Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull main batch of InfiniBand/RDMA changes from Roland Dreier:
 - Large ocrdma HW driver update: add "fast register" work requests,
   fixes, cleanups
 - Add receive flow steering support for raw QPs
 - Fix IPoIB neighbour race that leads to crash
 - iSER updates including support for using "fast register" memory
   registration
 - IPv6 support for iWARP
 - XRC transport fixes

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (54 commits)
  RDMA/ocrdma: Fix compiler warning about int/pointer size mismatch
  IB/iser: Fix redundant pointer check in dealloc flow
  IB/iser: Fix possible memory leak in iser_create_frwr_pool()
  IB/qib: Move COUNTER_MASK definition within qib_mad.h header guards
  RDMA/ocrdma: Fix passing wrong opcode to modify_srq
  RDMA/ocrdma: Fill PVID in UMC case
  RDMA/ocrdma: Add ABI versioning support
  RDMA/ocrdma: Consider multiple SGES in case of DPP
  RDMA/ocrdma: Fix for displaying proper link speed
  RDMA/ocrdma: Increase STAG array size
  RDMA/ocrdma: Dont use PD 0 for userpace CQ DB
  RDMA/ocrdma: FRMA code cleanup
  RDMA/ocrdma: For ERX2 irrespective of Qid, num_posted offset is 24
  RDMA/ocrdma: Fix to work with even a single MSI-X vector
  RDMA/ocrdma: Remove the MTU check based on Ethernet MTU
  RDMA/ocrdma: Add support for fast register work requests (FRWR)
  RDMA/ocrdma: Create IRD queue fix
  IB/core: Better checking of userspace values for receive flow steering
  IB/mlx4: Add receive flow steering support
  IB/core: Export ib_create/destroy_flow through uverbs
  ...

6 files changed, 334 insertions, 3 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 2aafb809e067..dfd1e36f5753 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -576,6 +576,7 @@ struct adapter {
 	struct l2t_data *l2t;
 	void *uld_handle[CXGB4_ULD_MAX];
 	struct list_head list_node;
+	struct list_head rcu_node;
 
 	struct tid_info tids;
 	void **tid_release_head;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 5a3256b083f2..038df4b96139 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -60,6 +60,7 @@
 #include <linux/workqueue.h>
 #include <net/neighbour.h>
 #include <net/netevent.h>
+#include <net/addrconf.h>
 #include <asm/uaccess.h>
 
 #include "cxgb4.h"
@@ -68,6 +69,11 @@
 #include "t4fw_api.h"
 #include "l2t.h"
 
+#include <../drivers/net/bonding/bonding.h>
+
+#ifdef DRV_VERSION
+#undef DRV_VERSION
+#endif
 #define DRV_VERSION "2.0.0-ko"
 #define DRV_DESC "Chelsio T4/T5 Network Driver"
 
@@ -400,6 +406,9 @@ static struct dentry *cxgb4_debugfs_root;
 
 static LIST_HEAD(adapter_list);
 static DEFINE_MUTEX(uld_mutex);
+/* Adapter list to be accessed from atomic context */
+static LIST_HEAD(adap_rcu_list);
+static DEFINE_SPINLOCK(adap_rcu_lock);
 static struct cxgb4_uld_info ulds[CXGB4_ULD_MAX];
 static const char *uld_str[] = { "RDMA", "iSCSI" };
 
@@ -3227,6 +3236,38 @@ static int tid_init(struct tid_info *t)
 	return 0;
 }
 
+static int cxgb4_clip_get(const struct net_device *dev,
+			  const struct in6_addr *lip)
+{
+	struct adapter *adap;
+	struct fw_clip_cmd c;
+
+	adap = netdev2adap(dev);
+	memset(&c, 0, sizeof(c));
+	c.op_to_write = htonl(FW_CMD_OP(FW_CLIP_CMD) |
+			FW_CMD_REQUEST | FW_CMD_WRITE);
+	c.alloc_to_len16 = htonl(F_FW_CLIP_CMD_ALLOC | FW_LEN16(c));
+	*(__be64 *)&c.ip_hi = *(__be64 *)(lip->s6_addr);
+	*(__be64 *)&c.ip_lo = *(__be64 *)(lip->s6_addr + 8);
+	return t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, false);
+}
+
+static int cxgb4_clip_release(const struct net_device *dev,
+			      const struct in6_addr *lip)
+{
+	struct adapter *adap;
+	struct fw_clip_cmd c;
+
+	adap = netdev2adap(dev);
+	memset(&c, 0, sizeof(c));
+	c.op_to_write = htonl(FW_CMD_OP(FW_CLIP_CMD) |
+			FW_CMD_REQUEST | FW_CMD_READ);
+	c.alloc_to_len16 = htonl(F_FW_CLIP_CMD_FREE | FW_LEN16(c));
+	*(__be64 *)&c.ip_hi = *(__be64 *)(lip->s6_addr);
+	*(__be64 *)&c.ip_lo = *(__be64 *)(lip->s6_addr + 8);
+	return t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, false);
+}
+
 /**
  *	cxgb4_create_server - create an IP server
  *	@dev: the device
@@ -3246,6 +3287,7 @@ int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
 	struct sk_buff *skb;
 	struct adapter *adap;
 	struct cpl_pass_open_req *req;
+	int ret;
 
 	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
 	if (!skb)
@@ -3263,10 +3305,78 @@ int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
 	req->opt0 = cpu_to_be64(TX_CHAN(chan));
 	req->opt1 = cpu_to_be64(CONN_POLICY_ASK |
 				SYN_RSS_ENABLE | SYN_RSS_QUEUE(queue));
-	return t4_mgmt_tx(adap, skb);
+	ret = t4_mgmt_tx(adap, skb);
+	return net_xmit_eval(ret);
 }
 EXPORT_SYMBOL(cxgb4_create_server);
 
+/*	cxgb4_create_server6 - create an IPv6 server
+ *	@dev: the device
+ *	@stid: the server TID
+ *	@sip: local IPv6 address to bind server to
+ *	@sport: the server's TCP port
+ *	@queue: queue to direct messages from this server to
+ *
+ *	Create an IPv6 server for the given port and address.
+ *	Returns <0 on error and one of the %NET_XMIT_* values on success.
+ */
+int cxgb4_create_server6(const struct net_device *dev, unsigned int stid,
+			 const struct in6_addr *sip, __be16 sport,
+			 unsigned int queue)
+{
+	unsigned int chan;
+	struct sk_buff *skb;
+	struct adapter *adap;
+	struct cpl_pass_open_req6 *req;
+	int ret;
+
+	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	adap = netdev2adap(dev);
+	req = (struct cpl_pass_open_req6 *)__skb_put(skb, sizeof(*req));
+	INIT_TP_WR(req, 0);
+	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_PASS_OPEN_REQ6, stid));
+	req->local_port = sport;
+	req->peer_port = htons(0);
+	req->local_ip_hi = *(__be64 *)(sip->s6_addr);
+	req->local_ip_lo = *(__be64 *)(sip->s6_addr + 8);
+	req->peer_ip_hi = cpu_to_be64(0);
+	req->peer_ip_lo = cpu_to_be64(0);
+	chan = rxq_to_chan(&adap->sge, queue);
+	req->opt0 = cpu_to_be64(TX_CHAN(chan));
+	req->opt1 = cpu_to_be64(CONN_POLICY_ASK |
+				SYN_RSS_ENABLE | SYN_RSS_QUEUE(queue));
+	ret = t4_mgmt_tx(adap, skb);
+	return net_xmit_eval(ret);
+}
+EXPORT_SYMBOL(cxgb4_create_server6);
+
+int cxgb4_remove_server(const struct net_device *dev, unsigned int stid,
+			unsigned int queue, bool ipv6)
+{
+	struct sk_buff *skb;
+	struct adapter *adap;
+	struct cpl_close_listsvr_req *req;
+	int ret;
+
+	adap = netdev2adap(dev);
+
+	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	req = (struct cpl_close_listsvr_req *)__skb_put(skb, sizeof(*req));
+	INIT_TP_WR(req, 0);
+	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_CLOSE_LISTSRV_REQ, stid));
+	req->reply_ctrl = htons(NO_REPLY(0) | (ipv6 ? LISTSVR_IPV6(1) :
+				LISTSVR_IPV6(0)) | QUEUENO(queue));
+	ret = t4_mgmt_tx(adap, skb);
+	return net_xmit_eval(ret);
+}
+EXPORT_SYMBOL(cxgb4_remove_server);
+
 /**
  *	cxgb4_best_mtu - find the entry in the MTU table closest to an MTU
  *	@mtus: the HW MTU table
@@ -3721,6 +3831,10 @@ static void attach_ulds(struct adapter *adap)
 {
 	unsigned int i;
 
+	spin_lock(&adap_rcu_lock);
+	list_add_tail_rcu(&adap->rcu_node, &adap_rcu_list);
+	spin_unlock(&adap_rcu_lock);
+
 	mutex_lock(&uld_mutex);
 	list_add_tail(&adap->list_node, &adapter_list);
 	for (i = 0; i < CXGB4_ULD_MAX; i++)
@@ -3746,6 +3860,10 @@ static void detach_ulds(struct adapter *adap)
 		netevent_registered = false;
 	}
 	mutex_unlock(&uld_mutex);
+
+	spin_lock(&adap_rcu_lock);
+	list_del_rcu(&adap->rcu_node);
+	spin_unlock(&adap_rcu_lock);
 }
 
 static void notify_ulds(struct adapter *adap, enum cxgb4_state new_state)
@@ -3809,6 +3927,169 @@ int cxgb4_unregister_uld(enum cxgb4_uld type)
 }
 EXPORT_SYMBOL(cxgb4_unregister_uld);
 
+/* Check if netdev on which event is occured belongs to us or not. Return
+ * suceess (1) if it belongs otherwise failure (0).
+ */
+static int cxgb4_netdev(struct net_device *netdev)
+{
+	struct adapter *adap;
+	int i;
+
+	spin_lock(&adap_rcu_lock);
+	list_for_each_entry_rcu(adap, &adap_rcu_list, rcu_node)
+		for (i = 0; i < MAX_NPORTS; i++)
+			if (adap->port[i] == netdev) {
+				spin_unlock(&adap_rcu_lock);
+				return 1;
+			}
+	spin_unlock(&adap_rcu_lock);
+	return 0;
+}
+
+static int clip_add(struct net_device *event_dev, struct inet6_ifaddr *ifa,
+		    unsigned long event)
+{
+	int ret = NOTIFY_DONE;
+
+	rcu_read_lock();
+	if (cxgb4_netdev(event_dev)) {
+		switch (event) {
+		case NETDEV_UP:
+			ret = cxgb4_clip_get(event_dev,
+				(const struct in6_addr *)ifa->addr.s6_addr);
+			if (ret < 0) {
+				rcu_read_unlock();
+				return ret;
+			}
+			ret = NOTIFY_OK;
+			break;
+		case NETDEV_DOWN:
+			cxgb4_clip_release(event_dev,
+				(const struct in6_addr *)ifa->addr.s6_addr);
+			ret = NOTIFY_OK;
+			break;
+		default:
+			break;
+		}
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static int cxgb4_inet6addr_handler(struct notifier_block *this,
+		unsigned long event, void *data)
+{
+	struct inet6_ifaddr *ifa = data;
+	struct net_device *event_dev;
+	int ret = NOTIFY_DONE;
+	int cnt;
+	struct bonding *bond = netdev_priv(ifa->idev->dev);
+	struct slave *slave;
+	struct pci_dev *first_pdev = NULL;
+
+	if (ifa->idev->dev->priv_flags & IFF_802_1Q_VLAN) {
+		event_dev = vlan_dev_real_dev(ifa->idev->dev);
+		ret = clip_add(event_dev, ifa, event);
+	} else if (ifa->idev->dev->flags & IFF_MASTER) {
+		/* It is possible that two different adapters are bonded in one
+		 * bond. We need to find such different adapters and add clip
+		 * in all of them only once.
+		 */
+		read_lock(&bond->lock);
+		bond_for_each_slave(bond, slave, cnt) {
+			if (!first_pdev) {
+				ret = clip_add(slave->dev, ifa, event);
+				/* If clip_add is success then only initialize
+				 * first_pdev since it means it is our device
+				 */
+				if (ret == NOTIFY_OK)
+					first_pdev = to_pci_dev(
+							slave->dev->dev.parent);
+			} else if (first_pdev !=
+				   to_pci_dev(slave->dev->dev.parent))
+					ret = clip_add(slave->dev, ifa, event);
+		}
+		read_unlock(&bond->lock);
+	} else
+		ret = clip_add(ifa->idev->dev, ifa, event);
+
+	return ret;
+}
+
+static struct notifier_block cxgb4_inet6addr_notifier = {
+	.notifier_call = cxgb4_inet6addr_handler
+};
+
+/* Retrieves IPv6 addresses from a root device (bond, vlan) associated with
+ * a physical device.
+ * The physical device reference is needed to send the actul CLIP command.
+ */
+static int update_dev_clip(struct net_device *root_dev, struct net_device *dev)
+{
+	struct inet6_dev *idev = NULL;
+	struct inet6_ifaddr *ifa;
+	int ret = 0;
+
+	idev = __in6_dev_get(root_dev);
+	if (!idev)
+		return ret;
+
+	read_lock_bh(&idev->lock);
+	list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		ret = cxgb4_clip_get(dev,
+				(const struct in6_addr *)ifa->addr.s6_addr);
+		if (ret < 0)
+			break;
+	}
+	read_unlock_bh(&idev->lock);
+
+	return ret;
+}
+
+static int update_root_dev_clip(struct net_device *dev)
+{
+	struct net_device *root_dev = NULL;
+	int i, ret = 0;
+
+	/* First populate the real net device's IPv6 addresses */
+	ret = update_dev_clip(dev, dev);
+	if (ret)
+		return ret;
+
+	/* Parse all bond and vlan devices layered on top of the physical dev */
+	for (i = 0; i < VLAN_N_VID; i++) {
+		root_dev = __vlan_find_dev_deep(dev, htons(ETH_P_8021Q), i);
+		if (!root_dev)
+			continue;
+
+		ret = update_dev_clip(root_dev, dev);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+static void update_clip(const struct adapter *adap)
+{
+	int i;
+	struct net_device *dev;
+	int ret;
+
+	rcu_read_lock();
+
+	for (i = 0; i < MAX_NPORTS; i++) {
+		dev = adap->port[i];
+		ret = 0;
+
+		if (dev)
+			ret = update_root_dev_clip(dev);
+
+		if (ret < 0)
+			break;
+	}
+	rcu_read_unlock();
+}
+
 /**
  *	cxgb_up - enable the adapter
  *	@adap: adapter being enabled
@@ -3854,6 +4135,7 @@ static int cxgb_up(struct adapter *adap)
 	t4_intr_enable(adap);
 	adap->flags |= FULL_INIT_DONE;
 	notify_ulds(adap, CXGB4_STATE_UP);
+	update_clip(adap);
  out:
 	return err;
  irq_err:
@@ -5870,11 +6152,15 @@ static int __init cxgb4_init_module(void)
 	ret = pci_register_driver(&cxgb4_driver);
 	if (ret < 0)
 		debugfs_remove(cxgb4_debugfs_root);
+
+	register_inet6addr_notifier(&cxgb4_inet6addr_notifier);
+
 	return ret;
 }
 
 static void __exit cxgb4_cleanup_module(void)
 {
+	unregister_inet6addr_notifier(&cxgb4_inet6addr_notifier);
 	pci_unregister_driver(&cxgb4_driver);
 	debugfs_remove(cxgb4_debugfs_root);  /* NULL ok */
 	flush_workqueue(workq);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 4faf4d067ee7..6f21f2451c30 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -154,6 +154,11 @@ struct in6_addr;
 int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
 			__be32 sip, __be16 sport, __be16 vlan,
 			unsigned int queue);
+int cxgb4_create_server6(const struct net_device *dev, unsigned int stid,
+			 const struct in6_addr *sip, __be16 sport,
+			 unsigned int queue);
+int cxgb4_remove_server(const struct net_device *dev, unsigned int stid,
+			unsigned int queue, bool ipv6);
 int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
 			       __be32 sip, __be16 sport, __be16 vlan,
 			       unsigned int queue,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index 01d484441200..cd6874b571ee 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -320,6 +320,21 @@ struct cpl_act_open_req6 {
 	__be32 opt2;
 };
 
+struct cpl_t5_act_open_req6 {
+	WR_HDR;
+	union opcode_tid ot;
+	__be16 local_port;
+	__be16 peer_port;
+	__be64 local_ip_hi;
+	__be64 local_ip_lo;
+	__be64 peer_ip_hi;
+	__be64 peer_ip_lo;
+	__be64 opt0;
+	__be32 rsvd;
+	__be32 opt2;
+	__be64 params;
+};
+
 struct cpl_act_open_rpl {
 	union opcode_tid ot;
 	__be32 atid_status;
@@ -405,7 +420,7 @@ struct cpl_close_listsvr_req {
 	WR_HDR;
 	union opcode_tid ot;
 	__be16 reply_ctrl;
-#define LISTSVR_IPV6 (1 << 14)
+#define LISTSVR_IPV6(x) ((x) << 14)
 	__be16 rsvd;
 };
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index d1c755f78aaf..6f77ac487743 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -616,6 +616,7 @@ enum fw_cmd_opcodes {
 	FW_RSS_IND_TBL_CMD             = 0x20,
 	FW_RSS_GLB_CONFIG_CMD          = 0x22,
 	FW_RSS_VI_CONFIG_CMD           = 0x23,
+	FW_CLIP_CMD                    = 0x28,
 	FW_LASTC2E_CMD                 = 0x40,
 	FW_ERROR_CMD                   = 0x80,
 	FW_DEBUG_CMD                   = 0x81,
@@ -2062,6 +2063,28 @@ struct fw_rss_vi_config_cmd {
 	} u;
 };
 
+struct fw_clip_cmd {
+	__be32 op_to_write;
+	__be32 alloc_to_len16;
+	__be64 ip_hi;
+	__be64 ip_lo;
+	__be32 r4[2];
+};
+
+#define S_FW_CLIP_CMD_ALLOC     31
+#define M_FW_CLIP_CMD_ALLOC     0x1
+#define V_FW_CLIP_CMD_ALLOC(x)  ((x) << S_FW_CLIP_CMD_ALLOC)
+#define G_FW_CLIP_CMD_ALLOC(x)  \
+	(((x) >> S_FW_CLIP_CMD_ALLOC) & M_FW_CLIP_CMD_ALLOC)
+#define F_FW_CLIP_CMD_ALLOC     V_FW_CLIP_CMD_ALLOC(1U)
+
+#define S_FW_CLIP_CMD_FREE      30
+#define M_FW_CLIP_CMD_FREE      0x1
+#define V_FW_CLIP_CMD_FREE(x)   ((x) << S_FW_CLIP_CMD_FREE)
+#define G_FW_CLIP_CMD_FREE(x)   \
+	(((x) >> S_FW_CLIP_CMD_FREE) & M_FW_CLIP_CMD_FREE)
+#define F_FW_CLIP_CMD_FREE      V_FW_CLIP_CMD_FREE(1U)
+
 enum fw_error_type {
 	FW_ERROR_TYPE_EXCEPTION		= 0x0,
 	FW_ERROR_TYPE_HWMODULE		= 0x1,
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index f984a89c27df..dd6876321116 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1909,7 +1909,8 @@ static int qp_get_mtt_size(struct mlx4_qp_context *qpc)
 	int log_rq_stride = qpc->rq_size_stride & 7;
 	int srq = (be32_to_cpu(qpc->srqn) >> 24) & 1;
 	int rss = (be32_to_cpu(qpc->flags) >> 13) & 1;
-	int xrc = (be32_to_cpu(qpc->local_qpn) >> 23) & 1;
+	u32 ts = (be32_to_cpu(qpc->flags) >> 16) & 0xff;
+	int xrc = (ts == MLX4_QP_ST_XRC) ? 1 : 0;
 	int sq_size;
 	int rq_size;
 	int total_pages;