summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/ulp
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/ulp')
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib.h20
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_cm.c15
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_ib.c12
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_main.c92
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_multicast.c6
5 files changed, 90 insertions, 55 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 7b8d2d9e2263..da12717a3eb7 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -63,6 +63,8 @@ enum ipoib_flush_level {
enum {
IPOIB_ENCAP_LEN = 4,
+ IPOIB_PSEUDO_LEN = 20,
+ IPOIB_HARD_LEN = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN,
IPOIB_UD_HEAD_SIZE = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
IPOIB_UD_RX_SG = 2, /* max buffer needed for 4K mtu */
@@ -134,15 +136,21 @@ struct ipoib_header {
u16 reserved;
};
-struct ipoib_cb {
- struct qdisc_skb_cb qdisc_cb;
- u8 hwaddr[INFINIBAND_ALEN];
+struct ipoib_pseudo_header {
+ u8 hwaddr[INFINIBAND_ALEN];
};
-static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb)
+static inline void skb_add_pseudo_hdr(struct sk_buff *skb)
{
- BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb));
- return (struct ipoib_cb *)skb->cb;
+ char *data = skb_push(skb, IPOIB_PSEUDO_LEN);
+
+ /*
+ * only the ipoib header is present now, make room for a dummy
+ * pseudo header and set skb field accordingly
+ */
+ memset(data, 0, IPOIB_PSEUDO_LEN);
+ skb_reset_mac_header(skb);
+ skb_pull(skb, IPOIB_HARD_LEN);
}
/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 4ad297d3de89..339a1eecdfe3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -63,6 +63,8 @@ MODULE_PARM_DESC(cm_data_debug_level,
#define IPOIB_CM_RX_DELAY (3 * 256 * HZ)
#define IPOIB_CM_RX_UPDATE_MASK (0x3)
+#define IPOIB_CM_RX_RESERVE (ALIGN(IPOIB_HARD_LEN, 16) - IPOIB_ENCAP_LEN)
+
static struct ib_qp_attr ipoib_cm_err_attr = {
.qp_state = IB_QPS_ERR
};
@@ -146,15 +148,15 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev,
struct sk_buff *skb;
int i;
- skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12);
+ skb = dev_alloc_skb(ALIGN(IPOIB_CM_HEAD_SIZE + IPOIB_PSEUDO_LEN, 16));
if (unlikely(!skb))
return NULL;
/*
- * IPoIB adds a 4 byte header. So we need 12 more bytes to align the
+ * IPoIB adds a IPOIB_ENCAP_LEN byte header, this will align the
* IP header to a multiple of 16.
*/
- skb_reserve(skb, 12);
+ skb_reserve(skb, IPOIB_CM_RX_RESERVE);
mapping[0] = ib_dma_map_single(priv->ca, skb->data, IPOIB_CM_HEAD_SIZE,
DMA_FROM_DEVICE);
@@ -624,9 +626,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
if (wc->byte_len < IPOIB_CM_COPYBREAK) {
int dlen = wc->byte_len;
- small_skb = dev_alloc_skb(dlen + 12);
+ small_skb = dev_alloc_skb(dlen + IPOIB_CM_RX_RESERVE);
if (small_skb) {
- skb_reserve(small_skb, 12);
+ skb_reserve(small_skb, IPOIB_CM_RX_RESERVE);
ib_dma_sync_single_for_cpu(priv->ca, rx_ring[wr_id].mapping[0],
dlen, DMA_FROM_DEVICE);
skb_copy_from_linear_data(skb, small_skb->data, dlen);
@@ -663,8 +665,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
copied:
skb->protocol = ((struct ipoib_header *) skb->data)->proto;
- skb_reset_mac_header(skb);
- skb_pull(skb, IPOIB_ENCAP_LEN);
+ skb_add_pseudo_hdr(skb);
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index be11d5d5b8c1..830fecb6934c 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -128,16 +128,15 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
- skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN);
+ skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN);
if (unlikely(!skb))
return NULL;
/*
- * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
- * header. So we need 4 more bytes to get to 48 and align the
- * IP header to a multiple of 16.
+ * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is
+ * 64 bytes aligned
*/
- skb_reserve(skb, 4);
+ skb_reserve(skb, sizeof(struct ipoib_pseudo_header));
mapping = priv->rx_ring[id].mapping;
mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
@@ -253,8 +252,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
skb_pull(skb, IB_GRH_BYTES);
skb->protocol = ((struct ipoib_header *) skb->data)->proto;
- skb_reset_mac_header(skb);
- skb_pull(skb, IPOIB_ENCAP_LEN);
+ skb_add_pseudo_hdr(skb);
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 5636fc3da6b8..c50794fb92db 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -292,6 +292,25 @@ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev)
return dev;
}
+struct ipoib_walk_data {
+ const struct sockaddr *addr;
+ struct net_device *result;
+};
+
+static int ipoib_upper_walk(struct net_device *upper, void *_data)
+{
+ struct ipoib_walk_data *data = _data;
+ int ret = 0;
+
+ if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) {
+ dev_hold(upper);
+ data->result = upper;
+ ret = 1;
+ }
+
+ return ret;
+}
+
/**
* Find a net_device matching the given address, which is an upper device of
* the given net_device.
@@ -304,27 +323,21 @@ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev)
static struct net_device *ipoib_get_net_dev_match_addr(
const struct sockaddr *addr, struct net_device *dev)
{
- struct net_device *upper,
- *result = NULL;
- struct list_head *iter;
+ struct ipoib_walk_data data = {
+ .addr = addr,
+ };
rcu_read_lock();
if (ipoib_is_dev_match_addr_rcu(addr, dev)) {
dev_hold(dev);
- result = dev;
+ data.result = dev;
goto out;
}
- netdev_for_each_all_upper_dev_rcu(dev, upper, iter) {
- if (ipoib_is_dev_match_addr_rcu(addr, upper)) {
- dev_hold(upper);
- result = upper;
- break;
- }
- }
+ netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &data);
out:
rcu_read_unlock();
- return result;
+ return data.result;
}
/* returns the number of IPoIB netdevs on top a given ipoib device matching a
@@ -925,9 +938,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
ipoib_neigh_free(neigh);
goto err_drop;
}
- if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+ if (skb_queue_len(&neigh->queue) <
+ IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&neigh->queue, skb);
- else {
+ } else {
ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
skb_queue_len(&neigh->queue));
goto err_drop;
@@ -964,7 +980,7 @@ err_drop:
}
static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
- struct ipoib_cb *cb)
+ struct ipoib_pseudo_header *phdr)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_path *path;
@@ -972,16 +988,18 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
spin_lock_irqsave(&priv->lock, flags);
- path = __path_find(dev, cb->hwaddr + 4);
+ path = __path_find(dev, phdr->hwaddr + 4);
if (!path || !path->valid) {
int new_path = 0;
if (!path) {
- path = path_rec_create(dev, cb->hwaddr + 4);
+ path = path_rec_create(dev, phdr->hwaddr + 4);
new_path = 1;
}
if (path) {
if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1009,10 +1027,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
be16_to_cpu(path->pathrec.dlid));
spin_unlock_irqrestore(&priv->lock, flags);
- ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr));
+ ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr));
return;
} else if ((path->query || !path_rec_start(dev, path)) &&
skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1026,13 +1046,15 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_neigh *neigh;
- struct ipoib_cb *cb = ipoib_skb_cb(skb);
+ struct ipoib_pseudo_header *phdr;
struct ipoib_header *header;
unsigned long flags;
+ phdr = (struct ipoib_pseudo_header *) skb->data;
+ skb_pull(skb, sizeof(*phdr));
header = (struct ipoib_header *) skb->data;
- if (unlikely(cb->hwaddr[4] == 0xff)) {
+ if (unlikely(phdr->hwaddr[4] == 0xff)) {
/* multicast, arrange "if" according to probability */
if ((header->proto != htons(ETH_P_IP)) &&
(header->proto != htons(ETH_P_IPV6)) &&
@@ -1045,13 +1067,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
/* Add in the P_Key for multicast*/
- cb->hwaddr[8] = (priv->pkey >> 8) & 0xff;
- cb->hwaddr[9] = priv->pkey & 0xff;
+ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
+ phdr->hwaddr[9] = priv->pkey & 0xff;
- neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ neigh = ipoib_neigh_get(dev, phdr->hwaddr);
if (likely(neigh))
goto send_using_neigh;
- ipoib_mcast_send(dev, cb->hwaddr, skb);
+ ipoib_mcast_send(dev, phdr->hwaddr, skb);
return NETDEV_TX_OK;
}
@@ -1060,16 +1082,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
case htons(ETH_P_IP):
case htons(ETH_P_IPV6):
case htons(ETH_P_TIPC):
- neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ neigh = ipoib_neigh_get(dev, phdr->hwaddr);
if (unlikely(!neigh)) {
- neigh_add_path(skb, cb->hwaddr, dev);
+ neigh_add_path(skb, phdr->hwaddr, dev);
return NETDEV_TX_OK;
}
break;
case htons(ETH_P_ARP):
case htons(ETH_P_RARP):
/* for unicast ARP and RARP should always perform path find */
- unicast_arp_send(skb, dev, cb);
+ unicast_arp_send(skb, dev, phdr);
return NETDEV_TX_OK;
default:
/* ethertype not supported by IPoIB */
@@ -1086,11 +1108,13 @@ send_using_neigh:
goto unref;
}
} else if (neigh->ah) {
- ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr));
+ ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr));
goto unref;
}
if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, sizeof(*phdr));
spin_lock_irqsave(&priv->lock, flags);
__skb_queue_tail(&neigh->queue, skb);
spin_unlock_irqrestore(&priv->lock, flags);
@@ -1122,8 +1146,8 @@ static int ipoib_hard_header(struct sk_buff *skb,
unsigned short type,
const void *daddr, const void *saddr, unsigned len)
{
+ struct ipoib_pseudo_header *phdr;
struct ipoib_header *header;
- struct ipoib_cb *cb = ipoib_skb_cb(skb);
header = (struct ipoib_header *) skb_push(skb, sizeof *header);
@@ -1132,12 +1156,13 @@ static int ipoib_hard_header(struct sk_buff *skb,
/*
* we don't rely on dst_entry structure, always stuff the
- * destination address into skb->cb so we can figure out where
+ * destination address into skb hard header so we can figure out where
* to send the packet later.
*/
- memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN);
+ phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr));
+ memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
- return sizeof *header;
+ return IPOIB_HARD_LEN;
}
static void ipoib_set_mcast_list(struct net_device *dev)
@@ -1759,7 +1784,7 @@ void ipoib_setup(struct net_device *dev)
dev->flags |= IFF_BROADCAST | IFF_MULTICAST;
- dev->hard_header_len = IPOIB_ENCAP_LEN;
+ dev->hard_header_len = IPOIB_HARD_LEN;
dev->addr_len = INFINIBAND_ALEN;
dev->type = ARPHRD_INFINIBAND;
dev->tx_queue_len = ipoib_sendq_size * 2;
@@ -2004,6 +2029,7 @@ static struct net_device *ipoib_add_port(const char *format,
/* 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;
+ priv->dev->max_mtu = IPOIB_CM_MTU;
priv->dev->neigh_priv_len = sizeof(struct ipoib_neigh);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index d3394b6add24..1909dd252c94 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -796,9 +796,11 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
__ipoib_mcast_add(dev, mcast);
list_add_tail(&mcast->list, &priv->multicast_list);
}
- if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
+ if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, sizeof(struct ipoib_pseudo_header));
skb_queue_tail(&mcast->pkt_queue, skb);
- else {
+ } else {
++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
OpenPOWER on IntegriCloud