwgroup.h>
 #include <asm/ccwdev.h>
 #include <asm/pnet.h>
+#include <asm/ebcdic.h>
 
 #define PNETIDS_LEN		64	/* Total utility string length in bytes
 					 * to cover up to 4 PNETIDs of 16 bytes
@@ -48,6 +49,7 @@ static int pnet_ids_by_device(struct device *dev, u8 *pnetids)
 		if (!util_str)
 			return -ENOMEM;
 		memcpy(pnetids, util_str, PNETIDS_LEN);
+		EBCASC(pnetids, PNETIDS_LEN);
 		kfree(util_str);
 		return 0;
 	}
@@ -55,6 +57,7 @@ static int pnet_ids_by_device(struct device *dev, u8 *pnetids)
 		struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 
 		memcpy(pnetids, zdev->util_str, sizeof(zdev->util_str));
+		EBCASC(pnetids, sizeof(zdev->util_str));
 		return 0;
 	}
 	return -EOPNOTSUPP;
-- 
2.16.4

[PATCH net-next 3/6] net/smc: rework pnet table

[Ursula Braun]

From: Hans Wippel <hwippel@linux.ibm.com>

If a device does not have a pnetid, users can set a temporary pnetid for
said device in the pnet table. This patch reworks the pnet table to make
it more flexible. Multiple entries with the same pnetid but differing
devices are now allowed. Additionally, the netlink interface now sends
each mapping from pnetid to device separately to the user while
maintaining the message format existing applications might expect. Also,
the SMC data structure for ib devices already has a pnetid attribute.
So, it is used to store the user defined pnetids. As a result, the pnet
table entries are only used for netdevs.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
---
 net/smc/smc_ib.c   |   1 -
 net/smc/smc_ib.h   |   2 +
 net/smc/smc_pnet.c | 439 ++++++++++++++++++++++++++++++-----------------------
 net/smc/smc_pnet.h |   1 -
 4 files changed, 249 insertions(+), 194 deletions(-)

diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 0b244be24fe0..53f429c04843 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -564,7 +564,6 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data)
 	spin_lock(&smc_ib_devices.lock);
 	list_del_init(&smcibdev->list); /* remove from smc_ib_devices */
 	spin_unlock(&smc_ib_devices.lock);
-	smc_pnet_remove_by_ibdev(smcibdev);
 	smc_ib_cleanup_per_ibdev(smcibdev);
 	ib_unregister_event_handler(&smcibdev->event_handler);
 	kfree(smcibdev);
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index bac7fd65a4c0..da60ab9e8d70 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -42,6 +42,8 @@ struct smc_ib_device {				/* ib-device infos for smc */
 						/* mac address per port*/
 	u8			pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN];
 						/* pnetid per port */
+	bool			pnetid_by_user[SMC_MAX_PORTS];
+						/* pnetid defined by user? */
 	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 632c3109dee5..327bf2afe820 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -24,6 +24,10 @@
 #include "smc_ib.h"
 #include "smc_ism.h"
 
+#define SMC_ASCII_BLANK 32
+
+static struct net_device *pnet_find_base_ndev(struct net_device *ndev);
+
 static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
 	[SMC_PNETID_NAME] = {
 		.type = NLA_NUL_STRING,
@@ -56,13 +60,14 @@ static struct smc_pnettable {
 };
 
 /**
- * struct smc_pnetentry - pnet identifier name entry
+ * struct smc_user_pnetentry - pnet identifier name entry for/from user
  * @list: List node.
  * @pnet_name: Pnet identifier name
  * @ndev: pointer to network device.
  * @smcibdev: Pointer to IB device.
+ * @ib_port: Port of IB device.
  */
-struct smc_pnetentry {
+struct smc_user_pnetentry {
 	struct list_head list;
 	char pnet_name[SMC_MAX_PNETID_LEN + 1];
 	struct net_device *ndev;
@@ -70,33 +75,26 @@ struct smc_pnetentry {
 	u8 ib_port;
 };
 
-/* Check if two RDMA device entries are identical. Use device name and port
- * number for comparison.
- */
-static bool smc_pnet_same_ibname(struct smc_pnetentry *pnetelem, char *ibname,
-				 u8 ibport)
-{
-	return pnetelem->ib_port == ibport &&
-	       !strncmp(pnetelem->smcibdev->ibdev->name, ibname,
-			sizeof(pnetelem->smcibdev->ibdev->name));
-}
+/* pnet entry stored in pnet table */
+struct smc_pnetentry {
+	struct list_head list;
+	char pnet_name[SMC_MAX_PNETID_LEN + 1];
+	struct net_device *ndev;
+};
 
-/* Find a pnetid in the pnet table.
- */
-static struct smc_pnetentry *smc_pnet_find_pnetid(char *pnet_name)
+/* Check if two given pnetids match */
+static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2)
 {
-	struct smc_pnetentry *pnetelem, *found_pnetelem = NULL;
+	int i;
 
-	read_lock(&smc_pnettable.lock);
-	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
-		if (!strncmp(pnetelem->pnet_name, pnet_name,
-			     sizeof(pnetelem->pnet_name))) {
-			found_pnetelem = pnetelem;
+	for (i = 0; i < SMC_MAX_PNETID_LEN; i++) {
+		if ((pnetid1[i] == 0 || pnetid1[i] == SMC_ASCII_BLANK) &&
+		    (pnetid2[i] == 0 || pnetid2[i] == SMC_ASCII_BLANK))
 			break;
-		}
+		if (pnetid1[i] != pnetid2[i])
+			return false;
 	}
-	read_unlock(&smc_pnettable.lock);
-	return found_pnetelem;
+	return true;
 }
 
 /* Remove a pnetid from the pnet table.
@@ -104,21 +102,39 @@ static struct smc_pnetentry *smc_pnet_find_pnetid(char *pnet_name)
 static int smc_pnet_remove_by_pnetid(char *pnet_name)
 {
 	struct smc_pnetentry *pnetelem, *tmp_pe;
+	struct smc_ib_device *ibdev;
 	int rc = -ENOENT;
+	int ibport;
 
+	/* remove netdevices */
 	write_lock(&smc_pnettable.lock);
 	list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
 				 list) {
-		if (!strncmp(pnetelem->pnet_name, pnet_name,
-			     sizeof(pnetelem->pnet_name))) {
+		if (!pnet_name ||
+		    smc_pnet_match(pnetelem->pnet_name, pnet_name)) {
 			list_del(&pnetelem->list);
 			dev_put(pnetelem->ndev);
 			kfree(pnetelem);
 			rc = 0;
-			break;
 		}
 	}
 	write_unlock(&smc_pnettable.lock);
+	/* remove ib devices */
+	spin_lock(&smc_ib_devices.lock);
+	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+		for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) {
+			if (ibdev->pnetid_by_user[ibport] &&
+			    (!pnet_name ||
+			     smc_pnet_match(pnet_name,
+					    ibdev->pnetid[ibport]))) {
+				memset(ibdev->pnetid[ibport], 0,
+				       SMC_MAX_PNETID_LEN);
+				ibdev->pnetid_by_user[ibport] = false;
+				rc = 0;
+			}
+		}
+	}
+	spin_unlock(&smc_ib_devices.lock);
 	return rc;
 }
 
@@ -144,53 +160,66 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev)
 	return rc;
 }
 
-/* Remove a pnet entry mentioning a given ib device from the pnet table.
+/* Append a pnetid to the end of the pnet table if not already on this list.
  */
-int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev)
+static int smc_pnet_enter(struct smc_user_pnetentry *new_pnetelem)
 {
-	struct smc_pnetentry *pnetelem, *tmp_pe;
-	int rc = -ENOENT;
-
-	write_lock(&smc_pnettable.lock);
-	list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
-				 list) {
-		if (pnetelem->smcibdev == ibdev) {
-			list_del(&pnetelem->list);
-			dev_put(pnetelem->ndev);
-			kfree(pnetelem);
-			rc = 0;
-			break;
+	u8 pnet_null[SMC_MAX_PNETID_LEN] = {0};
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+	struct smc_pnetentry *tmp_pnetelem;
+	struct smc_pnetentry *pnetelem;
+	struct net_device *ndev;
+	bool new_netdev = true;
+	bool new_ibdev = false;
+
+	if (new_pnetelem->smcibdev) {
+		struct smc_ib_device *ib_dev = new_pnetelem->smcibdev;
+		int ib_port = new_pnetelem->ib_port;
+
+		spin_lock(&smc_ib_devices.lock);
+		if (smc_pnet_match(ib_dev->pnetid[ib_port - 1], pnet_null)) {
+			memcpy(ib_dev->pnetid[ib_port - 1],
+			       new_pnetelem->pnet_name, SMC_MAX_PNETID_LEN);
+			ib_dev->pnetid_by_user[ib_port - 1] = true;
+			new_ibdev = true;
 		}
+		spin_unlock(&smc_ib_devices.lock);
 	}
-	write_unlock(&smc_pnettable.lock);
-	return rc;
-}
 
-/* Append a pnetid to the end of the pnet table if not already on this list.
- */
-static int smc_pnet_enter(struct smc_pnetentry *new_pnetelem)
-{
-	struct smc_pnetentry *pnetelem;
-	int rc = -EEXIST;
+	if (!new_pnetelem->ndev)
+		return new_ibdev ? 0 : -EEXIST;
+
+	/* check if (base) netdev already has a pnetid. If there is one, we do
+	 * not want to add a pnet table entry
+	 */
+	ndev = pnet_find_base_ndev(new_pnetelem->ndev);
+	if (!smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+				    ndev_pnetid))
+		return new_ibdev ? 0 : -EEXIST;
+
+	/* add a new netdev entry to the pnet table if there isn't one */
+	tmp_pnetelem = kzalloc(sizeof(*pnetelem), GFP_KERNEL);
+	if (!tmp_pnetelem)
+		return -ENOMEM;
+	memcpy(tmp_pnetelem->pnet_name, new_pnetelem->pnet_name,
+	       SMC_MAX_PNETID_LEN);
+	tmp_pnetelem->ndev = new_pnetelem->ndev;
 
 	write_lock(&smc_pnettable.lock);
 	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
-		if (!strncmp(pnetelem->pnet_name, new_pnetelem->pnet_name,
-			     sizeof(new_pnetelem->pnet_name)) ||
-		    !strncmp(pnetelem->ndev->name, new_pnetelem->ndev->name,
-			     sizeof(new_pnetelem->ndev->name)) ||
-		    smc_pnet_same_ibname(pnetelem,
-					 new_pnetelem->smcibdev->ibdev->name,
-					 new_pnetelem->ib_port)) {
-			dev_put(pnetelem->ndev);
-			goto found;
-		}
+		if (pnetelem->ndev == new_pnetelem->ndev)
+			new_netdev = false;
 	}
-	list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist);
-	rc = 0;
-found:
-	write_unlock(&smc_pnettable.lock);
-	return rc;
+	if (new_netdev) {
+		dev_hold(tmp_pnetelem->ndev);
+		list_add_tail(&tmp_pnetelem->list, &smc_pnettable.pnetlist);
+		write_unlock(&smc_pnettable.lock);
+	} else {
+		write_unlock(&smc_pnettable.lock);
+		kfree(tmp_pnetelem);
+	}
+
+	return (new_netdev || new_ibdev) ? 0 : -EEXIST;
 }
 
 /* The limit for pnetid is 16 characters.
@@ -241,7 +270,8 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
 /* Parse the supplied netlink attributes and fill a pnetentry structure.
  * For ethernet and infiniband device names verify that the devices exist.
  */
-static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem,
+static int smc_pnet_fill_entry(struct net *net,
+			       struct smc_user_pnetentry *pnetelem,
 			       struct nlattr *tb[])
 {
 	char *string, *ibname;
@@ -258,30 +288,29 @@ static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem,
 		goto error;
 
 	rc = -EINVAL;
-	if (!tb[SMC_PNETID_ETHNAME])
-		goto error;
-	rc = -ENOENT;
-	string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
-	pnetelem->ndev = dev_get_by_name(net, string);
-	if (!pnetelem->ndev)
-		goto error;
-
-	rc = -EINVAL;
-	if (!tb[SMC_PNETID_IBNAME])
-		goto error;
-	rc = -ENOENT;
-	ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
-	ibname = strim(ibname);
-	pnetelem->smcibdev = smc_pnet_find_ib(ibname);
-	if (!pnetelem->smcibdev)
-		goto error;
+	if (tb[SMC_PNETID_ETHNAME]) {
+		string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
+		pnetelem->ndev = dev_get_by_name(net, string);
+		if (!pnetelem->ndev)
+			goto error;
+	}
 
 	rc = -EINVAL;
-	if (!tb[SMC_PNETID_IBPORT])
-		goto error;
-	pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
-	if (pnetelem->ib_port < 1 || pnetelem->ib_port > SMC_MAX_PORTS)
-		goto error;
+	if (tb[SMC_PNETID_IBNAME]) {
+		ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
+		ibname = strim(ibname);
+		pnetelem->smcibdev = smc_pnet_find_ib(ibname);
+		if (!pnetelem->smcibdev)
+			goto error;
+		if (pnetelem->smcibdev) {
+			if (!tb[SMC_PNETID_IBPORT])
+				goto error;
+			pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
+			if (pnetelem->ib_port < 1 ||
+			    pnetelem->ib_port > SMC_MAX_PORTS)
+				goto error;
+		}
+	}
 
 	return 0;
 
@@ -292,71 +321,44 @@ static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem,
 }
 
 /* Convert an smc_pnetentry to a netlink attribute sequence */
-static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem)
+static int smc_pnet_set_nla(struct sk_buff *msg,
+			    struct smc_user_pnetentry *pnetelem)
 {
-	if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name) ||
-	    nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->ndev->name) ||
-	    nla_put_string(msg, SMC_PNETID_IBNAME,
-			   pnetelem->smcibdev->ibdev->name) ||
-	    nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port))
+	if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name))
 		return -1;
-	return 0;
-}
-
-/* Retrieve one PNETID entry */
-static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
-{
-	struct smc_pnetentry *pnetelem;
-	struct sk_buff *msg;
-	void *hdr;
-	int rc;
-
-	if (!info->attrs[SMC_PNETID_NAME])
-		return -EINVAL;
-	pnetelem = smc_pnet_find_pnetid(
-				(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
-	if (!pnetelem)
-		return -ENOENT;
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq,
-			  &smc_pnet_nl_family, 0, SMC_PNETID_GET);
-	if (!hdr) {
-		rc = -EMSGSIZE;
-		goto err_out;
+	if (pnetelem->ndev) {
+		if (nla_put_string(msg, SMC_PNETID_ETHNAME,
+				   pnetelem->ndev->name))
+			return -1;
+	} else {
+		if (nla_put_string(msg, SMC_PNETID_ETHNAME, "n/a"))
+			return -1;
 	}
-
-	if (smc_pnet_set_nla(msg, pnetelem)) {
-		rc = -ENOBUFS;
-		goto err_out;
+	if (pnetelem->smcibdev) {
+		if (nla_put_string(msg, SMC_PNETID_IBNAME,
+				   pnetelem->smcibdev->ibdev->name) ||
+		    nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port))
+			return -1;
+	} else {
+		if (nla_put_string(msg, SMC_PNETID_IBNAME, "n/a") ||
+		    nla_put_u8(msg, SMC_PNETID_IBPORT, 0xff))
+			return -1;
 	}
 
-	genlmsg_end(msg, hdr);
-	return genlmsg_reply(msg, info);
-
-err_out:
-	nlmsg_free(msg);
-	return rc;
+	return 0;
 }
 
 static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
-	struct smc_pnetentry *pnetelem;
+	struct smc_user_pnetentry pnetelem;
 	int rc;
 
-	pnetelem = kzalloc(sizeof(*pnetelem), GFP_KERNEL);
-	if (!pnetelem)
-		return -ENOMEM;
-	rc = smc_pnet_fill_entry(net, pnetelem, info->attrs);
+	rc = smc_pnet_fill_entry(net, &pnetelem, info->attrs);
 	if (!rc)
-		rc = smc_pnet_enter(pnetelem);
-	if (rc) {
-		kfree(pnetelem);
-		return rc;
-	}
+		rc = smc_pnet_enter(&pnetelem);
+	if (pnetelem.ndev)
+		dev_put(pnetelem.ndev);
 	return rc;
 }
 
@@ -376,7 +378,7 @@ static int smc_pnet_dump_start(struct netlink_callback *cb)
 
 static int smc_pnet_dumpinfo(struct sk_buff *skb,
 			     u32 portid, u32 seq, u32 flags,
-			     struct smc_pnetentry *pnetelem)
+			     struct smc_user_pnetentry *pnetelem)
 {
 	void *hdr;
 
@@ -392,42 +394,107 @@ static int smc_pnet_dumpinfo(struct sk_buff *skb,
 	return 0;
 }
 
-static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb)
+static int _smc_pnet_dump(struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid,
+			  int start_idx)
 {
+	struct smc_user_pnetentry tmp_entry;
 	struct smc_pnetentry *pnetelem;
+	struct smc_ib_device *ibdev;
 	int idx = 0;
+	int ibport;
 
+	/* dump netdevices */
 	read_lock(&smc_pnettable.lock);
 	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
-		if (idx++ < cb->args[0])
+		if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid))
+			continue;
+		if (idx++ < start_idx)
 			continue;
-		if (smc_pnet_dumpinfo(skb, NETLINK_CB(cb->skb).portid,
-				      cb->nlh->nlmsg_seq, NLM_F_MULTI,
-				      pnetelem)) {
+		memset(&tmp_entry, 0, sizeof(tmp_entry));
+		memcpy(&tmp_entry.pnet_name, pnetelem->pnet_name,
+		       SMC_MAX_PNETID_LEN);
+		tmp_entry.ndev = pnetelem->ndev;
+		if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI,
+				      &tmp_entry)) {
 			--idx;
 			break;
 		}
 	}
-	cb->args[0] = idx;
 	read_unlock(&smc_pnettable.lock);
+
+	/* dump ib devices */
+	spin_lock(&smc_ib_devices.lock);
+	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+		for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) {
+			if (ibdev->pnetid_by_user[ibport]) {
+				if (pnetid &&
+				    !smc_pnet_match(ibdev->pnetid[ibport],
+						    pnetid))
+					continue;
+				if (idx++ < start_idx)
+					continue;
+				memset(&tmp_entry, 0, sizeof(tmp_entry));
+				memcpy(&tmp_entry.pnet_name,
+				       ibdev->pnetid[ibport],
+				       SMC_MAX_PNETID_LEN);
+				tmp_entry.smcibdev = ibdev;
+				tmp_entry.ib_port = ibport + 1;
+				if (smc_pnet_dumpinfo(skb, portid, seq,
+						      NLM_F_MULTI,
+						      &tmp_entry)) {
+					--idx;
+					break;
+				}
+			}
+		}
+	}
+	spin_unlock(&smc_ib_devices.lock);
+
+	return idx;
+}
+
+static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	int idx;
+
+	idx = _smc_pnet_dump(skb, NETLINK_CB(cb->skb).portid,
+			     cb->nlh->nlmsg_seq, NULL, cb->args[0]);
+
+	cb->args[0] = idx;
 	return skb->len;
 }
 
+/* Retrieve one PNETID entry */
+static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *msg;
+	void *hdr;
+
+	if (!info->attrs[SMC_PNETID_NAME])
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	_smc_pnet_dump(msg, info->snd_portid, info->snd_seq,
+		       nla_data(info->attrs[SMC_PNETID_NAME]), 0);
+
+	/* finish multi part message and send it */
+	hdr = nlmsg_put(msg, info->snd_portid, info->snd_seq, NLMSG_DONE, 0,
+			NLM_F_MULTI);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return -EMSGSIZE;
+	}
+	return genlmsg_reply(msg, info);
+}
+
 /* Remove and delete all pnetids from pnet table.
  */
 static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info)
 {
-	struct smc_pnetentry *pnetelem, *tmp_pe;
-
-	write_lock(&smc_pnettable.lock);
-	list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
-				 list) {
-		list_del(&pnetelem->list);
-		dev_put(pnetelem->ndev);
-		kfree(pnetelem);
-	}
-	write_unlock(&smc_pnettable.lock);
-	return 0;
+	return smc_pnet_remove_by_pnetid(NULL);
 }
 
 /* SMC_PNETID generic netlink operation definition */
@@ -534,6 +601,25 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
 	return ndev;
 }
 
+static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *netdev,
+					      u8 *pnetid)
+{
+	struct smc_pnetentry *pnetelem;
+	int rc = -ENOENT;
+
+	read_lock(&smc_pnettable.lock);
+	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
+		if (netdev == pnetelem->ndev) {
+			/* get pnetid of netdev device */
+			memcpy(pnetid, pnetelem->pnet_name, SMC_MAX_PNETID_LEN);
+			rc = 0;
+			break;
+		}
+	}
+	read_unlock(&smc_pnettable.lock);
+	return rc;
+}
+
 /* Determine the corresponding IB device port based on the hardware PNETID.
  * Searching stops at the first matching active IB device port with vlan_id
  * configured.
@@ -549,7 +635,8 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
 
 	ndev = pnet_find_base_ndev(ndev);
 	if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
-				   ndev_pnetid))
+				   ndev_pnetid) &&
+	    smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid))
 		return; /* pnetid could not be determined */
 
 	spin_lock(&smc_ib_devices.lock);
@@ -557,8 +644,7 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
 		for (i = 1; i <= SMC_MAX_PORTS; i++) {
 			if (!rdma_is_port_valid(ibdev->ibdev, i))
 				continue;
-			if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid,
-				    SMC_MAX_PNETID_LEN) &&
+			if (smc_pnet_match(ibdev->pnetid[i - 1], ndev_pnetid) &&
 			    smc_ib_port_active(ibdev, i) &&
 			    !smc_ib_determine_gid(ibdev, i, vlan_id, gid,
 						  NULL))  {
@@ -593,31 +679,6 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
 	spin_unlock(&smcd_dev_list.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, unsigned short vlan_id,
-					u8 gid[])
-{
-	struct smc_pnetentry *pnetelem;
-
-	read_lock(&smc_pnettable.lock);
-	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
-		if (netdev == pnetelem->ndev) {
-			if (smc_ib_port_active(pnetelem->smcibdev,
-					       pnetelem->ib_port) &&
-			    !smc_ib_determine_gid(pnetelem->smcibdev,
-						  pnetelem->ib_port, vlan_id,
-						  gid, NULL)) {
-				*smcibdev = pnetelem->smcibdev;
-				*ibport = pnetelem->ib_port;
-			}
-			break;
-		}
-	}
-	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.
@@ -636,13 +697,7 @@ void smc_pnet_find_roce_resource(struct sock *sk,
 	if (!dst->dev)
 		goto out_rel;
 
-	/* if possible, lookup via hardware-defined pnetid */
 	smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport, vlan_id, gid);
-	if (*smcibdev)
-		goto out_rel;
-
-	/* lookup via SMC PNET table */
-	smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport, vlan_id, gid);
 
 out_rel:
 	dst_release(dst);
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 8ff777636e32..37044e4ee50f 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -31,7 +31,6 @@ static inline int smc_pnetid_by_dev_port(struct device *dev,
 
 int smc_pnet_init(void) __init;
 void smc_pnet_exit(void);
-int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev);
 void smc_pnet_find_roce_resource(struct sock *sk,
 				 struct smc_ib_device **smcibdev, u8 *ibport,
 				 unsigned short vlan_id, u8 gid[]);
-- 
2.16.4

[PATCH net-next 4/6] net/smc: add smcd support to the pnet table

[Ursula Braun]

From: Hans Wippel <hwippel@linux.ibm.com>

Currently, users can only set pnetids for netdevs and ib devices in the
pnet table. This patch adds support for smcd devices to the pnet table.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
---
 include/net/smc.h  |  1 +
 net/smc/smc_pnet.c | 87 +++++++++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 81 insertions(+), 7 deletions(-)

diff --git a/include/net/smc.h b/include/net/smc.h
index 9ef49f8b1002..bd9c0fb3b577 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -74,6 +74,7 @@ struct smcd_dev {
 	struct list_head vlan;
 	struct workqueue_struct *event_wq;
 	u8 pnetid[SMC_MAX_PNETID_LEN];
+	bool pnetid_by_user;
 };
 
 struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 327bf2afe820..5497a8b44287 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -66,6 +66,7 @@ static struct smc_pnettable {
  * @ndev: pointer to network device.
  * @smcibdev: Pointer to IB device.
  * @ib_port: Port of IB device.
+ * @smcd_dev: Pointer to smcd device.
  */
 struct smc_user_pnetentry {
 	struct list_head list;
@@ -73,6 +74,7 @@ struct smc_user_pnetentry {
 	struct net_device *ndev;
 	struct smc_ib_device *smcibdev;
 	u8 ib_port;
+	struct smcd_dev *smcd_dev;
 };
 
 /* pnet entry stored in pnet table */
@@ -103,6 +105,7 @@ static int smc_pnet_remove_by_pnetid(char *pnet_name)
 {
 	struct smc_pnetentry *pnetelem, *tmp_pe;
 	struct smc_ib_device *ibdev;
+	struct smcd_dev *smcd_dev;
 	int rc = -ENOENT;
 	int ibport;
 
@@ -135,6 +138,18 @@ static int smc_pnet_remove_by_pnetid(char *pnet_name)
 		}
 	}
 	spin_unlock(&smc_ib_devices.lock);
+	/* remove smcd devices */
+	spin_lock(&smcd_dev_list.lock);
+	list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) {
+		if (smcd_dev->pnetid_by_user &&
+		    (!pnet_name ||
+		     smc_pnet_match(pnet_name, smcd_dev->pnetid))) {
+			memset(smcd_dev->pnetid, 0, SMC_MAX_PNETID_LEN);
+			smcd_dev->pnetid_by_user = false;
+			rc = 0;
+		}
+	}
+	spin_unlock(&smcd_dev_list.lock);
 	return rc;
 }
 
@@ -168,6 +183,7 @@ static int smc_pnet_enter(struct smc_user_pnetentry *new_pnetelem)
 	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
 	struct smc_pnetentry *tmp_pnetelem;
 	struct smc_pnetentry *pnetelem;
+	bool new_smcddev = false;
 	struct net_device *ndev;
 	bool new_netdev = true;
 	bool new_ibdev = false;
@@ -185,9 +201,21 @@ static int smc_pnet_enter(struct smc_user_pnetentry *new_pnetelem)
 		}
 		spin_unlock(&smc_ib_devices.lock);
 	}
+	if (new_pnetelem->smcd_dev) {
+		struct smcd_dev *smcd_dev = new_pnetelem->smcd_dev;
+
+		spin_lock(&smcd_dev_list.lock);
+		if (smc_pnet_match(smcd_dev->pnetid, pnet_null)) {
+			memcpy(smcd_dev->pnetid, new_pnetelem->pnet_name,
+			       SMC_MAX_PNETID_LEN);
+			smcd_dev->pnetid_by_user = true;
+			new_smcddev = true;
+		}
+		spin_unlock(&smcd_dev_list.lock);
+	}
 
 	if (!new_pnetelem->ndev)
-		return new_ibdev ? 0 : -EEXIST;
+		return (new_ibdev || new_smcddev) ? 0 : -EEXIST;
 
 	/* check if (base) netdev already has a pnetid. If there is one, we do
 	 * not want to add a pnet table entry
@@ -195,7 +223,7 @@ static int smc_pnet_enter(struct smc_user_pnetentry *new_pnetelem)
 	ndev = pnet_find_base_ndev(new_pnetelem->ndev);
 	if (!smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
 				    ndev_pnetid))
-		return new_ibdev ? 0 : -EEXIST;
+		return (new_ibdev || new_smcddev) ? 0 : -EEXIST;
 
 	/* add a new netdev entry to the pnet table if there isn't one */
 	tmp_pnetelem = kzalloc(sizeof(*pnetelem), GFP_KERNEL);
@@ -219,7 +247,7 @@ static int smc_pnet_enter(struct smc_user_pnetentry *new_pnetelem)
 		kfree(tmp_pnetelem);
 	}
 
-	return (new_netdev || new_ibdev) ? 0 : -EEXIST;
+	return (new_netdev || new_ibdev || new_smcddev) ? 0 : -EEXIST;
 }
 
 /* The limit for pnetid is 16 characters.
@@ -267,6 +295,23 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
 	return ibdev;
 }
 
+/* Find an smcd device by a given name. The device might not exist. */
+static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name)
+{
+	struct smcd_dev *smcd_dev;
+
+	spin_lock(&smcd_dev_list.lock);
+	list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) {
+		if (!strncmp(dev_name(&smcd_dev->dev), smcd_name,
+			     IB_DEVICE_NAME_MAX - 1))
+			goto out;
+	}
+	smcd_dev = NULL;
+out:
+	spin_unlock(&smcd_dev_list.lock);
+	return smcd_dev;
+}
+
 /* Parse the supplied netlink attributes and fill a pnetentry structure.
  * For ethernet and infiniband device names verify that the devices exist.
  */
@@ -300,7 +345,8 @@ static int smc_pnet_fill_entry(struct net *net,
 		ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
 		ibname = strim(ibname);
 		pnetelem->smcibdev = smc_pnet_find_ib(ibname);
-		if (!pnetelem->smcibdev)
+		pnetelem->smcd_dev = smc_pnet_find_smcd(ibname);
+		if (!pnetelem->smcibdev && !pnetelem->smcd_dev)
 			goto error;
 		if (pnetelem->smcibdev) {
 			if (!tb[SMC_PNETID_IBPORT])
@@ -339,6 +385,11 @@ static int smc_pnet_set_nla(struct sk_buff *msg,
 				   pnetelem->smcibdev->ibdev->name) ||
 		    nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port))
 			return -1;
+	} else if (pnetelem->smcd_dev) {
+		if (nla_put_string(msg, SMC_PNETID_IBNAME,
+				   dev_name(&pnetelem->smcd_dev->dev)) ||
+		    nla_put_u8(msg, SMC_PNETID_IBPORT, 1))
+			return -1;
 	} else {
 		if (nla_put_string(msg, SMC_PNETID_IBNAME, "n/a") ||
 		    nla_put_u8(msg, SMC_PNETID_IBPORT, 0xff))
@@ -400,6 +451,7 @@ static int _smc_pnet_dump(struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid,
 	struct smc_user_pnetentry tmp_entry;
 	struct smc_pnetentry *pnetelem;
 	struct smc_ib_device *ibdev;
+	struct smcd_dev *smcd_dev;
 	int idx = 0;
 	int ibport;
 
@@ -450,6 +502,27 @@ static int _smc_pnet_dump(struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid,
 	}
 	spin_unlock(&smc_ib_devices.lock);
 
+	/* dump smcd devices */
+	spin_lock(&smcd_dev_list.lock);
+	list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) {
+		if (smcd_dev->pnetid_by_user) {
+			if (pnetid && !smc_pnet_match(smcd_dev->pnetid, pnetid))
+				continue;
+			if (idx++ < start_idx)
+				continue;
+			memset(&tmp_entry, 0, sizeof(tmp_entry));
+			memcpy(&tmp_entry.pnet_name, smcd_dev->pnetid,
+			       SMC_MAX_PNETID_LEN);
+			tmp_entry.smcd_dev = smcd_dev;
+			if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI,
+					      &tmp_entry)) {
+				--idx;
+				break;
+			}
+		}
+	}
+	spin_unlock(&smcd_dev_list.lock);
+
 	return idx;
 }
 
@@ -666,12 +739,13 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
 
 	ndev = pnet_find_base_ndev(ndev);
 	if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
-				   ndev_pnetid))
+				   ndev_pnetid) &&
+	    smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid))
 		return; /* pnetid could not be determined */
 
 	spin_lock(&smcd_dev_list.lock);
 	list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
-		if (!memcmp(ismdev->pnetid, ndev_pnetid, SMC_MAX_PNETID_LEN)) {
+		if (smc_pnet_match(ismdev->pnetid, ndev_pnetid)) {
 			*smcismdev = ismdev;
 			break;
 		}
@@ -715,7 +789,6 @@ void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev)
 	if (!dst->dev)
 		goto out_rel;
 
-	/* if possible, lookup via hardware-defined pnetid */
 	smc_pnet_find_ism_by_pnetid(dst->dev, smcismdev);
 
 out_rel:
-- 
2.16.4

[PATCH net-next 5/6] net/smc: add pnet table namespace support

[Ursula Braun]

From: Hans Wippel <hwippel@linux.ibm.com>

This patch adds namespace support to the pnet table code. Each network
namespace gets its own pnet table. Infiniband and smcd device pnetids
can only be modified in the initial namespace. In other namespaces they
can still be used as if they were set by the underlying hardware.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
---
 net/smc/af_smc.c    |  28 ++++++++++
 net/smc/smc_netns.h |  20 ++++++++
 net/smc/smc_pnet.c  | 145 ++++++++++++++++++++++++++++++++++++----------------
 net/smc/smc_pnet.h  |  12 +++++
 4 files changed, 162 insertions(+), 43 deletions(-)
 create mode 100644 net/smc/smc_netns.h

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 46fa9f3016cc..77ef53596d18 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -30,6 +30,10 @@
 #include <net/smc.h>
 #include <asm/ioctls.h>
 
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include "smc_netns.h"
+
 #include "smc.h"
 #include "smc_clc.h"
 #include "smc_llc.h"
@@ -1966,10 +1970,33 @@ static const struct net_proto_family smc_sock_family_ops = {
 	.create	= smc_create,
 };
 
+unsigned int smc_net_id;
+
+static __net_init int smc_net_init(struct net *net)
+{
+	return smc_pnet_net_init(net);
+}
+
+static void __net_exit smc_net_exit(struct net *net)
+{
+	smc_pnet_net_exit(net);
+}
+
+static struct pernet_operations smc_net_ops = {
+	.init = smc_net_init,
+	.exit = smc_net_exit,
+	.id   = &smc_net_id,
+	.size = sizeof(struct smc_net),
+};
+
 static int __init smc_init(void)
 {
 	int rc;
 
+	rc = register_pernet_subsys(&smc_net_ops);
+	if (rc)
+		return rc;
+
 	rc = smc_pnet_init();
 	if (rc)
 		return rc;
@@ -2035,6 +2062,7 @@ static void __exit smc_exit(void)
 	proto_unregister(&smc_proto6);
 	proto_unregister(&smc_proto);
 	smc_pnet_exit();
+	unregister_pernet_subsys(&smc_net_ops);
 }
 
 module_init(smc_init);
diff --git a/net/smc/smc_netns.h b/net/smc/smc_netns.h
new file mode 100644
index 000000000000..e7a8fc4ae02f
--- /dev/null
+++ b/net/smc/smc_netns.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Shared Memory Communications
+ *
+ * Network namespace definitions.
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#ifndef SMC_NETNS_H
+#define SMC_NETNS_H
+
+#include "smc_pnet.h"
+
+extern unsigned int smc_net_id;
+
+/* per-network namespace private data */
+struct smc_net {
+	struct smc_pnettable pnettable;
+};
+#endif
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 5497a8b44287..878f5c085444 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -20,6 +20,9 @@
 
 #include <rdma/ib_verbs.h>
 
+#include <net/netns/generic.h>
+#include "smc_netns.h"
+
 #include "smc_pnet.h"
 #include "smc_ib.h"
 #include "smc_ism.h"
@@ -46,19 +49,6 @@ static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
 
 static struct genl_family smc_pnet_nl_family;
 
-/**
- * struct smc_pnettable - SMC PNET table anchor
- * @lock: Lock for list action
- * @pnetlist: List of PNETIDs
- */
-static struct smc_pnettable {
-	rwlock_t lock;
-	struct list_head pnetlist;
-} smc_pnettable = {
-	.pnetlist = LIST_HEAD_INIT(smc_pnettable.pnetlist),
-	.lock = __RW_LOCK_UNLOCKED(smc_pnettable.lock)
-};
-
 /**
  * struct smc_user_pnetentry - pnet identifier name entry for/from user
  * @list: List node.
@@ -101,17 +91,23 @@ static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2)
 
 /* Remove a pnetid from the pnet table.
  */
-static int smc_pnet_remove_by_pnetid(char *pnet_name)
+static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name)
 {
 	struct smc_pnetentry *pnetelem, *tmp_pe;
+	struct smc_pnettable *pnettable;
 	struct smc_ib_device *ibdev;
 	struct smcd_dev *smcd_dev;
+	struct smc_net *sn;
 	int rc = -ENOENT;
 	int ibport;
 
+	/* get pnettable for namespace */
+	sn = net_generic(net, smc_net_id);
+	pnettable = &sn->pnettable;
+
 	/* remove netdevices */
-	write_lock(&smc_pnettable.lock);
-	list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
+	write_lock(&pnettable->lock);
+	list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist,
 				 list) {
 		if (!pnet_name ||
 		    smc_pnet_match(pnetelem->pnet_name, pnet_name)) {
@@ -121,7 +117,12 @@ static int smc_pnet_remove_by_pnetid(char *pnet_name)
 			rc = 0;
 		}
 	}
-	write_unlock(&smc_pnettable.lock);
+	write_unlock(&pnettable->lock);
+
+	/* if this is not the initial namespace, stop here */
+	if (net != &init_net)
+		return rc;
+
 	/* remove ib devices */
 	spin_lock(&smc_ib_devices.lock);
 	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
@@ -158,11 +159,17 @@ static int smc_pnet_remove_by_pnetid(char *pnet_name)
 static int smc_pnet_remove_by_ndev(struct net_device *ndev)
 {
 	struct smc_pnetentry *pnetelem, *tmp_pe;
+	struct smc_pnettable *pnettable;
+	struct net *net = dev_net(ndev);
+	struct smc_net *sn;
 	int rc = -ENOENT;
 
-	write_lock(&smc_pnettable.lock);
-	list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist,
-				 list) {
+	/* get pnettable for namespace */
+	sn = net_generic(net, smc_net_id);
+	pnettable = &sn->pnettable;
+
+	write_lock(&pnettable->lock);
+	list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) {
 		if (pnetelem->ndev == ndev) {
 			list_del(&pnetelem->list);
 			dev_put(pnetelem->ndev);
@@ -171,13 +178,14 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev)
 			break;
 		}
 	}
-	write_unlock(&smc_pnettable.lock);
+	write_unlock(&pnettable->lock);
 	return rc;
 }
 
 /* Append a pnetid to the end of the pnet table if not already on this list.
  */
-static int smc_pnet_enter(struct smc_user_pnetentry *new_pnetelem)
+static int smc_pnet_enter(struct smc_pnettable *pnettable,
+			  struct smc_user_pnetentry *new_pnetelem)
 {
 	u8 pnet_null[SMC_MAX_PNETID_LEN] = {0};
 	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
@@ -233,17 +241,17 @@ static int smc_pnet_enter(struct smc_user_pnetentry *new_pnetelem)
 	       SMC_MAX_PNETID_LEN);
 	tmp_pnetelem->ndev = new_pnetelem->ndev;
 
-	write_lock(&smc_pnettable.lock);
-	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
+	write_lock(&pnettable->lock);
+	list_for_each_entry(pnetelem, &pnettable->pnetlist, list) {
 		if (pnetelem->ndev == new_pnetelem->ndev)
 			new_netdev = false;
 	}
 	if (new_netdev) {
 		dev_hold(tmp_pnetelem->ndev);
-		list_add_tail(&tmp_pnetelem->list, &smc_pnettable.pnetlist);
-		write_unlock(&smc_pnettable.lock);
+		list_add_tail(&tmp_pnetelem->list, &pnettable->pnetlist);
+		write_unlock(&pnettable->lock);
 	} else {
-		write_unlock(&smc_pnettable.lock);
+		write_unlock(&pnettable->lock);
 		kfree(tmp_pnetelem);
 	}
 
@@ -340,6 +348,10 @@ static int smc_pnet_fill_entry(struct net *net,
 			goto error;
 	}
 
+	/* if this is not the initial namespace, stop here */
+	if (net != &init_net)
+		return 0;
+
 	rc = -EINVAL;
 	if (tb[SMC_PNETID_IBNAME]) {
 		ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
@@ -403,11 +415,17 @@ static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
 	struct smc_user_pnetentry pnetelem;
+	struct smc_pnettable *pnettable;
+	struct smc_net *sn;
 	int rc;
 
+	/* get pnettable for namespace */
+	sn = net_generic(net, smc_net_id);
+	pnettable = &sn->pnettable;
+
 	rc = smc_pnet_fill_entry(net, &pnetelem, info->attrs);
 	if (!rc)
-		rc = smc_pnet_enter(&pnetelem);
+		rc = smc_pnet_enter(pnettable, &pnetelem);
 	if (pnetelem.ndev)
 		dev_put(pnetelem.ndev);
 	return rc;
@@ -415,9 +433,11 @@ static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info)
 
 static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info)
 {
+	struct net *net = genl_info_net(info);
+
 	if (!info->attrs[SMC_PNETID_NAME])
 		return -EINVAL;
-	return smc_pnet_remove_by_pnetid(
+	return smc_pnet_remove_by_pnetid(net,
 				(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
 }
 
@@ -445,19 +465,25 @@ static int smc_pnet_dumpinfo(struct sk_buff *skb,
 	return 0;
 }
 
-static int _smc_pnet_dump(struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid,
-			  int start_idx)
+static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid,
+			  u32 seq, u8 *pnetid, int start_idx)
 {
 	struct smc_user_pnetentry tmp_entry;
+	struct smc_pnettable *pnettable;
 	struct smc_pnetentry *pnetelem;
 	struct smc_ib_device *ibdev;
 	struct smcd_dev *smcd_dev;
+	struct smc_net *sn;
 	int idx = 0;
 	int ibport;
 
+	/* get pnettable for namespace */
+	sn = net_generic(net, smc_net_id);
+	pnettable = &sn->pnettable;
+
 	/* dump netdevices */
-	read_lock(&smc_pnettable.lock);
-	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
+	read_lock(&pnettable->lock);
+	list_for_each_entry(pnetelem, &pnettable->pnetlist, list) {
 		if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid))
 			continue;
 		if (idx++ < start_idx)
@@ -472,7 +498,11 @@ static int _smc_pnet_dump(struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid,
 			break;
 		}
 	}
-	read_unlock(&smc_pnettable.lock);
+	read_unlock(&pnettable->lock);
+
+	/* if this is not the initial namespace, stop here */
+	if (net != &init_net)
+		return idx;
 
 	/* dump ib devices */
 	spin_lock(&smc_ib_devices.lock);
@@ -528,9 +558,10 @@ static int _smc_pnet_dump(struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid,
 
 static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct net *net = sock_net(skb->sk);
 	int idx;
 
-	idx = _smc_pnet_dump(skb, NETLINK_CB(cb->skb).portid,
+	idx = _smc_pnet_dump(net, skb, NETLINK_CB(cb->skb).portid,
 			     cb->nlh->nlmsg_seq, NULL, cb->args[0]);
 
 	cb->args[0] = idx;
@@ -540,6 +571,7 @@ static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb)
 /* Retrieve one PNETID entry */
 static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
 {
+	struct net *net = genl_info_net(info);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -550,7 +582,7 @@ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
 	if (!msg)
 		return -ENOMEM;
 
-	_smc_pnet_dump(msg, info->snd_portid, info->snd_seq,
+	_smc_pnet_dump(net, msg, info->snd_portid, info->snd_seq,
 		       nla_data(info->attrs[SMC_PNETID_NAME]), 0);
 
 	/* finish multi part message and send it */
@@ -567,7 +599,9 @@ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
  */
 static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info)
 {
-	return smc_pnet_remove_by_pnetid(NULL);
+	struct net *net = genl_info_net(info);
+
+	return smc_pnet_remove_by_pnetid(net, NULL);
 }
 
 /* SMC_PNETID generic netlink operation definition */
@@ -631,6 +665,18 @@ static struct notifier_block smc_netdev_notifier = {
 	.notifier_call = smc_pnet_netdev_event
 };
 
+/* init network namespace */
+int smc_pnet_net_init(struct net *net)
+{
+	struct smc_net *sn = net_generic(net, smc_net_id);
+	struct smc_pnettable *pnettable = &sn->pnettable;
+
+	INIT_LIST_HEAD(&pnettable->pnetlist);
+	rwlock_init(&pnettable->lock);
+
+	return 0;
+}
+
 int __init smc_pnet_init(void)
 {
 	int rc;
@@ -644,9 +690,15 @@ int __init smc_pnet_init(void)
 	return rc;
 }
 
+/* exit network namespace */
+void smc_pnet_net_exit(struct net *net)
+{
+	/* flush pnet table */
+	smc_pnet_remove_by_pnetid(net, NULL);
+}
+
 void smc_pnet_exit(void)
 {
-	smc_pnet_flush(NULL, NULL);
 	unregister_netdevice_notifier(&smc_netdev_notifier);
 	genl_unregister_family(&smc_pnet_nl_family);
 }
@@ -674,22 +726,29 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
 	return ndev;
 }
 
-static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *netdev,
+static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev,
 					      u8 *pnetid)
 {
+	struct smc_pnettable *pnettable;
+	struct net *net = dev_net(ndev);
 	struct smc_pnetentry *pnetelem;
+	struct smc_net *sn;
 	int rc = -ENOENT;
 
-	read_lock(&smc_pnettable.lock);
-	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
-		if (netdev == pnetelem->ndev) {
+	/* get pnettable for namespace */
+	sn = net_generic(net, smc_net_id);
+	pnettable = &sn->pnettable;
+
+	read_lock(&pnettable->lock);
+	list_for_each_entry(pnetelem, &pnettable->pnetlist, list) {
+		if (ndev == pnetelem->ndev) {
 			/* get pnetid of netdev device */
 			memcpy(pnetid, pnetelem->pnet_name, SMC_MAX_PNETID_LEN);
 			rc = 0;
 			break;
 		}
 	}
-	read_unlock(&smc_pnettable.lock);
+	read_unlock(&pnettable->lock);
 	return rc;
 }
 
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 37044e4ee50f..5eac42fb45d0 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -19,6 +19,16 @@
 struct smc_ib_device;
 struct smcd_dev;
 
+/**
+ * struct smc_pnettable - SMC PNET table anchor
+ * @lock: Lock for list action
+ * @pnetlist: List of PNETIDs
+ */
+struct smc_pnettable {
+	rwlock_t lock;
+	struct list_head pnetlist;
+};
+
 static inline int smc_pnetid_by_dev_port(struct device *dev,
 					 unsigned short port, u8 *pnetid)
 {
@@ -30,7 +40,9 @@ static inline int smc_pnetid_by_dev_port(struct device *dev,
 }
 
 int smc_pnet_init(void) __init;
+int smc_pnet_net_init(struct net *net);
 void smc_pnet_exit(void);
+void smc_pnet_net_exit(struct net *net);
 void smc_pnet_find_roce_resource(struct sock *sk,
 				 struct smc_ib_device **smcibdev, u8 *ibport,
 				 unsigned short vlan_id, u8 gid[]);
-- 
2.16.4

[PATCH net-next 6/6] net/smc: allow PCI IDs as ib device names in the pnet table

[Ursula Braun]

From: Hans Wippel <hwippel@linux.ibm.com>

SMC-D devices are identified by their PCI IDs in the pnet table. In
order to make usage of the pnet table more consistent for users, this
patch adds this form of identification for ib devices as well.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
---
 net/smc/smc_pnet.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 878f5c085444..25dfbe343e26 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -293,7 +293,9 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
 	spin_lock(&smc_ib_devices.lock);
 	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
 		if (!strncmp(ibdev->ibdev->name, ib_name,
-			     sizeof(ibdev->ibdev->name))) {
+			     sizeof(ibdev->ibdev->name)) ||
+		    !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name,
+			     IB_DEVICE_NAME_MAX - 1)) {
 			goto out;
 		}
 	}
@@ -394,7 +396,7 @@ static int smc_pnet_set_nla(struct sk_buff *msg,
 	}
 	if (pnetelem->smcibdev) {
 		if (nla_put_string(msg, SMC_PNETID_IBNAME,
-				   pnetelem->smcibdev->ibdev->name) ||
+			dev_name(pnetelem->smcibdev->ibdev->dev.parent)) ||
 		    nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port))
 			return -1;
 	} else if (pnetelem->smcd_dev) {
-- 
2.16.4

Re: [PATCH net-next 0/6] net/smc: patches 2019-02-21

[David Miller]

From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 21 Feb 2019 13:00:57 +0100

> here are patches for SMC:
> * patch 1 is a cleanup without functional change
> * patches 2-6 enhance SMC pnetid support

Series applied, thanks.