diff options
Diffstat (limited to 'kernel/drivers/infiniband/ulp/ipoib')
| -rw-r--r-- | kernel/drivers/infiniband/ulp/ipoib/ipoib.h | 21 | ||||
| -rw-r--r-- | kernel/drivers/infiniband/ulp/ipoib/ipoib_cm.c | 33 | ||||
| -rw-r--r-- | kernel/drivers/infiniband/ulp/ipoib/ipoib_ib.c | 23 | ||||
| -rw-r--r-- | kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c | 60 | ||||
| -rw-r--r-- | kernel/drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 37 |
5 files changed, 116 insertions, 58 deletions
diff --git a/kernel/drivers/infiniband/ulp/ipoib/ipoib.h b/kernel/drivers/infiniband/ulp/ipoib/ipoib.h index 3ede10309..07cfcc326 100644 --- a/kernel/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/kernel/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 */ @@ -131,15 +133,21 @@ 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) */ @@ -472,6 +480,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_ah *address, u32 qpn); void ipoib_reap_ah(struct work_struct *work); +struct ipoib_path *__path_find(struct net_device *dev, void *gid); void ipoib_mark_paths_invalid(struct net_device *dev); void ipoib_flush_paths(struct net_device *dev); struct ipoib_dev_priv *ipoib_intf_alloc(const char *format); diff --git a/kernel/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/kernel/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 3ae9726ef..3ba7de5f9 100644 --- a/kernel/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/kernel/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 }; @@ -147,15 +149,15 @@ 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; @@ -1035,8 +1036,6 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_ tx_qp = ib_create_qp(priv->pd, &attr); if (PTR_ERR(tx_qp) == -EINVAL) { - ipoib_warn(priv, "can't use GFP_NOIO for QPs on device %s, using GFP_KERNEL\n", - priv->ca->name); attr.create_flags &= ~IB_QP_CREATE_USE_GFP_NOIO; tx_qp = ib_create_qp(priv->pd, &attr); } @@ -1299,6 +1298,8 @@ void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx) } } +#define QPN_AND_OPTIONS_OFFSET 4 + static void ipoib_cm_tx_start(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, @@ -1307,6 +1308,7 @@ static void ipoib_cm_tx_start(struct work_struct *work) struct ipoib_neigh *neigh; struct ipoib_cm_tx *p; unsigned long flags; + struct ipoib_path *path; int ret; struct ib_sa_path_rec pathrec; @@ -1319,7 +1321,19 @@ static void ipoib_cm_tx_start(struct work_struct *work) p = list_entry(priv->cm.start_list.next, typeof(*p), list); list_del_init(&p->list); neigh = p->neigh; + qpn = IPOIB_QPN(neigh->daddr); + /* + * As long as the search is with these 2 locks, + * path existence indicates its validity. + */ + path = __path_find(dev, neigh->daddr + QPN_AND_OPTIONS_OFFSET); + if (!path) { + pr_info("%s ignore not valid path %pI6\n", + __func__, + neigh->daddr + QPN_AND_OPTIONS_OFFSET); + goto free_neigh; + } memcpy(&pathrec, &p->path->pathrec, sizeof pathrec); spin_unlock_irqrestore(&priv->lock, flags); @@ -1331,6 +1345,7 @@ static void ipoib_cm_tx_start(struct work_struct *work) spin_lock_irqsave(&priv->lock, flags); if (ret) { +free_neigh: neigh = p->neigh; if (neigh) { neigh->cm = NULL; diff --git a/kernel/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/kernel/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 5ea0c1407..8f8c3af9f 100644 --- a/kernel/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/kernel/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -130,16 +130,15 @@ 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, @@ -242,10 +241,7 @@ 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->truesize = SKB_TRUESIZE(skb->len); + skb_add_pseudo_hdr(skb); ++dev->stats.rx_packets; dev->stats.rx_bytes += skb->len; @@ -1030,8 +1026,17 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, } if (level == IPOIB_FLUSH_LIGHT) { + int oper_up; ipoib_mark_paths_invalid(dev); + /* Set IPoIB operation as down to prevent races between: + * the flush flow which leaves MCG and on the fly joins + * which can happen during that time. mcast restart task + * should deal with join requests we missed. + */ + oper_up = test_and_clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags); ipoib_mcast_dev_flush(dev); + if (oper_up) + set_bit(IPOIB_FLAG_OPER_UP, &priv->flags); ipoib_flush_ah(dev); } diff --git a/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c b/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c index 7d3281866..8a4d10452 100644 --- a/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -481,7 +481,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf) return -EINVAL; } -static struct ipoib_path *__path_find(struct net_device *dev, void *gid) +struct ipoib_path *__path_find(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct rb_node *n = priv->path_tree.rb_node; @@ -850,9 +850,12 @@ 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; @@ -889,7 +892,7 @@ 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; @@ -897,16 +900,18 @@ 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; @@ -934,10 +939,12 @@ 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; @@ -951,13 +958,15 @@ 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)) && @@ -970,13 +979,13 @@ 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; } @@ -985,16 +994,16 @@ 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 */ @@ -1011,11 +1020,13 @@ 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); @@ -1047,8 +1058,8 @@ 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); @@ -1057,12 +1068,13 @@ 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) @@ -1131,7 +1143,9 @@ struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr) neigh = NULL; goto out_unlock; } - neigh->alive = jiffies; + + if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)) + neigh->alive = jiffies; goto out_unlock; } } @@ -1636,7 +1650,7 @@ 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; diff --git a/kernel/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/kernel/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 6dcef673d..a123d0439 100644 --- a/kernel/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/kernel/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -456,7 +456,10 @@ out_locked: return status; } -static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) +/* + * Caller must hold 'priv->lock' + */ +static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ib_sa_multicast *multicast; @@ -466,6 +469,10 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) ib_sa_comp_mask comp_mask; int ret = 0; + if (!priv->broadcast || + !test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) + return -EINVAL; + ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw); rec.mgid = mcast->mcmember.mgid; @@ -525,20 +532,23 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) rec.join_state = 4; #endif } + spin_unlock_irq(&priv->lock); multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, &rec, comp_mask, GFP_KERNEL, ipoib_mcast_join_complete, mcast); + spin_lock_irq(&priv->lock); if (IS_ERR(multicast)) { ret = PTR_ERR(multicast); ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret); - spin_lock_irq(&priv->lock); /* Requeue this join task with a backoff delay */ __ipoib_mcast_schedule_join_thread(priv, mcast, 1); clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); spin_unlock_irq(&priv->lock); complete(&mcast->done); + spin_lock_irq(&priv->lock); } + return 0; } void ipoib_mcast_join_task(struct work_struct *work) @@ -553,8 +563,11 @@ void ipoib_mcast_join_task(struct work_struct *work) if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) return; - if (ib_query_port(priv->ca, priv->port, &port_attr) || - port_attr.state != IB_PORT_ACTIVE) { + if (ib_query_port(priv->ca, priv->port, &port_attr)) { + ipoib_dbg(priv, "ib_query_port() failed\n"); + return; + } + if (port_attr.state != IB_PORT_ACTIVE) { ipoib_dbg(priv, "port state is not ACTIVE (state = %d) suspending join task\n", port_attr.state); return; @@ -620,9 +633,10 @@ void ipoib_mcast_join_task(struct work_struct *work) /* Found the next unjoined group */ init_completion(&mcast->done); set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - spin_unlock_irq(&priv->lock); - ipoib_mcast_join(dev, mcast); - spin_lock_irq(&priv->lock); + if (ipoib_mcast_join(dev, mcast)) { + spin_unlock_irq(&priv->lock); + return; + } } else if (!delay_until || time_before(mcast->delay_until, delay_until)) delay_until = mcast->delay_until; @@ -641,10 +655,9 @@ out: if (mcast) { init_completion(&mcast->done); set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + ipoib_mcast_join(dev, mcast); } spin_unlock_irq(&priv->lock); - if (mcast) - ipoib_mcast_join(dev, mcast); } int ipoib_mcast_start_thread(struct net_device *dev) @@ -743,9 +756,11 @@ 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); } |