From 2bd01c5d2ed04838d50548cb7b955505a20ac0bd Mon Sep 17 00:00:00 2001
From: Roland Dreier <rolandd@cisco.com>
Date: Wed, 23 Apr 2008 11:52:18 -0700
Subject: [PATCH 01/14] RDMA/nes: Use print_mac() to format ethernet addresses
 for printing

Removing open-coded MAC formats shrinks the source and the generated
code too, eg on x86-64:

add/remove: 0/0 grow/shrink: 0/4 up/down: 0/-103 (-103)
function                                     old     new   delta
make_cm_node                                 932     912     -20
nes_netdev_set_mac_address                   427     406     -21
nes_netdev_set_multicast_list               1148    1124     -24
nes_probe                                   2349    2311     -38

Acked-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/nes/nes.c     | 10 ++++------
 drivers/infiniband/hw/nes/nes_cm.c  |  8 +++-----
 drivers/infiniband/hw/nes/nes_nic.c | 18 ++++++++----------
 3 files changed, 15 insertions(+), 21 deletions(-)

diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c
index b046262ed638..c0671ad7de82 100644
--- a/drivers/infiniband/hw/nes/nes.c
+++ b/drivers/infiniband/hw/nes/nes.c
@@ -353,13 +353,11 @@ struct ib_qp *nes_get_qp(struct ib_device *device, int qpn)
  */
 static void nes_print_macaddr(struct net_device *netdev)
 {
-	nes_debug(NES_DBG_INIT, "%s: MAC %02X:%02X:%02X:%02X:%02X:%02X, IRQ %u\n",
-			netdev->name,
-			netdev->dev_addr[0], netdev->dev_addr[1], netdev->dev_addr[2],
-			netdev->dev_addr[3], netdev->dev_addr[4], netdev->dev_addr[5],
-			netdev->irq);
-}
+	DECLARE_MAC_BUF(mac);
 
+	nes_debug(NES_DBG_INIT, "%s: %s, IRQ %u\n",
+		  netdev->name, print_mac(mac, netdev->dev_addr), netdev->irq);
+}
 
 /**
  * nes_interrupt - handle interrupts
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index d0738623bcf3..b53bceb44255 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1054,6 +1054,7 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 	int arpindex = 0;
 	struct nes_device *nesdev;
 	struct nes_adapter *nesadapter;
+	DECLARE_MAC_BUF(mac);
 
 	/* create an hte and cm_node for this instance */
 	cm_node = kzalloc(sizeof(*cm_node), GFP_ATOMIC);
@@ -1116,11 +1117,8 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 
 	/* copy the mac addr to node context */
 	memcpy(cm_node->rem_mac, nesadapter->arp_table[arpindex].mac_addr, ETH_ALEN);
-	nes_debug(NES_DBG_CM, "Remote mac addr from arp table:%02x,"
-			" %02x, %02x, %02x, %02x, %02x\n",
-			cm_node->rem_mac[0], cm_node->rem_mac[1],
-			cm_node->rem_mac[2], cm_node->rem_mac[3],
-			cm_node->rem_mac[4], cm_node->rem_mac[5]);
+	nes_debug(NES_DBG_CM, "Remote mac addr from arp table: %s\n",
+		  print_mac(mac, cm_node->rem_mac));
 
 	add_hte_node(cm_core, cm_node);
 	atomic_inc(&cm_nodes_created);
diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c
index 01cd0effc492..e5366b013c1a 100644
--- a/drivers/infiniband/hw/nes/nes_nic.c
+++ b/drivers/infiniband/hw/nes/nes_nic.c
@@ -787,16 +787,14 @@ static int nes_netdev_set_mac_address(struct net_device *netdev, void *p)
 	int i;
 	u32 macaddr_low;
 	u16 macaddr_high;
+	DECLARE_MAC_BUF(mac);
 
 	if (!is_valid_ether_addr(mac_addr->sa_data))
 		return -EADDRNOTAVAIL;
 
 	memcpy(netdev->dev_addr, mac_addr->sa_data, netdev->addr_len);
-	printk(PFX "%s: Address length = %d, Address = %02X%02X%02X%02X%02X%02X..\n",
-		   __func__, netdev->addr_len,
-		   mac_addr->sa_data[0], mac_addr->sa_data[1],
-		   mac_addr->sa_data[2], mac_addr->sa_data[3],
-		   mac_addr->sa_data[4], mac_addr->sa_data[5]);
+	printk(PFX "%s: Address length = %d, Address = %s\n",
+	       __func__, netdev->addr_len, print_mac(mac, mac_addr->sa_data));
 	macaddr_high = ((u16)netdev->dev_addr[0]) << 8;
 	macaddr_high += (u16)netdev->dev_addr[1];
 	macaddr_low = ((u32)netdev->dev_addr[2]) << 24;
@@ -878,11 +876,11 @@ static void nes_netdev_set_multicast_list(struct net_device *netdev)
 			if (mc_nic_index < 0)
 				mc_nic_index = nesvnic->nic_index;
 			if (multicast_addr) {
-				nes_debug(NES_DBG_NIC_RX, "Assigning MC Address = %02X%02X%02X%02X%02X%02X to register 0x%04X nic_idx=%d\n",
-						  multicast_addr->dmi_addr[0], multicast_addr->dmi_addr[1],
-						  multicast_addr->dmi_addr[2], multicast_addr->dmi_addr[3],
-						  multicast_addr->dmi_addr[4], multicast_addr->dmi_addr[5],
-						  perfect_filter_register_address+(mc_index * 8), mc_nic_index);
+				DECLARE_MAC_BUF(mac);
+				nes_debug(NES_DBG_NIC_RX, "Assigning MC Address %s to register 0x%04X nic_idx=%d\n",
+					  print_mac(mac, multicast_addr->dmi_addr),
+					  perfect_filter_register_address+(mc_index * 8),
+					  mc_nic_index);
 				macaddr_high = ((u16)multicast_addr->dmi_addr[0]) << 8;
 				macaddr_high += (u16)multicast_addr->dmi_addr[1];
 				macaddr_low = ((u32)multicast_addr->dmi_addr[2]) << 24;

From e447703123d817b3f802c6eb69171d5342c8832e Mon Sep 17 00:00:00 2001
From: Roland Dreier <rolandd@cisco.com>
Date: Wed, 23 Apr 2008 11:55:43 -0700
Subject: [PATCH 02/14] RDMA/nes: Print IPv4 addresses in a readable format

Use NIPQUAD_FMT instead of printing raw 32-bit hex quantities in
debugging output.

Acked-by: Glenn Streiff <gstreiff@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/nes/nes.c       |  5 +++--
 drivers/infiniband/hw/nes/nes_cm.c    | 13 +++++++------
 drivers/infiniband/hw/nes/nes_utils.c |  4 +++-
 3 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c
index c0671ad7de82..a4e9269a29bd 100644
--- a/drivers/infiniband/hw/nes/nes.c
+++ b/drivers/infiniband/hw/nes/nes.c
@@ -139,8 +139,9 @@ static int nes_inetaddr_event(struct notifier_block *notifier,
 
 	addr = ntohl(ifa->ifa_address);
 	mask = ntohl(ifa->ifa_mask);
-	nes_debug(NES_DBG_NETDEV, "nes_inetaddr_event: ip address %08X, netmask %08X.\n",
-			addr, mask);
+	nes_debug(NES_DBG_NETDEV, "nes_inetaddr_event: ip address " NIPQUAD_FMT
+		  ", netmask " NIPQUAD_FMT ".\n",
+		  HIPQUAD(addr), HIPQUAD(mask));
 	list_for_each_entry(nesdev, &nes_dev_list, list) {
 		nes_debug(NES_DBG_NETDEV, "Nesdev list entry = 0x%p. (%s)\n",
 				nesdev, nesdev->netdev[0]->name);
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index b53bceb44255..38ea14cc7077 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -852,8 +852,8 @@ static struct nes_cm_node *find_node(struct nes_cm_core *cm_core,
 	/* get a handle on the hte */
 	hte = &cm_core->connected_nodes;
 
-	nes_debug(NES_DBG_CM, "Searching for an owner node:%x:%x from core %p->%p\n",
-			loc_addr, loc_port, cm_core, hte);
+	nes_debug(NES_DBG_CM, "Searching for an owner node: " NIPQUAD_FMT ":%x from core %p->%p\n",
+		  HIPQUAD(loc_addr), loc_port, cm_core, hte);
 
 	/* walk list and find cm_node associated with this session ID */
 	spin_lock_irqsave(&cm_core->ht_lock, flags);
@@ -902,8 +902,8 @@ static struct nes_cm_listener *find_listener(struct nes_cm_core *cm_core,
 	}
 	spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
 
-	nes_debug(NES_DBG_CM, "Unable to find listener- %x:%x\n",
-			dst_addr, dst_port);
+	nes_debug(NES_DBG_CM, "Unable to find listener for " NIPQUAD_FMT ":%x\n",
+		  HIPQUAD(dst_addr), dst_port);
 
 	/* no listener */
 	return NULL;
@@ -1067,8 +1067,9 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 	cm_node->loc_port = cm_info->loc_port;
 	cm_node->rem_port = cm_info->rem_port;
 	cm_node->send_write0 = send_first;
-	nes_debug(NES_DBG_CM, "Make node addresses : loc = %x:%x, rem = %x:%x\n",
-			cm_node->loc_addr, cm_node->loc_port, cm_node->rem_addr, cm_node->rem_port);
+	nes_debug(NES_DBG_CM, "Make node addresses : loc = " NIPQUAD_FMT ":%x, rem = " NIPQUAD_FMT ":%x\n",
+		  HIPQUAD(cm_node->loc_addr), cm_node->loc_port,
+		  HIPQUAD(cm_node->rem_addr), cm_node->rem_port);
 	cm_node->listener = listener;
 	cm_node->netdev = nesvnic->netdev;
 	cm_node->cm_id = cm_info->cm_id;
diff --git a/drivers/infiniband/hw/nes/nes_utils.c b/drivers/infiniband/hw/nes/nes_utils.c
index f9db07c2717d..c6d5631a6995 100644
--- a/drivers/infiniband/hw/nes/nes_utils.c
+++ b/drivers/infiniband/hw/nes/nes_utils.c
@@ -660,7 +660,9 @@ int nes_arp_table(struct nes_device *nesdev, u32 ip_addr, u8 *mac_addr, u32 acti
 
 	/* DELETE or RESOLVE */
 	if (arp_index == nesadapter->arp_table_size) {
-		nes_debug(NES_DBG_NETDEV, "mac address not in ARP table - cannot delete or resolve\n");
+		nes_debug(NES_DBG_NETDEV, "MAC for " NIPQUAD_FMT " not in ARP table - cannot %s\n",
+			  HIPQUAD(ip_addr),
+			  action == NES_ARP_RESOLVE ? "resolve" : "delete");
 		return -1;
 	}
 

From bc5698f3ecc9587e1edb343a2878f8d228c49e0e Mon Sep 17 00:00:00 2001
From: Chien Tung <ctung@neteffect.com>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 03/14] RDMA/nes: Fix adapter reset after PXE boot

After PXE boot, the iw_nes driver does a full reset to ensure the card
is in a clean state.  However, it doesn't wait for firmware to
complete its work before issuing a port reset to enable the ports,
which leads to problems bringing up the ports.

The solution is to wait for firmware to complete its work before
proceeding with port reset.

This bug was flagged by Roland Dreier <rolandd@cisco.com>.

Cc: <stable@kernel.org>
Signed-off-by: Chien Tung <ctung@neteffect.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/nes/nes_cm.c |  6 ++++--
 drivers/infiniband/hw/nes/nes_hw.c | 20 +++++++++-----------
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 38ea14cc7077..d940fc27129a 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1849,8 +1849,10 @@ static int mini_cm_recv_pkt(struct nes_cm_core *cm_core, struct nes_vnic *nesvni
 	nfo.rem_addr = ntohl(iph->saddr);
 	nfo.rem_port = ntohs(tcph->source);
 
-	nes_debug(NES_DBG_CM, "Received packet: dest=0x%08X:0x%04X src=0x%08X:0x%04X\n",
-			iph->daddr, tcph->dest, iph->saddr, tcph->source);
+	nes_debug(NES_DBG_CM, "Received packet: dest=" NIPQUAD_FMT
+		  ":0x%04X src=" NIPQUAD_FMT ":0x%04X\n",
+		  NIPQUAD(iph->daddr), tcph->dest,
+		  NIPQUAD(iph->saddr), tcph->source);
 
 	/* note: this call is going to increment cm_node ref count */
 	cm_node = find_node(cm_core,
diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c
index aa53aab91bf8..08964cc7e98a 100644
--- a/drivers/infiniband/hw/nes/nes_hw.c
+++ b/drivers/infiniband/hw/nes/nes_hw.c
@@ -636,6 +636,15 @@ static unsigned int nes_reset_adapter_ne020(struct nes_device *nesdev, u8 *OneG_
 			nes_debug(NES_DBG_INIT, "Did not see full soft reset done.\n");
 			return 0;
 		}
+
+		i = 0;
+		while ((nes_read_indexed(nesdev, NES_IDX_INT_CPU_STATUS) != 0x80) && i++ < 10000)
+			mdelay(1);
+		if (i >= 10000) {
+			printk(KERN_ERR PFX "Internal CPU not ready, status = %02X\n",
+			       nes_read_indexed(nesdev, NES_IDX_INT_CPU_STATUS));
+			return 0;
+		}
 	}
 
 	/* port reset */
@@ -684,17 +693,6 @@ static unsigned int nes_reset_adapter_ne020(struct nes_device *nesdev, u8 *OneG_
 		}
 	}
 
-
-
-	i = 0;
-	while ((nes_read_indexed(nesdev, NES_IDX_INT_CPU_STATUS) != 0x80) && i++ < 10000)
-		mdelay(1);
-	if (i >= 10000) {
-		printk(KERN_ERR PFX "Internal CPU not ready, status = %02X\n",
-				nes_read_indexed(nesdev, NES_IDX_INT_CPU_STATUS));
-		return 0;
-	}
-
 	return port_count;
 }
 

From bc7b3a36ba02e4053ca38653e6a753082d9add03 Mon Sep 17 00:00:00 2001
From: Shirley Ma <mashirle@us.ibm.com>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 04/14] IPoIB: Handle 4K IB MTU for UD (datagram) mode

This patch enables IPoIB to use 4K UD messages (when the underlying
device and fabrics support a 4K MTU) by using two scatter buffers when
PAGE_SIZE is less than or equal to thhe HCA IB MTU size.  The first
buffer is for IPoIB header + GRH header, and the second buffer is the
IPoIB payload, which is 4K-4.

Signed-off-by: Shirley Ma <xma@us.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/ulp/ipoib/ipoib.h          |  20 ++-
 drivers/infiniband/ulp/ipoib/ipoib_ib.c       | 125 ++++++++++++------
 drivers/infiniband/ulp/ipoib/ipoib_main.c     |  19 ++-
 .../infiniband/ulp/ipoib/ipoib_multicast.c    |   3 +-
 drivers/infiniband/ulp/ipoib/ipoib_verbs.c    |  15 ++-
 drivers/infiniband/ulp/ipoib/ipoib_vlan.c     |   1 +
 6 files changed, 134 insertions(+), 49 deletions(-)

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 73b2b176ad0e..f1f142dc64b1 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -56,11 +56,11 @@
 /* constants */
 
 enum {
-	IPOIB_PACKET_SIZE	  = 2048,
-	IPOIB_BUF_SIZE		  = IPOIB_PACKET_SIZE + IB_GRH_BYTES,
-
 	IPOIB_ENCAP_LEN		  = 4,
 
+	IPOIB_UD_HEAD_SIZE	  = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
+	IPOIB_UD_RX_SG		  = 2, /* max buffer needed for 4K mtu */
+
 	IPOIB_CM_MTU		  = 0x10000 - 0x10, /* padding to align header to 16 */
 	IPOIB_CM_BUF_SIZE	  = IPOIB_CM_MTU  + IPOIB_ENCAP_LEN,
 	IPOIB_CM_HEAD_SIZE	  = IPOIB_CM_BUF_SIZE % PAGE_SIZE,
@@ -139,7 +139,7 @@ struct ipoib_mcast {
 
 struct ipoib_rx_buf {
 	struct sk_buff *skb;
-	u64		mapping;
+	u64		mapping[IPOIB_UD_RX_SG];
 };
 
 struct ipoib_tx_buf {
@@ -294,6 +294,7 @@ struct ipoib_dev_priv {
 
 	unsigned int admin_mtu;
 	unsigned int mcast_mtu;
+	unsigned int max_ib_mtu;
 
 	struct ipoib_rx_buf *rx_ring;
 
@@ -305,6 +306,9 @@ struct ipoib_dev_priv {
 	struct ib_send_wr    tx_wr;
 	unsigned	     tx_outstanding;
 
+	struct ib_recv_wr    rx_wr;
+	struct ib_sge	     rx_sge[IPOIB_UD_RX_SG];
+
 	struct ib_wc ibwc[IPOIB_NUM_WC];
 
 	struct list_head dead_ahs;
@@ -366,6 +370,14 @@ struct ipoib_neigh {
 	struct list_head    list;
 };
 
+#define IPOIB_UD_MTU(ib_mtu)		(ib_mtu - IPOIB_ENCAP_LEN)
+#define IPOIB_UD_BUF_SIZE(ib_mtu)	(ib_mtu + IB_GRH_BYTES)
+
+static inline int ipoib_ud_need_sg(unsigned int ib_mtu)
+{
+	return IPOIB_UD_BUF_SIZE(ib_mtu) > PAGE_SIZE;
+}
+
 /*
  * We stash a pointer to our private neighbour information after our
  * hardware address in neigh->ha.  The ALIGN() expression here makes
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 0205eb7c1bd3..7cf1fa7074ab 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -89,28 +89,59 @@ void ipoib_free_ah(struct kref *kref)
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
+static void ipoib_ud_dma_unmap_rx(struct ipoib_dev_priv *priv,
+				  u64 mapping[IPOIB_UD_RX_SG])
+{
+	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
+		ib_dma_unmap_single(priv->ca, mapping[0], IPOIB_UD_HEAD_SIZE,
+				    DMA_FROM_DEVICE);
+		ib_dma_unmap_page(priv->ca, mapping[1], PAGE_SIZE,
+				  DMA_FROM_DEVICE);
+	} else
+		ib_dma_unmap_single(priv->ca, mapping[0],
+				    IPOIB_UD_BUF_SIZE(priv->max_ib_mtu),
+				    DMA_FROM_DEVICE);
+}
+
+static void ipoib_ud_skb_put_frags(struct ipoib_dev_priv *priv,
+				   struct sk_buff *skb,
+				   unsigned int length)
+{
+	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
+		unsigned int size;
+		/*
+		 * There is only two buffers needed for max_payload = 4K,
+		 * first buf size is IPOIB_UD_HEAD_SIZE
+		 */
+		skb->tail += IPOIB_UD_HEAD_SIZE;
+		skb->len  += length;
+
+		size = length - IPOIB_UD_HEAD_SIZE;
+
+		frag->size     = size;
+		skb->data_len += size;
+		skb->truesize += size;
+	} else
+		skb_put(skb, length);
+
+}
+
 static int ipoib_ib_post_receive(struct net_device *dev, int id)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	struct ib_sge list;
-	struct ib_recv_wr param;
 	struct ib_recv_wr *bad_wr;
 	int ret;
 
-	list.addr     = priv->rx_ring[id].mapping;
-	list.length   = IPOIB_BUF_SIZE;
-	list.lkey     = priv->mr->lkey;
+	priv->rx_wr.wr_id   = id | IPOIB_OP_RECV;
+	priv->rx_sge[0].addr = priv->rx_ring[id].mapping[0];
+	priv->rx_sge[1].addr = priv->rx_ring[id].mapping[1];
 
-	param.next    = NULL;
-	param.wr_id   = id | IPOIB_OP_RECV;
-	param.sg_list = &list;
-	param.num_sge = 1;
 
-	ret = ib_post_recv(priv->qp, &param, &bad_wr);
+	ret = ib_post_recv(priv->qp, &priv->rx_wr, &bad_wr);
 	if (unlikely(ret)) {
 		ipoib_warn(priv, "receive failed for buf %d (%d)\n", id, ret);
-		ib_dma_unmap_single(priv->ca, priv->rx_ring[id].mapping,
-				    IPOIB_BUF_SIZE, DMA_FROM_DEVICE);
+		ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[id].mapping);
 		dev_kfree_skb_any(priv->rx_ring[id].skb);
 		priv->rx_ring[id].skb = NULL;
 	}
@@ -118,15 +149,21 @@ static int ipoib_ib_post_receive(struct net_device *dev, int id)
 	return ret;
 }
 
-static int ipoib_alloc_rx_skb(struct net_device *dev, int id)
+static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct sk_buff *skb;
-	u64 addr;
+	int buf_size;
+	u64 *mapping;
 
-	skb = dev_alloc_skb(IPOIB_BUF_SIZE + 4);
-	if (!skb)
-		return -ENOMEM;
+	if (ipoib_ud_need_sg(priv->max_ib_mtu))
+		buf_size = IPOIB_UD_HEAD_SIZE;
+	else
+		buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
+
+	skb = dev_alloc_skb(buf_size + 4);
+	if (unlikely(!skb))
+		return NULL;
 
 	/*
 	 * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
@@ -135,17 +172,32 @@ static int ipoib_alloc_rx_skb(struct net_device *dev, int id)
 	 */
 	skb_reserve(skb, 4);
 
-	addr = ib_dma_map_single(priv->ca, skb->data, IPOIB_BUF_SIZE,
-				 DMA_FROM_DEVICE);
-	if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
-		dev_kfree_skb_any(skb);
-		return -EIO;
+	mapping = priv->rx_ring[id].mapping;
+	mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
+				       DMA_FROM_DEVICE);
+	if (unlikely(ib_dma_mapping_error(priv->ca, mapping[0])))
+		goto error;
+
+	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
+		struct page *page = alloc_page(GFP_ATOMIC);
+		if (!page)
+			goto partial_error;
+		skb_fill_page_desc(skb, 0, page, 0, PAGE_SIZE);
+		mapping[1] =
+			ib_dma_map_page(priv->ca, skb_shinfo(skb)->frags[0].page,
+					0, PAGE_SIZE, DMA_FROM_DEVICE);
+		if (unlikely(ib_dma_mapping_error(priv->ca, mapping[1])))
+			goto partial_error;
 	}
 
-	priv->rx_ring[id].skb     = skb;
-	priv->rx_ring[id].mapping = addr;
+	priv->rx_ring[id].skb = skb;
+	return skb;
 
-	return 0;
+partial_error:
+	ib_dma_unmap_single(priv->ca, mapping[0], buf_size, DMA_FROM_DEVICE);
+error:
+	dev_kfree_skb_any(skb);
+	return NULL;
 }
 
 static int ipoib_ib_post_receives(struct net_device *dev)
@@ -154,7 +206,7 @@ static int ipoib_ib_post_receives(struct net_device *dev)
 	int i;
 
 	for (i = 0; i < ipoib_recvq_size; ++i) {
-		if (ipoib_alloc_rx_skb(dev, i)) {
+		if (!ipoib_alloc_rx_skb(dev, i)) {
 			ipoib_warn(priv, "failed to allocate receive buffer %d\n", i);
 			return -ENOMEM;
 		}
@@ -172,7 +224,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	unsigned int wr_id = wc->wr_id & ~IPOIB_OP_RECV;
 	struct sk_buff *skb;
-	u64 addr;
+	u64 mapping[IPOIB_UD_RX_SG];
 
 	ipoib_dbg_data(priv, "recv completion: id %d, status: %d\n",
 		       wr_id, wc->status);
@@ -184,15 +236,13 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	}
 
 	skb  = priv->rx_ring[wr_id].skb;
-	addr = priv->rx_ring[wr_id].mapping;
 
 	if (unlikely(wc->status != IB_WC_SUCCESS)) {
 		if (wc->status != IB_WC_WR_FLUSH_ERR)
 			ipoib_warn(priv, "failed recv event "
 				   "(status=%d, wrid=%d vend_err %x)\n",
 				   wc->status, wr_id, wc->vendor_err);
-		ib_dma_unmap_single(priv->ca, addr,
-				    IPOIB_BUF_SIZE, DMA_FROM_DEVICE);
+		ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[wr_id].mapping);
 		dev_kfree_skb_any(skb);
 		priv->rx_ring[wr_id].skb = NULL;
 		return;
@@ -205,11 +255,14 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	if (wc->slid == priv->local_lid && wc->src_qp == priv->qp->qp_num)
 		goto repost;
 
+	memcpy(mapping, priv->rx_ring[wr_id].mapping,
+	       IPOIB_UD_RX_SG * sizeof *mapping);
+
 	/*
 	 * If we can't allocate a new RX buffer, dump
 	 * this packet and reuse the old buffer.
 	 */
-	if (unlikely(ipoib_alloc_rx_skb(dev, wr_id))) {
+	if (unlikely(!ipoib_alloc_rx_skb(dev, wr_id))) {
 		++dev->stats.rx_dropped;
 		goto repost;
 	}
@@ -217,9 +270,9 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	ipoib_dbg_data(priv, "received %d bytes, SLID 0x%04x\n",
 		       wc->byte_len, wc->slid);
 
-	ib_dma_unmap_single(priv->ca, addr, IPOIB_BUF_SIZE, DMA_FROM_DEVICE);
+	ipoib_ud_dma_unmap_rx(priv, mapping);
+	ipoib_ud_skb_put_frags(priv, skb, wc->byte_len);
 
-	skb_put(skb, wc->byte_len);
 	skb_pull(skb, IB_GRH_BYTES);
 
 	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
@@ -733,10 +786,8 @@ int ipoib_ib_dev_stop(struct net_device *dev, int flush)
 				rx_req = &priv->rx_ring[i];
 				if (!rx_req->skb)
 					continue;
-				ib_dma_unmap_single(priv->ca,
-						    rx_req->mapping,
-						    IPOIB_BUF_SIZE,
-						    DMA_FROM_DEVICE);
+				ipoib_ud_dma_unmap_rx(priv,
+						      priv->rx_ring[i].mapping);
 				dev_kfree_skb_any(rx_req->skb);
 				rx_req->skb = NULL;
 			}
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index bd07f02cf02b..7a4ed9d3d844 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -195,7 +195,7 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
 		return 0;
 	}
 
-	if (new_mtu > IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN)
+	if (new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu))
 		return -EINVAL;
 
 	priv->admin_mtu = new_mtu;
@@ -971,10 +971,6 @@ static void ipoib_setup(struct net_device *dev)
 				    NETIF_F_LLTX		|
 				    NETIF_F_HIGHDMA);
 
-	/* MTU will be reset when mcast join happens */
-	dev->mtu		 = IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN;
-	priv->mcast_mtu		 = priv->admin_mtu = dev->mtu;
-
 	memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN);
 
 	netif_carrier_off(dev);
@@ -1107,6 +1103,7 @@ static struct net_device *ipoib_add_port(const char *format,
 {
 	struct ipoib_dev_priv *priv;
 	struct ib_device_attr *device_attr;
+	struct ib_port_attr attr;
 	int result = -ENOMEM;
 
 	priv = ipoib_intf_alloc(format);
@@ -1115,6 +1112,18 @@ static struct net_device *ipoib_add_port(const char *format,
 
 	SET_NETDEV_DEV(priv->dev, hca->dma_device);
 
+	if (!ib_query_port(hca, port, &attr))
+		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
+	else {
+		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
+		       hca->name, port);
+		goto device_init_failed;
+	}
+
+	/* MTU will be reset when mcast join happens */
+	priv->dev->mtu  = IPOIB_UD_MTU(priv->max_ib_mtu);
+	priv->mcast_mtu  = priv->admin_mtu = priv->dev->mtu;
+
 	result = ib_query_pkey(hca, port, 0, &priv->pkey);
 	if (result) {
 		printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 31a53c5bcb13..d00a2c174aee 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -567,8 +567,7 @@ void ipoib_mcast_join_task(struct work_struct *work)
 		return;
 	}
 
-	priv->mcast_mtu = ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu) -
-		IPOIB_ENCAP_LEN;
+	priv->mcast_mtu = IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu));
 
 	if (!ipoib_cm_admin_enabled(dev))
 		dev->mtu = min(priv->mcast_mtu, priv->admin_mtu);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 8a20e3742c43..07c03f178a49 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -150,7 +150,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 			.max_send_wr  = ipoib_sendq_size,
 			.max_recv_wr  = ipoib_recvq_size,
 			.max_send_sge = 1,
-			.max_recv_sge = 1
+			.max_recv_sge = IPOIB_UD_RX_SG
 		},
 		.sq_sig_type = IB_SIGNAL_ALL_WR,
 		.qp_type     = IB_QPT_UD
@@ -215,6 +215,19 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	priv->tx_wr.sg_list	= priv->tx_sge;
 	priv->tx_wr.send_flags	= IB_SEND_SIGNALED;
 
+	priv->rx_sge[0].lkey = priv->mr->lkey;
+	if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
+		priv->rx_sge[0].length = IPOIB_UD_HEAD_SIZE;
+		priv->rx_sge[1].length = PAGE_SIZE;
+		priv->rx_sge[1].lkey = priv->mr->lkey;
+		priv->rx_wr.num_sge = IPOIB_UD_RX_SG;
+	} else {
+		priv->rx_sge[0].length = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
+		priv->rx_wr.num_sge = 1;
+	}
+	priv->rx_wr.next = NULL;
+	priv->rx_wr.sg_list = priv->rx_sge;
+
 	return 0;
 
 out_free_cq:
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 293f5b892e3f..431fdeaa2dc4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -89,6 +89,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
 		goto err;
 	}
 
+	priv->max_ib_mtu = ppriv->max_ib_mtu;
 	set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags);
 
 	priv->pkey = pkey;

From 863fb09fbf1eb74f56ea02184a62165056aa29cb Mon Sep 17 00:00:00 2001
From: Joachim Fenkes <fenkes@de.ibm.com>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 05/14] IB/ehca: Prevent posting of SQ WQEs if QP not in RTS

...as required by IB Spec, C10-29.

Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/ehca/ehca_classes.h | 1 +
 drivers/infiniband/hw/ehca/ehca_qp.c      | 3 +++
 drivers/infiniband/hw/ehca/ehca_reqs.c    | 5 +++++
 3 files changed, 9 insertions(+)

diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h b/drivers/infiniband/hw/ehca/ehca_classes.h
index 0d13fe0a260b..3d6d9461c31d 100644
--- a/drivers/infiniband/hw/ehca/ehca_classes.h
+++ b/drivers/infiniband/hw/ehca/ehca_classes.h
@@ -160,6 +160,7 @@ struct ehca_qp {
 	};
 	u32 qp_type;
 	enum ehca_ext_qp_type ext_type;
+	enum ib_qp_state state;
 	struct ipz_queue ipz_squeue;
 	struct ipz_queue ipz_rqueue;
 	struct h_galpas galpas;
diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/infiniband/hw/ehca/ehca_qp.c
index 3eb14a52cbf2..5a653d75fd2e 100644
--- a/drivers/infiniband/hw/ehca/ehca_qp.c
+++ b/drivers/infiniband/hw/ehca/ehca_qp.c
@@ -550,6 +550,7 @@ static struct ehca_qp *internal_create_qp(
 	spin_lock_init(&my_qp->spinlock_r);
 	my_qp->qp_type = qp_type;
 	my_qp->ext_type = parms.ext_type;
+	my_qp->state = IB_QPS_RESET;
 
 	if (init_attr->recv_cq)
 		my_qp->recv_cq =
@@ -1508,6 +1509,8 @@ static int internal_modify_qp(struct ib_qp *ibqp,
 	if (attr_mask & IB_QP_QKEY)
 		my_qp->qkey = attr->qkey;
 
+	my_qp->state = qp_new_state;
+
 modify_qp_exit2:
 	if (squeue_locked) { /* this means: sqe -> rts */
 		spin_unlock_irqrestore(&my_qp->spinlock_s, flags);
diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c b/drivers/infiniband/hw/ehca/ehca_reqs.c
index a20bbf466188..0b2359e2757a 100644
--- a/drivers/infiniband/hw/ehca/ehca_reqs.c
+++ b/drivers/infiniband/hw/ehca/ehca_reqs.c
@@ -421,6 +421,11 @@ int ehca_post_send(struct ib_qp *qp,
 	int ret = 0;
 	unsigned long flags;
 
+	if (unlikely(my_qp->state != IB_QPS_RTS)) {
+		ehca_err(qp->device, "QP not in RTS state  qpn=%x", qp->qp_num);
+		return -EINVAL;
+	}
+
 	/* LOCK the QUEUE */
 	spin_lock_irqsave(&my_qp->spinlock_s, flags);
 

From 4da27d6d5b92c8fe4b3a3e5bcf42606d9e4a6fc8 Mon Sep 17 00:00:00 2001
From: Joachim Fenkes <fenkes@de.ibm.com>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 06/14] IB/ehca: Move high-volume debug output to higher debug
 levels

Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/ehca/ehca_irq.c    |  2 +-
 drivers/infiniband/hw/ehca/ehca_main.c   | 14 +++++---
 drivers/infiniband/hw/ehca/ehca_mrmw.c   | 16 +++++----
 drivers/infiniband/hw/ehca/ehca_qp.c     | 12 +++----
 drivers/infiniband/hw/ehca/ehca_reqs.c   | 46 ++++++++++++------------
 drivers/infiniband/hw/ehca/ehca_uverbs.c |  6 ++--
 drivers/infiniband/hw/ehca/hcp_if.c      | 23 ++++++------
 7 files changed, 63 insertions(+), 56 deletions(-)

diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c
index b5ca94c6b8d9..ca5eb0cb628c 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -633,7 +633,7 @@ static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
 	unsigned long flags;
 
 	WARN_ON_ONCE(!in_interrupt());
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 3)
 		ehca_dmp(&cpu_online_map, sizeof(cpumask_t), "");
 
 	spin_lock_irqsave(&pool->last_cpu_lock, flags);
diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c
index 65b3362cdb9b..4379beff987f 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -85,8 +85,8 @@ module_param_named(lock_hcalls,   ehca_lock_hcalls,   bool, S_IRUGO);
 MODULE_PARM_DESC(open_aqp1,
 		 "AQP1 on startup (0: no (default), 1: yes)");
 MODULE_PARM_DESC(debug_level,
-		 "debug level"
-		 " (0: no debug traces (default), 1: with debug traces)");
+		 "Amount of debug output (0: none (default), 1: traces, "
+		 "2: some dumps, 3: lots)");
 MODULE_PARM_DESC(hw_level,
 		 "hardware level"
 		 " (0: autosensing (default), 1: v. 0.20, 2: v. 0.21)");
@@ -275,6 +275,7 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
 	u64 h_ret;
 	struct hipz_query_hca *rblock;
 	struct hipz_query_port *port;
+	const char *loc_code;
 
 	static const u32 pgsize_map[] = {
 		HCA_CAP_MR_PGSIZE_4K,  0x1000,
@@ -283,6 +284,12 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
 		HCA_CAP_MR_PGSIZE_16M, 0x1000000,
 	};
 
+	ehca_gen_dbg("Probing adapter %s...",
+		     shca->ofdev->node->full_name);
+	loc_code = of_get_property(shca->ofdev->node, "ibm,loc-code", NULL);
+	if (loc_code)
+		ehca_gen_dbg(" ... location lode=%s", loc_code);
+
 	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_gen_err("Cannot allocate rblock memory.");
@@ -567,8 +574,7 @@ static int ehca_destroy_aqp1(struct ehca_sport *sport)
 
 static ssize_t ehca_show_debug_level(struct device_driver *ddp, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n",
-			ehca_debug_level);
+	return snprintf(buf, PAGE_SIZE, "%d\n", ehca_debug_level);
 }
 
 static ssize_t ehca_store_debug_level(struct device_driver *ddp,
diff --git a/drivers/infiniband/hw/ehca/ehca_mrmw.c b/drivers/infiniband/hw/ehca/ehca_mrmw.c
index f26997fc00f8..46ae4eb2c4e1 100644
--- a/drivers/infiniband/hw/ehca/ehca_mrmw.c
+++ b/drivers/infiniband/hw/ehca/ehca_mrmw.c
@@ -1794,8 +1794,9 @@ static int ehca_check_kpages_per_ate(struct scatterlist *page_list,
 	int t;
 	for (t = start_idx; t <= end_idx; t++) {
 		u64 pgaddr = page_to_pfn(sg_page(&page_list[t])) << PAGE_SHIFT;
-		ehca_gen_dbg("chunk_page=%lx value=%016lx", pgaddr,
-			     *(u64 *)abs_to_virt(phys_to_abs(pgaddr)));
+		if (ehca_debug_level >= 3)
+			ehca_gen_dbg("chunk_page=%lx value=%016lx", pgaddr,
+				     *(u64 *)abs_to_virt(phys_to_abs(pgaddr)));
 		if (pgaddr - PAGE_SIZE != *prev_pgaddr) {
 			ehca_gen_err("uncontiguous page found pgaddr=%lx "
 				     "prev_pgaddr=%lx page_list_i=%x",
@@ -1862,10 +1863,13 @@ static int ehca_set_pagebuf_user2(struct ehca_mr_pginfo *pginfo,
 						pgaddr &
 						~(pginfo->hwpage_size - 1));
 				}
-				ehca_gen_dbg("kpage=%lx chunk_page=%lx "
-					     "value=%016lx", *kpage, pgaddr,
-					     *(u64 *)abs_to_virt(
-						     phys_to_abs(pgaddr)));
+				if (ehca_debug_level >= 3) {
+					u64 val = *(u64 *)abs_to_virt(
+						phys_to_abs(pgaddr));
+					ehca_gen_dbg("kpage=%lx chunk_page=%lx "
+						     "value=%016lx",
+						     *kpage, pgaddr, val);
+				}
 				prev_pgaddr = pgaddr;
 				i++;
 				pginfo->kpage_cnt++;
diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/infiniband/hw/ehca/ehca_qp.c
index 5a653d75fd2e..57bef1152cc2 100644
--- a/drivers/infiniband/hw/ehca/ehca_qp.c
+++ b/drivers/infiniband/hw/ehca/ehca_qp.c
@@ -966,7 +966,7 @@ static int prepare_sqe_rts(struct ehca_qp *my_qp, struct ehca_shca *shca,
 		 qp_num, bad_send_wqe_p);
 	/* convert wqe pointer to vadr */
 	bad_send_wqe_v = abs_to_virt((u64)bad_send_wqe_p);
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(bad_send_wqe_v, 32, "qp_num=%x bad_wqe", qp_num);
 	squeue = &my_qp->ipz_squeue;
 	if (ipz_queue_abs_to_offset(squeue, (u64)bad_send_wqe_p, &q_ofs)) {
@@ -979,7 +979,7 @@ static int prepare_sqe_rts(struct ehca_qp *my_qp, struct ehca_shca *shca,
 	wqe = (struct ehca_wqe *)ipz_qeit_calc(squeue, q_ofs);
 	*bad_wqe_cnt = 0;
 	while (wqe->optype != 0xff && wqe->wqef != 0xff) {
-		if (ehca_debug_level)
+		if (ehca_debug_level >= 2)
 			ehca_dmp(wqe, 32, "qp_num=%x wqe", qp_num);
 		wqe->nr_of_data_seg = 0; /* suppress data access */
 		wqe->wqef = WQEF_PURGE; /* WQE to be purged */
@@ -1451,7 +1451,7 @@ static int internal_modify_qp(struct ib_qp *ibqp,
 		/* no support for max_send/recv_sge yet */
 	}
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(mqpcb, 4*70, "qp_num=%x", ibqp->qp_num);
 
 	h_ret = hipz_h_modify_qp(shca->ipz_hca_handle,
@@ -1766,7 +1766,7 @@ int ehca_query_qp(struct ib_qp *qp,
 	if (qp_init_attr)
 		*qp_init_attr = my_qp->init_attr;
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(qpcb, 4*70, "qp_num=%x", qp->qp_num);
 
 query_qp_exit1:
@@ -1814,7 +1814,7 @@ int ehca_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		goto modify_srq_exit0;
 	}
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(mqpcb, 4*70, "qp_num=%x", my_qp->real_qp_num);
 
 	h_ret = hipz_h_modify_qp(shca->ipz_hca_handle, my_qp->ipz_qp_handle,
@@ -1867,7 +1867,7 @@ int ehca_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr)
 	srq_attr->srq_limit = EHCA_BMASK_GET(
 		MQPCB_CURR_SRQ_LIMIT, qpcb->curr_srq_limit);
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(qpcb, 4*70, "qp_num=%x", my_qp->real_qp_num);
 
 query_srq_exit1:
diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c b/drivers/infiniband/hw/ehca/ehca_reqs.c
index 0b2359e2757a..bbe0436f4f75 100644
--- a/drivers/infiniband/hw/ehca/ehca_reqs.c
+++ b/drivers/infiniband/hw/ehca/ehca_reqs.c
@@ -81,7 +81,7 @@ static inline int ehca_write_rwqe(struct ipz_queue *ipz_rqueue,
 			recv_wr->sg_list[cnt_ds].length;
 	}
 
-	if (ehca_debug_level) {
+	if (ehca_debug_level >= 3) {
 		ehca_gen_dbg("RECEIVE WQE written into ipz_rqueue=%p",
 			     ipz_rqueue);
 		ehca_dmp(wqe_p, 16*(6 + wqe_p->nr_of_data_seg), "recv wqe");
@@ -281,7 +281,7 @@ static inline int ehca_write_swqe(struct ehca_qp *qp,
 		return -EINVAL;
 	}
 
-	if (ehca_debug_level) {
+	if (ehca_debug_level >= 3) {
 		ehca_gen_dbg("SEND WQE written into queue qp=%p ", qp);
 		ehca_dmp( wqe_p, 16*(6 + wqe_p->nr_of_data_seg), "send wqe");
 	}
@@ -459,13 +459,14 @@ int ehca_post_send(struct ib_qp *qp,
 			goto post_send_exit0;
 		}
 		wqe_cnt++;
-		ehca_dbg(qp->device, "ehca_qp=%p qp_num=%x wqe_cnt=%d",
-			 my_qp, qp->qp_num, wqe_cnt);
 	} /* eof for cur_send_wr */
 
 post_send_exit0:
 	iosync(); /* serialize GAL register access */
 	hipz_update_sqa(my_qp, wqe_cnt);
+	if (unlikely(ret || ehca_debug_level >= 2))
+		ehca_dbg(qp->device, "ehca_qp=%p qp_num=%x wqe_cnt=%d ret=%i",
+			 my_qp, qp->qp_num, wqe_cnt, ret);
 	my_qp->message_count += wqe_cnt;
 	spin_unlock_irqrestore(&my_qp->spinlock_s, flags);
 	return ret;
@@ -525,13 +526,14 @@ static int internal_post_recv(struct ehca_qp *my_qp,
 			goto post_recv_exit0;
 		}
 		wqe_cnt++;
-		ehca_dbg(dev, "ehca_qp=%p qp_num=%x wqe_cnt=%d",
-			 my_qp, my_qp->real_qp_num, wqe_cnt);
 	} /* eof for cur_recv_wr */
 
 post_recv_exit0:
 	iosync(); /* serialize GAL register access */
 	hipz_update_rqa(my_qp, wqe_cnt);
+	if (unlikely(ret || ehca_debug_level >= 2))
+	    ehca_dbg(dev, "ehca_qp=%p qp_num=%x wqe_cnt=%d ret=%i",
+		     my_qp, my_qp->real_qp_num, wqe_cnt, ret);
 	spin_unlock_irqrestore(&my_qp->spinlock_r, flags);
 	return ret;
 }
@@ -575,16 +577,17 @@ static inline int ehca_poll_cq_one(struct ib_cq *cq, struct ib_wc *wc)
 	struct ehca_cq *my_cq = container_of(cq, struct ehca_cq, ib_cq);
 	struct ehca_cqe *cqe;
 	struct ehca_qp *my_qp;
-	int cqe_count = 0;
+	int cqe_count = 0, is_error;
 
 poll_cq_one_read_cqe:
 	cqe = (struct ehca_cqe *)
 		ipz_qeit_get_inc_valid(&my_cq->ipz_queue);
 	if (!cqe) {
 		ret = -EAGAIN;
-		ehca_dbg(cq->device, "Completion queue is empty ehca_cq=%p "
-			 "cq_num=%x ret=%i", my_cq, my_cq->cq_number, ret);
-		goto  poll_cq_one_exit0;
+		if (ehca_debug_level >= 3)
+			ehca_dbg(cq->device, "Completion queue is empty  "
+				 "my_cq=%p cq_num=%x", my_cq, my_cq->cq_number);
+		goto poll_cq_one_exit0;
 	}
 
 	/* prevents loads being reordered across this point */
@@ -614,7 +617,7 @@ poll_cq_one_read_cqe:
 			ehca_dbg(cq->device,
 				 "Got CQE with purged bit qp_num=%x src_qp=%x",
 				 cqe->local_qp_number, cqe->remote_qp_number);
-			if (ehca_debug_level)
+			if (ehca_debug_level >= 2)
 				ehca_dmp(cqe, 64, "qp_num=%x src_qp=%x",
 					 cqe->local_qp_number,
 					 cqe->remote_qp_number);
@@ -627,11 +630,13 @@ poll_cq_one_read_cqe:
 		}
 	}
 
-	/* tracing cqe */
-	if (unlikely(ehca_debug_level)) {
+	is_error = cqe->status & WC_STATUS_ERROR_BIT;
+
+	/* trace error CQEs if debug_level >= 1, trace all CQEs if >= 3 */
+	if (unlikely(ehca_debug_level >= 3 || (ehca_debug_level && is_error))) {
 		ehca_dbg(cq->device,
-			 "Received COMPLETION ehca_cq=%p cq_num=%x -----",
-			 my_cq, my_cq->cq_number);
+			 "Received %sCOMPLETION ehca_cq=%p cq_num=%x -----",
+			 is_error ? "ERROR " : "", my_cq, my_cq->cq_number);
 		ehca_dmp(cqe, 64, "ehca_cq=%p cq_num=%x",
 			 my_cq, my_cq->cq_number);
 		ehca_dbg(cq->device,
@@ -654,8 +659,9 @@ poll_cq_one_read_cqe:
 		/* update also queue adder to throw away this entry!!! */
 		goto poll_cq_one_exit0;
 	}
+
 	/* eval ib_wc_status */
-	if (unlikely(cqe->status & WC_STATUS_ERROR_BIT)) {
+	if (unlikely(is_error)) {
 		/* complete with errors */
 		map_ib_wc_status(cqe->status, &wc->status);
 		wc->vendor_err = wc->status;
@@ -676,14 +682,6 @@ poll_cq_one_read_cqe:
 	wc->imm_data = cpu_to_be32(cqe->immediate_data);
 	wc->sl = cqe->service_level;
 
-	if (unlikely(wc->status != IB_WC_SUCCESS))
-		ehca_dbg(cq->device,
-			 "ehca_cq=%p cq_num=%x WARNING unsuccessful cqe "
-			 "OPType=%x status=%x qp_num=%x src_qp=%x wr_id=%lx "
-			 "cqe=%p", my_cq, my_cq->cq_number, cqe->optype,
-			 cqe->status, cqe->local_qp_number,
-			 cqe->remote_qp_number, cqe->work_request_id, cqe);
-
 poll_cq_one_exit0:
 	if (cqe_count > 0)
 		hipz_update_feca(my_cq, cqe_count);
diff --git a/drivers/infiniband/hw/ehca/ehca_uverbs.c b/drivers/infiniband/hw/ehca/ehca_uverbs.c
index 1b07f2beafaf..e43ed8f8a0c8 100644
--- a/drivers/infiniband/hw/ehca/ehca_uverbs.c
+++ b/drivers/infiniband/hw/ehca/ehca_uverbs.c
@@ -211,8 +211,7 @@ static int ehca_mmap_qp(struct vm_area_struct *vma, struct ehca_qp *qp,
 		break;
 
 	case 1: /* qp rqueue_addr */
-		ehca_dbg(qp->ib_qp.device, "qp_num=%x rqueue",
-			 qp->ib_qp.qp_num);
+		ehca_dbg(qp->ib_qp.device, "qp_num=%x rq", qp->ib_qp.qp_num);
 		ret = ehca_mmap_queue(vma, &qp->ipz_rqueue,
 				      &qp->mm_count_rqueue);
 		if (unlikely(ret)) {
@@ -224,8 +223,7 @@ static int ehca_mmap_qp(struct vm_area_struct *vma, struct ehca_qp *qp,
 		break;
 
 	case 2: /* qp squeue_addr */
-		ehca_dbg(qp->ib_qp.device, "qp_num=%x squeue",
-			 qp->ib_qp.qp_num);
+		ehca_dbg(qp->ib_qp.device, "qp_num=%x sq", qp->ib_qp.qp_num);
 		ret = ehca_mmap_queue(vma, &qp->ipz_squeue,
 				      &qp->mm_count_squeue);
 		if (unlikely(ret)) {
diff --git a/drivers/infiniband/hw/ehca/hcp_if.c b/drivers/infiniband/hw/ehca/hcp_if.c
index 7029aa653751..5245e13c3a30 100644
--- a/drivers/infiniband/hw/ehca/hcp_if.c
+++ b/drivers/infiniband/hw/ehca/hcp_if.c
@@ -123,8 +123,9 @@ static long ehca_plpar_hcall_norets(unsigned long opcode,
 	int i, sleep_msecs;
 	unsigned long flags = 0;
 
-	ehca_gen_dbg("opcode=%lx " HCALL7_REGS_FORMAT,
-		     opcode, arg1, arg2, arg3, arg4, arg5, arg6, arg7);
+	if (unlikely(ehca_debug_level >= 2))
+		ehca_gen_dbg("opcode=%lx " HCALL7_REGS_FORMAT,
+			     opcode, arg1, arg2, arg3, arg4, arg5, arg6, arg7);
 
 	for (i = 0; i < 5; i++) {
 		/* serialize hCalls to work around firmware issue */
@@ -148,7 +149,8 @@ static long ehca_plpar_hcall_norets(unsigned long opcode,
 				     opcode, ret, arg1, arg2, arg3,
 				     arg4, arg5, arg6, arg7);
 		else
-			ehca_gen_dbg("opcode=%lx ret=%li", opcode, ret);
+			if (unlikely(ehca_debug_level >= 2))
+				ehca_gen_dbg("opcode=%lx ret=%li", opcode, ret);
 
 		return ret;
 	}
@@ -172,8 +174,10 @@ static long ehca_plpar_hcall9(unsigned long opcode,
 	int i, sleep_msecs;
 	unsigned long flags = 0;
 
-	ehca_gen_dbg("INPUT -- opcode=%lx " HCALL9_REGS_FORMAT, opcode,
-		     arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8, arg9);
+	if (unlikely(ehca_debug_level >= 2))
+		ehca_gen_dbg("INPUT -- opcode=%lx " HCALL9_REGS_FORMAT, opcode,
+			     arg1, arg2, arg3, arg4, arg5,
+			     arg6, arg7, arg8, arg9);
 
 	for (i = 0; i < 5; i++) {
 		/* serialize hCalls to work around firmware issue */
@@ -201,7 +205,7 @@ static long ehca_plpar_hcall9(unsigned long opcode,
 				     ret, outs[0], outs[1], outs[2], outs[3],
 				     outs[4], outs[5], outs[6], outs[7],
 				     outs[8]);
-		} else
+		} else if (unlikely(ehca_debug_level >= 2))
 			ehca_gen_dbg("OUTPUT -- ret=%li " HCALL9_REGS_FORMAT,
 				     ret, outs[0], outs[1], outs[2], outs[3],
 				     outs[4], outs[5], outs[6], outs[7],
@@ -381,7 +385,7 @@ u64 hipz_h_query_port(const struct ipz_adapter_handle adapter_handle,
 				      r_cb,	             /* r6 */
 				      0, 0, 0, 0);
 
-	if (ehca_debug_level)
+	if (ehca_debug_level >= 2)
 		ehca_dmp(query_port_response_block, 64, "response_block");
 
 	return ret;
@@ -731,9 +735,6 @@ u64 hipz_h_alloc_resource_mr(const struct ipz_adapter_handle adapter_handle,
 	u64 ret;
 	u64 outs[PLPAR_HCALL9_BUFSIZE];
 
-	ehca_gen_dbg("kernel PAGE_SIZE=%x access_ctrl=%016x "
-		     "vaddr=%lx length=%lx",
-		     (u32)PAGE_SIZE, access_ctrl, vaddr, length);
 	ret = ehca_plpar_hcall9(H_ALLOC_RESOURCE, outs,
 				adapter_handle.handle,            /* r4 */
 				5,                                /* r5 */
@@ -758,7 +759,7 @@ u64 hipz_h_register_rpage_mr(const struct ipz_adapter_handle adapter_handle,
 {
 	u64 ret;
 
-	if (unlikely(ehca_debug_level >= 2)) {
+	if (unlikely(ehca_debug_level >= 3)) {
 		if (count > 1) {
 			u64 *kpage;
 			int i;

From a7607c9b1112b498c3044c9e5bc68fdb4985f93e Mon Sep 17 00:00:00 2001
From: Joachim Fenkes <fenkes@de.ibm.com>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 07/14] IB/ehca: Remove mr_largepage parameter

Always enable large page support; didn't seem to cause problems for anyone.

Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/ehca/ehca_main.c | 22 +++-------------------
 1 file changed, 3 insertions(+), 19 deletions(-)

diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c
index 4379beff987f..ab02ac836f94 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -60,7 +60,6 @@ MODULE_VERSION(HCAD_VERSION);
 static int ehca_open_aqp1     = 0;
 static int ehca_hw_level      = 0;
 static int ehca_poll_all_eqs  = 1;
-static int ehca_mr_largepage  = 1;
 
 int ehca_debug_level   = 0;
 int ehca_nr_ports      = 2;
@@ -79,7 +78,6 @@ module_param_named(port_act_time, ehca_port_act_time, int, S_IRUGO);
 module_param_named(poll_all_eqs,  ehca_poll_all_eqs,  int, S_IRUGO);
 module_param_named(static_rate,   ehca_static_rate,   int, S_IRUGO);
 module_param_named(scaling_code,  ehca_scaling_code,  int, S_IRUGO);
-module_param_named(mr_largepage,  ehca_mr_largepage,  int, S_IRUGO);
 module_param_named(lock_hcalls,   ehca_lock_hcalls,   bool, S_IRUGO);
 
 MODULE_PARM_DESC(open_aqp1,
@@ -104,9 +102,6 @@ MODULE_PARM_DESC(static_rate,
 		 "set permanent static rate (default: disabled)");
 MODULE_PARM_DESC(scaling_code,
 		 "set scaling code (0: disabled/default, 1: enabled)");
-MODULE_PARM_DESC(mr_largepage,
-		 "use large page for MR (0: use PAGE_SIZE (default), "
-		 "1: use large page depending on MR size");
 MODULE_PARM_DESC(lock_hcalls,
 		 "serialize all hCalls made by the driver "
 		 "(default: autodetect)");
@@ -357,11 +352,9 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
 
 	/* translate supported MR page sizes; always support 4K */
 	shca->hca_cap_mr_pgsize = EHCA_PAGESIZE;
-	if (ehca_mr_largepage) { /* support extra sizes only if enabled */
-		for (i = 0; i < ARRAY_SIZE(pgsize_map); i += 2)
-			if (rblock->memory_page_size_supported & pgsize_map[i])
-				shca->hca_cap_mr_pgsize |= pgsize_map[i + 1];
-	}
+	for (i = 0; i < ARRAY_SIZE(pgsize_map); i += 2)
+		if (rblock->memory_page_size_supported & pgsize_map[i])
+			shca->hca_cap_mr_pgsize |= pgsize_map[i + 1];
 
 	/* query max MTU from first port -- it's the same for all ports */
 	port = (struct hipz_query_port *)rblock;
@@ -663,14 +656,6 @@ static ssize_t ehca_show_adapter_handle(struct device *dev,
 }
 static DEVICE_ATTR(adapter_handle, S_IRUGO, ehca_show_adapter_handle, NULL);
 
-static ssize_t ehca_show_mr_largepage(struct device *dev,
-				      struct device_attribute *attr,
-				      char *buf)
-{
-	return sprintf(buf, "%d\n", ehca_mr_largepage);
-}
-static DEVICE_ATTR(mr_largepage, S_IRUGO, ehca_show_mr_largepage, NULL);
-
 static struct attribute *ehca_dev_attrs[] = {
 	&dev_attr_adapter_handle.attr,
 	&dev_attr_num_ports.attr,
@@ -687,7 +672,6 @@ static struct attribute *ehca_dev_attrs[] = {
 	&dev_attr_cur_mw.attr,
 	&dev_attr_max_pd.attr,
 	&dev_attr_max_ah.attr,
-	&dev_attr_mr_largepage.attr,
 	NULL
 };
 

From 0455e36d81db76f5f4acb68a820da43adfa7ccec Mon Sep 17 00:00:00 2001
From: Joachim Fenkes <fenkes@de.ibm.com>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 08/14] IB/ehca: Make some module parameters bool, update
 descriptions

Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/ehca/ehca_main.c | 37 +++++++++++++-------------
 1 file changed, 18 insertions(+), 19 deletions(-)

diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c
index ab02ac836f94..45fe35a6e9f9 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -69,41 +69,40 @@ int ehca_static_rate   = -1;
 int ehca_scaling_code  = 0;
 int ehca_lock_hcalls   = -1;
 
-module_param_named(open_aqp1,     ehca_open_aqp1,     int, S_IRUGO);
-module_param_named(debug_level,   ehca_debug_level,   int, S_IRUGO);
-module_param_named(hw_level,      ehca_hw_level,      int, S_IRUGO);
-module_param_named(nr_ports,      ehca_nr_ports,      int, S_IRUGO);
-module_param_named(use_hp_mr,     ehca_use_hp_mr,     int, S_IRUGO);
-module_param_named(port_act_time, ehca_port_act_time, int, S_IRUGO);
-module_param_named(poll_all_eqs,  ehca_poll_all_eqs,  int, S_IRUGO);
-module_param_named(static_rate,   ehca_static_rate,   int, S_IRUGO);
-module_param_named(scaling_code,  ehca_scaling_code,  int, S_IRUGO);
+module_param_named(open_aqp1,     ehca_open_aqp1,     bool, S_IRUGO);
+module_param_named(debug_level,   ehca_debug_level,   int,  S_IRUGO);
+module_param_named(hw_level,      ehca_hw_level,      int,  S_IRUGO);
+module_param_named(nr_ports,      ehca_nr_ports,      int,  S_IRUGO);
+module_param_named(use_hp_mr,     ehca_use_hp_mr,     bool, S_IRUGO);
+module_param_named(port_act_time, ehca_port_act_time, int,  S_IRUGO);
+module_param_named(poll_all_eqs,  ehca_poll_all_eqs,  bool, S_IRUGO);
+module_param_named(static_rate,   ehca_static_rate,   int,  S_IRUGO);
+module_param_named(scaling_code,  ehca_scaling_code,  bool, S_IRUGO);
 module_param_named(lock_hcalls,   ehca_lock_hcalls,   bool, S_IRUGO);
 
 MODULE_PARM_DESC(open_aqp1,
-		 "AQP1 on startup (0: no (default), 1: yes)");
+		 "Open AQP1 on startup (default: no)");
 MODULE_PARM_DESC(debug_level,
 		 "Amount of debug output (0: none (default), 1: traces, "
 		 "2: some dumps, 3: lots)");
 MODULE_PARM_DESC(hw_level,
-		 "hardware level"
-		 " (0: autosensing (default), 1: v. 0.20, 2: v. 0.21)");
+		 "Hardware level (0: autosensing (default), "
+		 "0x10..0x14: eHCA, 0x20..0x23: eHCA2)");
 MODULE_PARM_DESC(nr_ports,
 		 "number of connected ports (-1: autodetect, 1: port one only, "
 		 "2: two ports (default)");
 MODULE_PARM_DESC(use_hp_mr,
-		 "high performance MRs (0: no (default), 1: yes)");
+		 "Use high performance MRs (default: no)");
 MODULE_PARM_DESC(port_act_time,
-		 "time to wait for port activation (default: 30 sec)");
+		 "Time to wait for port activation (default: 30 sec)");
 MODULE_PARM_DESC(poll_all_eqs,
-		 "polls all event queues periodically"
-		 " (0: no, 1: yes (default))");
+		 "Poll all event queues periodically (default: yes)");
 MODULE_PARM_DESC(static_rate,
-		 "set permanent static rate (default: disabled)");
+		 "Set permanent static rate (default: no static rate)");
 MODULE_PARM_DESC(scaling_code,
-		 "set scaling code (0: disabled/default, 1: enabled)");
+		 "Enable scaling code (default: no)");
 MODULE_PARM_DESC(lock_hcalls,
-		 "serialize all hCalls made by the driver "
+		 "Serialize all hCalls made by the driver "
 		 "(default: autodetect)");
 
 DEFINE_RWLOCK(ehca_qp_idr_lock);

From 14fb05b3497351fbeb514381bcd227d84e115bd9 Mon Sep 17 00:00:00 2001
From: Joachim Fenkes <fenkes@de.ibm.com>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 09/14] IB/ehca: Bump version number to 0026

Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/ehca/ehca_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c
index 45fe35a6e9f9..65048976198c 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -50,7 +50,7 @@
 #include "ehca_tools.h"
 #include "hcp_if.h"
 
-#define HCAD_VERSION "0025"
+#define HCAD_VERSION "0026"
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Christoph Raisch <raisch@de.ibm.com>");

From 6296883ca4cd52dafb45f191d24102e28ded38f2 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 10/14] mlx4_core: Move kernel doorbell management into core

In addition to mlx4_ib, there will be ethernet and FC consumers of
mlx4_core, so move the code for managing kernel doorbells into the
core module to avoid having to duplicate this multiple times.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/mlx4/cq.c       |   6 +-
 drivers/infiniband/hw/mlx4/doorbell.c | 122 +-------------------------
 drivers/infiniband/hw/mlx4/main.c     |   3 -
 drivers/infiniband/hw/mlx4/mlx4_ib.h  |  33 ++-----
 drivers/infiniband/hw/mlx4/qp.c       |   6 +-
 drivers/infiniband/hw/mlx4/srq.c      |   6 +-
 drivers/net/mlx4/alloc.c              | 111 +++++++++++++++++++++++
 drivers/net/mlx4/main.c               |   3 +
 drivers/net/mlx4/mlx4.h               |   3 +
 include/linux/mlx4/device.h           |  29 ++++++
 10 files changed, 162 insertions(+), 160 deletions(-)

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 3557e7edc9b6..5e570bb0bb6f 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -204,7 +204,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 
 		uar = &to_mucontext(context)->uar;
 	} else {
-		err = mlx4_ib_db_alloc(dev, &cq->db, 1);
+		err = mlx4_db_alloc(dev->dev, &cq->db, 1);
 		if (err)
 			goto err_cq;
 
@@ -250,7 +250,7 @@ err_mtt:
 
 err_db:
 	if (!context)
-		mlx4_ib_db_free(dev, &cq->db);
+		mlx4_db_free(dev->dev, &cq->db);
 
 err_cq:
 	kfree(cq);
@@ -435,7 +435,7 @@ int mlx4_ib_destroy_cq(struct ib_cq *cq)
 		ib_umem_release(mcq->umem);
 	} else {
 		mlx4_ib_free_cq_buf(dev, &mcq->buf, cq->cqe + 1);
-		mlx4_ib_db_free(dev, &mcq->db);
+		mlx4_db_free(dev->dev, &mcq->db);
 	}
 
 	kfree(mcq);
diff --git a/drivers/infiniband/hw/mlx4/doorbell.c b/drivers/infiniband/hw/mlx4/doorbell.c
index 1c36087aef14..8e342cc9baec 100644
--- a/drivers/infiniband/hw/mlx4/doorbell.c
+++ b/drivers/infiniband/hw/mlx4/doorbell.c
@@ -34,124 +34,6 @@
 
 #include "mlx4_ib.h"
 
-struct mlx4_ib_db_pgdir {
-	struct list_head	list;
-	DECLARE_BITMAP(order0, MLX4_IB_DB_PER_PAGE);
-	DECLARE_BITMAP(order1, MLX4_IB_DB_PER_PAGE / 2);
-	unsigned long	       *bits[2];
-	__be32		       *db_page;
-	dma_addr_t		db_dma;
-};
-
-static struct mlx4_ib_db_pgdir *mlx4_ib_alloc_db_pgdir(struct mlx4_ib_dev *dev)
-{
-	struct mlx4_ib_db_pgdir *pgdir;
-
-	pgdir = kzalloc(sizeof *pgdir, GFP_KERNEL);
-	if (!pgdir)
-		return NULL;
-
-	bitmap_fill(pgdir->order1, MLX4_IB_DB_PER_PAGE / 2);
-	pgdir->bits[0] = pgdir->order0;
-	pgdir->bits[1] = pgdir->order1;
-	pgdir->db_page = dma_alloc_coherent(dev->ib_dev.dma_device,
-					    PAGE_SIZE, &pgdir->db_dma,
-					    GFP_KERNEL);
-	if (!pgdir->db_page) {
-		kfree(pgdir);
-		return NULL;
-	}
-
-	return pgdir;
-}
-
-static int mlx4_ib_alloc_db_from_pgdir(struct mlx4_ib_db_pgdir *pgdir,
-				       struct mlx4_ib_db *db, int order)
-{
-	int o;
-	int i;
-
-	for (o = order; o <= 1; ++o) {
-		i = find_first_bit(pgdir->bits[o], MLX4_IB_DB_PER_PAGE >> o);
-		if (i < MLX4_IB_DB_PER_PAGE >> o)
-			goto found;
-	}
-
-	return -ENOMEM;
-
-found:
-	clear_bit(i, pgdir->bits[o]);
-
-	i <<= o;
-
-	if (o > order)
-		set_bit(i ^ 1, pgdir->bits[order]);
-
-	db->u.pgdir = pgdir;
-	db->index   = i;
-	db->db      = pgdir->db_page + db->index;
-	db->dma     = pgdir->db_dma  + db->index * 4;
-	db->order   = order;
-
-	return 0;
-}
-
-int mlx4_ib_db_alloc(struct mlx4_ib_dev *dev, struct mlx4_ib_db *db, int order)
-{
-	struct mlx4_ib_db_pgdir *pgdir;
-	int ret = 0;
-
-	mutex_lock(&dev->pgdir_mutex);
-
-	list_for_each_entry(pgdir, &dev->pgdir_list, list)
-		if (!mlx4_ib_alloc_db_from_pgdir(pgdir, db, order))
-			goto out;
-
-	pgdir = mlx4_ib_alloc_db_pgdir(dev);
-	if (!pgdir) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	list_add(&pgdir->list, &dev->pgdir_list);
-
-	/* This should never fail -- we just allocated an empty page: */
-	WARN_ON(mlx4_ib_alloc_db_from_pgdir(pgdir, db, order));
-
-out:
-	mutex_unlock(&dev->pgdir_mutex);
-
-	return ret;
-}
-
-void mlx4_ib_db_free(struct mlx4_ib_dev *dev, struct mlx4_ib_db *db)
-{
-	int o;
-	int i;
-
-	mutex_lock(&dev->pgdir_mutex);
-
-	o = db->order;
-	i = db->index;
-
-	if (db->order == 0 && test_bit(i ^ 1, db->u.pgdir->order0)) {
-		clear_bit(i ^ 1, db->u.pgdir->order0);
-		++o;
-	}
-
-	i >>= o;
-	set_bit(i, db->u.pgdir->bits[o]);
-
-	if (bitmap_full(db->u.pgdir->order1, MLX4_IB_DB_PER_PAGE / 2)) {
-		dma_free_coherent(dev->ib_dev.dma_device, PAGE_SIZE,
-				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
-		list_del(&db->u.pgdir->list);
-		kfree(db->u.pgdir);
-	}
-
-	mutex_unlock(&dev->pgdir_mutex);
-}
-
 struct mlx4_ib_user_db_page {
 	struct list_head	list;
 	struct ib_umem	       *umem;
@@ -160,7 +42,7 @@ struct mlx4_ib_user_db_page {
 };
 
 int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
-			struct mlx4_ib_db *db)
+			struct mlx4_db *db)
 {
 	struct mlx4_ib_user_db_page *page;
 	struct ib_umem_chunk *chunk;
@@ -202,7 +84,7 @@ out:
 	return err;
 }
 
-void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_ib_db *db)
+void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_db *db)
 {
 	mutex_lock(&context->db_page_mutex);
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 4d9b5ac42202..4d61e32866c6 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -557,9 +557,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		goto err_uar;
 	MLX4_INIT_DOORBELL_LOCK(&ibdev->uar_lock);
 
-	INIT_LIST_HEAD(&ibdev->pgdir_list);
-	mutex_init(&ibdev->pgdir_mutex);
-
 	ibdev->dev = dev;
 
 	strlcpy(ibdev->ib_dev.name, "mlx4_%d", IB_DEVICE_NAME_MAX);
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 9e637323c155..5cf994794d25 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -43,24 +43,6 @@
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
 
-enum {
-	MLX4_IB_DB_PER_PAGE	= PAGE_SIZE / 4
-};
-
-struct mlx4_ib_db_pgdir;
-struct mlx4_ib_user_db_page;
-
-struct mlx4_ib_db {
-	__be32		       *db;
-	union {
-		struct mlx4_ib_db_pgdir	       *pgdir;
-		struct mlx4_ib_user_db_page    *user_page;
-	}			u;
-	dma_addr_t		dma;
-	int			index;
-	int			order;
-};
-
 struct mlx4_ib_ucontext {
 	struct ib_ucontext	ibucontext;
 	struct mlx4_uar		uar;
@@ -88,7 +70,7 @@ struct mlx4_ib_cq {
 	struct mlx4_cq		mcq;
 	struct mlx4_ib_cq_buf	buf;
 	struct mlx4_ib_cq_resize *resize_buf;
-	struct mlx4_ib_db	db;
+	struct mlx4_db		db;
 	spinlock_t		lock;
 	struct mutex		resize_mutex;
 	struct ib_umem	       *umem;
@@ -127,7 +109,7 @@ struct mlx4_ib_qp {
 	struct mlx4_qp		mqp;
 	struct mlx4_buf		buf;
 
-	struct mlx4_ib_db	db;
+	struct mlx4_db		db;
 	struct mlx4_ib_wq	rq;
 
 	u32			doorbell_qpn;
@@ -154,7 +136,7 @@ struct mlx4_ib_srq {
 	struct ib_srq		ibsrq;
 	struct mlx4_srq		msrq;
 	struct mlx4_buf		buf;
-	struct mlx4_ib_db	db;
+	struct mlx4_db		db;
 	u64		       *wrid;
 	spinlock_t		lock;
 	int			head;
@@ -175,9 +157,6 @@ struct mlx4_ib_dev {
 	struct mlx4_dev	       *dev;
 	void __iomem	       *uar_map;
 
-	struct list_head	pgdir_list;
-	struct mutex		pgdir_mutex;
-
 	struct mlx4_uar		priv_uar;
 	u32			priv_pdn;
 	MLX4_DECLARE_DOORBELL_LOCK(uar_lock);
@@ -248,11 +227,9 @@ static inline struct mlx4_ib_ah *to_mah(struct ib_ah *ibah)
 	return container_of(ibah, struct mlx4_ib_ah, ibah);
 }
 
-int mlx4_ib_db_alloc(struct mlx4_ib_dev *dev, struct mlx4_ib_db *db, int order);
-void mlx4_ib_db_free(struct mlx4_ib_dev *dev, struct mlx4_ib_db *db);
 int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
-			struct mlx4_ib_db *db);
-void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_ib_db *db);
+			struct mlx4_db *db);
+void mlx4_ib_db_unmap_user(struct mlx4_ib_ucontext *context, struct mlx4_db *db);
 
 struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc);
 int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index b75efae7e449..80ea8b9e7761 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -514,7 +514,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			goto err;
 
 		if (!init_attr->srq) {
-			err = mlx4_ib_db_alloc(dev, &qp->db, 0);
+			err = mlx4_db_alloc(dev->dev, &qp->db, 0);
 			if (err)
 				goto err;
 
@@ -580,7 +580,7 @@ err_buf:
 
 err_db:
 	if (!pd->uobject && !init_attr->srq)
-		mlx4_ib_db_free(dev, &qp->db);
+		mlx4_db_free(dev->dev, &qp->db);
 
 err:
 	return err;
@@ -666,7 +666,7 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 		kfree(qp->rq.wrid);
 		mlx4_buf_free(dev->dev, qp->buf_size, &qp->buf);
 		if (!qp->ibqp.srq)
-			mlx4_ib_db_free(dev, &qp->db);
+			mlx4_db_free(dev->dev, &qp->db);
 	}
 }
 
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index beaa3b06cf58..204619702f9d 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -129,7 +129,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 		if (err)
 			goto err_mtt;
 	} else {
-		err = mlx4_ib_db_alloc(dev, &srq->db, 0);
+		err = mlx4_db_alloc(dev->dev, &srq->db, 0);
 		if (err)
 			goto err_srq;
 
@@ -200,7 +200,7 @@ err_buf:
 
 err_db:
 	if (!pd->uobject)
-		mlx4_ib_db_free(dev, &srq->db);
+		mlx4_db_free(dev->dev, &srq->db);
 
 err_srq:
 	kfree(srq);
@@ -267,7 +267,7 @@ int mlx4_ib_destroy_srq(struct ib_srq *srq)
 		kfree(msrq->wrid);
 		mlx4_buf_free(dev->dev, msrq->msrq.max << msrq->msrq.wqe_shift,
 			      &msrq->buf);
-		mlx4_ib_db_free(dev, &msrq->db);
+		mlx4_db_free(dev->dev, &msrq->db);
 	}
 
 	kfree(msrq);
diff --git a/drivers/net/mlx4/alloc.c b/drivers/net/mlx4/alloc.c
index 75ef9d0d974d..43c6d04bb880 100644
--- a/drivers/net/mlx4/alloc.c
+++ b/drivers/net/mlx4/alloc.c
@@ -196,3 +196,114 @@ void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf)
 	}
 }
 EXPORT_SYMBOL_GPL(mlx4_buf_free);
+
+static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device)
+{
+	struct mlx4_db_pgdir *pgdir;
+
+	pgdir = kzalloc(sizeof *pgdir, GFP_KERNEL);
+	if (!pgdir)
+		return NULL;
+
+	bitmap_fill(pgdir->order1, MLX4_DB_PER_PAGE / 2);
+	pgdir->bits[0] = pgdir->order0;
+	pgdir->bits[1] = pgdir->order1;
+	pgdir->db_page = dma_alloc_coherent(dma_device, PAGE_SIZE,
+					    &pgdir->db_dma, GFP_KERNEL);
+	if (!pgdir->db_page) {
+		kfree(pgdir);
+		return NULL;
+	}
+
+	return pgdir;
+}
+
+static int mlx4_alloc_db_from_pgdir(struct mlx4_db_pgdir *pgdir,
+				    struct mlx4_db *db, int order)
+{
+	int o;
+	int i;
+
+	for (o = order; o <= 1; ++o) {
+		i = find_first_bit(pgdir->bits[o], MLX4_DB_PER_PAGE >> o);
+		if (i < MLX4_DB_PER_PAGE >> o)
+			goto found;
+	}
+
+	return -ENOMEM;
+
+found:
+	clear_bit(i, pgdir->bits[o]);
+
+	i <<= o;
+
+	if (o > order)
+		set_bit(i ^ 1, pgdir->bits[order]);
+
+	db->u.pgdir = pgdir;
+	db->index   = i;
+	db->db      = pgdir->db_page + db->index;
+	db->dma     = pgdir->db_dma  + db->index * 4;
+	db->order   = order;
+
+	return 0;
+}
+
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_db_pgdir *pgdir;
+	int ret = 0;
+
+	mutex_lock(&priv->pgdir_mutex);
+
+	list_for_each_entry(pgdir, &priv->pgdir_list, list)
+		if (!mlx4_alloc_db_from_pgdir(pgdir, db, order))
+			goto out;
+
+	pgdir = mlx4_alloc_db_pgdir(&(dev->pdev->dev));
+	if (!pgdir) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	list_add(&pgdir->list, &priv->pgdir_list);
+
+	/* This should never fail -- we just allocated an empty page: */
+	WARN_ON(mlx4_alloc_db_from_pgdir(pgdir, db, order));
+
+out:
+	mutex_unlock(&priv->pgdir_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx4_db_alloc);
+
+void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int o;
+	int i;
+
+	mutex_lock(&priv->pgdir_mutex);
+
+	o = db->order;
+	i = db->index;
+
+	if (db->order == 0 && test_bit(i ^ 1, db->u.pgdir->order0)) {
+		clear_bit(i ^ 1, db->u.pgdir->order0);
+		++o;
+	}
+	i >>= o;
+	set_bit(i, db->u.pgdir->bits[o]);
+
+	if (bitmap_full(db->u.pgdir->order1, MLX4_DB_PER_PAGE / 2)) {
+		dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
+		list_del(&db->u.pgdir->list);
+		kfree(db->u.pgdir);
+	}
+
+	mutex_unlock(&priv->pgdir_mutex);
+}
+EXPORT_SYMBOL_GPL(mlx4_db_free);
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 49a4acab5e82..a6aa49fc1d68 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -798,6 +798,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
 
+	INIT_LIST_HEAD(&priv->pgdir_list);
+	mutex_init(&priv->pgdir_mutex);
+
 	/*
 	 * Now reset the HCA before we touch the PCI capabilities or
 	 * attempt a firmware command, since a boot ROM may have left
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 73336810e652..a4023c2dd050 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -257,6 +257,9 @@ struct mlx4_priv {
 	struct list_head	ctx_list;
 	spinlock_t		ctx_lock;
 
+	struct list_head        pgdir_list;
+	struct mutex            pgdir_mutex;
+
 	struct mlx4_fw		fw;
 	struct mlx4_cmd		cmd;
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index ff7df1a2222f..0a47457931ac 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -208,6 +208,32 @@ struct mlx4_mtt {
 	int			page_shift;
 };
 
+enum {
+	MLX4_DB_PER_PAGE = PAGE_SIZE / 4
+};
+
+struct mlx4_db_pgdir {
+	struct list_head	list;
+	DECLARE_BITMAP(order0, MLX4_DB_PER_PAGE);
+	DECLARE_BITMAP(order1, MLX4_DB_PER_PAGE / 2);
+	unsigned long	       *bits[2];
+	__be32		       *db_page;
+	dma_addr_t		db_dma;
+};
+
+struct mlx4_ib_user_db_page;
+
+struct mlx4_db {
+	__be32			*db;
+	union {
+		struct mlx4_db_pgdir		*pgdir;
+		struct mlx4_ib_user_db_page	*user_page;
+	}			u;
+	dma_addr_t		dma;
+	int			index;
+	int			order;
+};
+
 struct mlx4_mr {
 	struct mlx4_mtt		mtt;
 	u64			iova;
@@ -341,6 +367,9 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		       struct mlx4_buf *buf);
 
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order);
+void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
+
 int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq);
 void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);

From f5b3a096b138940f283907debe9bde6c6f40ebf3 Mon Sep 17 00:00:00 2001
From: Vladimir Sokolovsky <vlad@mellanox.co.il>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 11/14] mlx4_core: CQ resizing should pass a 0 opcode modifier
 to MODIFY_CQ

The call to mlx4_MODIFY_CQ() had a typo so that mlx4_cq_resize() was
actually asking the FW to modify a CQ's interrupt moderation rather than
asking it to resize a CQ.

Signed-off-by: Vladimir Sokolovsky <vlad@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/net/mlx4/cq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/mlx4/cq.c b/drivers/net/mlx4/cq.c
index caa5bcf54e35..6fda0af9d0a6 100644
--- a/drivers/net/mlx4/cq.c
+++ b/drivers/net/mlx4/cq.c
@@ -180,7 +180,7 @@ int mlx4_cq_resize(struct mlx4_dev *dev, struct mlx4_cq *cq,
 	cq_context->mtt_base_addr_h = mtt_addr >> 32;
 	cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
 
-	err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 1);
+	err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 0);
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;

From 31d1e340f0e8d53804d737571b2f2bb28a74ecc5 Mon Sep 17 00:00:00 2001
From: Roland Dreier <rolandd@cisco.com>
Date: Wed, 23 Apr 2008 11:55:45 -0700
Subject: [PATCH 12/14] RDMA/nes: Remove volatile qualifier from struct
 nes_hw_cq.cq_vbase

Remove the volatile qualifier from the cq_vbase member of struct
nes_hw_cq, and add an rmb() in the one place where it looks like
access order might make a difference.  As usual, removing a volatile
qualifier in a declaration is actually a bug fix, since a volatile
qualifier is not sufficient to make sure that aggressively
out-of-order CPUs don't reorder things and cause incorrect results.

For example, a CPU might speculatively execute reads of other cqe
fields before the NIC hardware has written those fields and before it
has set the NES_CQE_VALID bit (even though those reads come after the
test of the NES_CQE_VALID bit in program order), but then when the CPU
actually executes the conditional test of the NES_CQE_VALID, the bit
has been set, and the CPU will proceed with the results of the earlier
speculative execution and end up using bogus data.

This also gets rid of the warning:

    drivers/infiniband/hw/nes/nes_verbs.c: In function 'nes_destroy_cq':
    drivers/infiniband/hw/nes/nes_verbs.c:1978: warning: passing argument 3 of 'pci_free_consistent' discards qualifiers from pointer target type

Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/nes/nes_hw.h    | 2 +-
 drivers/infiniband/hw/nes/nes_verbs.c | 8 +++++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/nes/nes_hw.h b/drivers/infiniband/hw/nes/nes_hw.h
index b7e2844f096b..8f36e231bdf5 100644
--- a/drivers/infiniband/hw/nes/nes_hw.h
+++ b/drivers/infiniband/hw/nes/nes_hw.h
@@ -905,7 +905,7 @@ struct nes_hw_qp {
 };
 
 struct nes_hw_cq {
-	struct nes_hw_cqe volatile *cq_vbase;	/* PCI memory for host rings */
+	struct nes_hw_cqe *cq_vbase;	/* PCI memory for host rings */
 	void (*ce_handler)(struct nes_device *nesdev, struct nes_hw_cq *cq);
 	dma_addr_t cq_pbase;	/* PCI memory for host rings */
 	u16 cq_head;
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index f9a5d4390892..ee74f7c7a6da 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -1976,7 +1976,7 @@ static int nes_destroy_cq(struct ib_cq *ib_cq)
 
 	if (nescq->cq_mem_size)
 		pci_free_consistent(nesdev->pcidev, nescq->cq_mem_size,
-				(void *)nescq->hw_cq.cq_vbase, nescq->hw_cq.cq_pbase);
+				    nescq->hw_cq.cq_vbase, nescq->hw_cq.cq_pbase);
 	kfree(nescq);
 
 	return ret;
@@ -3610,6 +3610,12 @@ static int nes_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry)
 	while (cqe_count < num_entries) {
 		if (le32_to_cpu(nescq->hw_cq.cq_vbase[head].cqe_words[NES_CQE_OPCODE_IDX]) &
 				NES_CQE_VALID) {
+			/*
+			 * Make sure we read CQ entry contents *after*
+			 * we've checked the valid bit.
+			 */
+			rmb();
+
 			cqe = nescq->hw_cq.cq_vbase[head];
 			nescq->hw_cq.cq_vbase[head].cqe_words[NES_CQE_OPCODE_IDX] = 0;
 			u32temp = le32_to_cpu(cqe.cqe_words[NES_CQE_COMP_COMP_CTX_LOW_IDX]);

From 38ae6a535470b959df67ded6798fc542bb212e19 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Fri, 25 Apr 2008 14:27:08 -0700
Subject: [PATCH 13/14] mlx4_core: Add HW queues allocation helpers

Wrap doorbell, buffer and MTT allocation in helper functions for
ethernet and FC modules to use.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/net/mlx4/alloc.c    | 46 +++++++++++++++++++++++++++++++++++++
 include/linux/mlx4/device.h | 11 +++++++++
 2 files changed, 57 insertions(+)

diff --git a/drivers/net/mlx4/alloc.c b/drivers/net/mlx4/alloc.c
index 43c6d04bb880..f9d6b4dca180 100644
--- a/drivers/net/mlx4/alloc.c
+++ b/drivers/net/mlx4/alloc.c
@@ -307,3 +307,49 @@ void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db)
 	mutex_unlock(&priv->pgdir_mutex);
 }
 EXPORT_SYMBOL_GPL(mlx4_db_free);
+
+int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
+		       int size, int max_direct)
+{
+	int err;
+
+	err = mlx4_db_alloc(dev, &wqres->db, 1);
+	if (err)
+		return err;
+
+	*wqres->db.db = 0;
+
+	err = mlx4_buf_alloc(dev, size, max_direct, &wqres->buf);
+	if (err)
+		goto err_db;
+
+	err = mlx4_mtt_init(dev, wqres->buf.npages, wqres->buf.page_shift,
+			    &wqres->mtt);
+	if (err)
+		goto err_buf;
+
+	err = mlx4_buf_write_mtt(dev, &wqres->mtt, &wqres->buf);
+	if (err)
+		goto err_mtt;
+
+	return 0;
+
+err_mtt:
+	mlx4_mtt_cleanup(dev, &wqres->mtt);
+err_buf:
+	mlx4_buf_free(dev, size, &wqres->buf);
+err_db:
+	mlx4_db_free(dev, &wqres->db);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_alloc_hwq_res);
+
+void mlx4_free_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
+		       int size)
+{
+	mlx4_mtt_cleanup(dev, &wqres->mtt);
+	mlx4_buf_free(dev, size, &wqres->buf);
+	mlx4_db_free(dev, &wqres->db);
+}
+EXPORT_SYMBOL_GPL(mlx4_free_hwq_res);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 0a47457931ac..9fa1a8002ce2 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -234,6 +234,12 @@ struct mlx4_db {
 	int			order;
 };
 
+struct mlx4_hwq_resources {
+	struct mlx4_db		db;
+	struct mlx4_mtt		mtt;
+	struct mlx4_buf		buf;
+};
+
 struct mlx4_mr {
 	struct mlx4_mtt		mtt;
 	u64			iova;
@@ -370,6 +376,11 @@ int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order);
 void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
 
+int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
+		       int size, int max_direct);
+void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres,
+		       int size);
+
 int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq);
 void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);

From ed4d3c1061d6f367a4ef5e1656c25af3314fe2b7 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Fri, 25 Apr 2008 14:52:32 -0700
Subject: [PATCH 14/14] mlx4_core: Add helper to move QP to ready-to-send

Avoid duplicating code in ethernet and FC modules.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/net/mlx4/qp.c   | 31 +++++++++++++++++++++++++++++++
 include/linux/mlx4/qp.h |  4 ++++
 2 files changed, 35 insertions(+)

diff --git a/drivers/net/mlx4/qp.c b/drivers/net/mlx4/qp.c
index fa24e6597591..ee5484c44a18 100644
--- a/drivers/net/mlx4/qp.c
+++ b/drivers/net/mlx4/qp.c
@@ -299,3 +299,34 @@ int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp,
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_query);
 
+int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+		     struct mlx4_qp_context *context,
+		     struct mlx4_qp *qp, enum mlx4_qp_state *qp_state)
+{
+	int err;
+	int i;
+	enum mlx4_qp_state states[] = {
+		MLX4_QP_STATE_RST,
+		MLX4_QP_STATE_INIT,
+		MLX4_QP_STATE_RTR,
+		MLX4_QP_STATE_RTS
+	};
+
+	for (i = 0; i < ARRAY_SIZE(states) - 1; i++) {
+		context->flags &= cpu_to_be32(~(0xf << 28));
+		context->flags |= cpu_to_be32(states[i + 1] << 28);
+		err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
+				     context, 0, 0, qp);
+		if (err) {
+			mlx4_err(dev, "Failed to bring QP to state: "
+				 "%d with error: %d\n",
+				 states[i + 1], err);
+			return err;
+		}
+
+		*qp_state = states[i + 1];
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_qp_to_ready);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index a5e43febee4f..7f128b266faa 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -296,6 +296,10 @@ int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp,
 		  struct mlx4_qp_context *context);
 
+int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+		     struct mlx4_qp_context *context,
+		     struct mlx4_qp *qp, enum mlx4_qp_state *qp_state);
+
 static inline struct mlx4_qp *__mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn)
 {
 	return radix_tree_lookup(&dev->qp_table_tree, qpn & (dev->caps.num_qps - 1));