* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (87 commits)
mlx4_core: Fix section mismatches
IPoIB: Allow setting policy to ignore multicast groups
IB/mthca: Mark error paths as unlikely() in post_srq_recv functions
IB/ipath: Minor fix to ordering of freeing and zeroing of tid pages.
IB/ipath: Remove redundant link state checks
IB/ipath: Fix IB_EVENT_PORT_ERR event
IB/ipath: Better handling of unexpected GPIO interrupts
IB/ipath: Maintain active time on all chips
IB/ipath: Fix QHT7040 serial number check
IB/ipath: Indicate a couple of chip bugs to userspace
IB/ipath: iba6110 rev4 no longer needs recv header overrun workaround
IB/ipath: Use counters in ipath_poll and cleanup interrupts in ipath_close
IB/ipath: Remove duplicate copy of LMC
IB/ipath: Add ability to set the LMC via the sysfs debugging interface
IB/ipath: Optimize completion queue entry insertion and polling
IB/ipath: Implement IB_EVENT_QP_LAST_WQE_REACHED
IB/ipath: Generate flush CQE when QP is in error state
IB/ipath: Remove redundant code
IB/ipath: Future proof eeprom checksum code (contents reading)
IB/ipath: UC RDMA WRITE with IMMEDIATE doesn't send the immediate
...
#define CMA_CM_RESPONSE_TIMEOUT 20
#define CMA_MAX_CM_RETRIES 15
+ #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
static void cma_add_one(struct ib_device *device);
static void cma_remove_one(struct ib_device *device);
u32 qkey;
u32 qp_num;
u8 srq;
+ u8 tos;
};
struct cma_multicast {
event.param.ud.private_data_len =
IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset;
} else {
+ ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
conn_id = cma_new_conn_id(&listen_id->id, ib_event);
cma_set_req_event_data(&event, &ib_event->param.req_rcvd,
ib_event->private_data, offset);
}
EXPORT_SYMBOL(rdma_listen);
+ void rdma_set_service_type(struct rdma_cm_id *id, int tos)
+ {
+ struct rdma_id_private *id_priv;
+
+ id_priv = container_of(id, struct rdma_id_private, id);
+ id_priv->tos = (u8) tos;
+ }
+ EXPORT_SYMBOL(rdma_set_service_type);
+
static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec,
void *context)
{
static int cma_query_ib_route(struct rdma_id_private *id_priv, int timeout_ms,
struct cma_work *work)
{
- struct rdma_dev_addr *addr = &id_priv->id.route.addr.dev_addr;
+ struct rdma_addr *addr = &id_priv->id.route.addr;
struct ib_sa_path_rec path_rec;
+ ib_sa_comp_mask comp_mask;
+ struct sockaddr_in6 *sin6;
memset(&path_rec, 0, sizeof path_rec);
- ib_addr_get_sgid(addr, &path_rec.sgid);
- ib_addr_get_dgid(addr, &path_rec.dgid);
- path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(addr));
+ ib_addr_get_sgid(&addr->dev_addr, &path_rec.sgid);
+ ib_addr_get_dgid(&addr->dev_addr, &path_rec.dgid);
+ path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(&addr->dev_addr));
path_rec.numb_path = 1;
path_rec.reversible = 1;
+ path_rec.service_id = cma_get_service_id(id_priv->id.ps, &addr->dst_addr);
+
+ comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
+ IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
+ IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID;
+
+ if (addr->src_addr.sa_family == AF_INET) {
+ path_rec.qos_class = cpu_to_be16((u16) id_priv->tos);
+ comp_mask |= IB_SA_PATH_REC_QOS_CLASS;
+ } else {
+ sin6 = (struct sockaddr_in6 *) &addr->src_addr;
+ path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20);
+ comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS;
+ }
id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device,
- id_priv->id.port_num, &path_rec,
- IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
- IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
- IB_SA_PATH_REC_REVERSIBLE,
- timeout_ms, GFP_KERNEL,
- cma_query_handler, work, &id_priv->query);
+ id_priv->id.port_num, &path_rec,
+ comp_mask, timeout_ms,
+ GFP_KERNEL, cma_query_handler,
+ work, &id_priv->query);
return (id_priv->query_id < 0) ? id_priv->query_id : 0;
}
static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
{
struct rdma_bind_list *bind_list;
- int port, ret;
+ int port, ret, low, high;
bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);
if (!bind_list)
return -ENOMEM;
retry:
+ /* FIXME: add proper port randomization per like inet_csk_get_port */
do {
ret = idr_get_new_above(ps, bind_list, next_port, &port);
} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
if (ret)
goto err1;
- if (port > sysctl_local_port_range[1]) {
- if (next_port != sysctl_local_port_range[0]) {
+ inet_get_local_port_range(&low, &high);
+ if (port > high) {
+ if (next_port != low) {
idr_remove(ps, port);
- next_port = sysctl_local_port_range[0];
+ next_port = low;
goto retry;
}
ret = -EADDRNOTAVAIL;
goto err2;
}
- if (port == sysctl_local_port_range[1])
- next_port = sysctl_local_port_range[0];
+ if (port == high)
+ next_port = low;
else
next_port = port + 1;
static int cma_init(void)
{
- int ret;
+ int ret, low, high;
get_random_bytes(&next_port, sizeof next_port);
- next_port = ((unsigned int) next_port %
- (sysctl_local_port_range[1] - sysctl_local_port_range[0])) +
- sysctl_local_port_range[0];
+ inet_get_local_port_range(&low, &high);
+ next_port = ((unsigned int) next_port % (high - low)) + low;
+
cma_wq = create_singlethread_workqueue("rdma_cm");
if (!cma_wq)
return -ENOMEM;
IPOIB_MCAST_STARTED = 8,
IPOIB_FLAG_NETIF_STOPPED = 9,
IPOIB_FLAG_ADMIN_CM = 10,
+ IPOIB_FLAG_UMCAST = 11,
IPOIB_MAX_BACKOFF_SECONDS = 16,
u8 hwaddr[INFINIBAND_ALEN];
};
- struct ipoib_mcast;
+ /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
+ struct ipoib_mcast {
+ struct ib_sa_mcmember_rec mcmember;
+ struct ib_sa_multicast *mc;
+ struct ipoib_ah *ah;
+
+ struct rb_node rb_node;
+ struct list_head list;
+
+ unsigned long created;
+ unsigned long backoff;
+
+ unsigned long flags;
+ unsigned char logcount;
+
+ struct list_head neigh_list;
+
+ struct sk_buff_head pkt_queue;
+
+ struct net_device *dev;
+ };
struct ipoib_rx_buf {
struct sk_buff *skb;
struct net_device *dev;
+ struct napi_struct napi;
+
unsigned long flags;
struct mutex mcast_mutex;
struct ib_event_handler event_handler;
- struct net_device_stats stats;
-
struct net_device *parent;
struct list_head child_intfs;
struct list_head list;
/* functions */
-int ipoib_poll(struct net_device *dev, int *budget);
+int ipoib_poll(struct napi_struct *napi, int budget);
void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr);
struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
int ipoib_open(struct net_device *dev);
int ipoib_add_pkey_attr(struct net_device *dev);
+ int ipoib_add_umcast_attr(struct net_device *dev);
void ipoib_send(struct net_device *dev, struct sk_buff *skb,
struct ipoib_ah *address, u32 qpn);
ipoib_dbg(priv, "cm recv error "
"(status=%d, wrid=%d vend_err %x)\n",
wc->status, wr_id, wc->vendor_err);
- ++priv->stats.rx_dropped;
+ ++dev->stats.rx_dropped;
goto repost;
}
* this packet and reuse the old buffer.
*/
ipoib_dbg(priv, "failed to allocate receive buffer %d\n", wr_id);
- ++priv->stats.rx_dropped;
+ ++dev->stats.rx_dropped;
goto repost;
}
skb_pull(skb, IPOIB_ENCAP_LEN);
dev->last_rx = jiffies;
- ++priv->stats.rx_packets;
- priv->stats.rx_bytes += skb->len;
+ ++dev->stats.rx_packets;
+ dev->stats.rx_bytes += skb->len;
skb->dev = dev;
/* XXX get correct PACKET_ type here */
if (unlikely(skb->len > tx->mtu)) {
ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
skb->len, tx->mtu);
- ++priv->stats.tx_dropped;
- ++priv->stats.tx_errors;
+ ++dev->stats.tx_dropped;
+ ++dev->stats.tx_errors;
ipoib_cm_skb_too_long(dev, skb, tx->mtu - IPOIB_ENCAP_LEN);
return;
}
tx_req->skb = skb;
addr = ib_dma_map_single(priv->ca, skb->data, skb->len, DMA_TO_DEVICE);
if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
- ++priv->stats.tx_errors;
+ ++dev->stats.tx_errors;
dev_kfree_skb_any(skb);
return;
}
if (unlikely(post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1),
addr, skb->len))) {
ipoib_warn(priv, "post_send failed\n");
- ++priv->stats.tx_errors;
+ ++dev->stats.tx_errors;
ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE);
dev_kfree_skb_any(skb);
} else {
ib_dma_unmap_single(priv->ca, tx_req->mapping, tx_req->skb->len, DMA_TO_DEVICE);
/* FIXME: is this right? Shouldn't we only increment on success? */
- ++priv->stats.tx_packets;
- priv->stats.tx_bytes += tx_req->skb->len;
+ ++dev->stats.tx_packets;
+ dev->stats.tx_bytes += tx_req->skb->len;
dev_kfree_skb_any(tx_req->skb);
static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ib_cq *cq)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
- struct ib_qp_init_attr attr = {};
- attr.recv_cq = priv->cq;
- attr.srq = priv->cm.srq;
- attr.cap.max_send_wr = ipoib_sendq_size;
- attr.cap.max_send_sge = 1;
- attr.sq_sig_type = IB_SIGNAL_ALL_WR;
- attr.qp_type = IB_QPT_RC;
- attr.send_cq = cq;
+ struct ib_qp_init_attr attr = {
+ .send_cq = cq,
+ .recv_cq = priv->cq,
+ .srq = priv->cm.srq,
+ .cap.max_send_wr = ipoib_sendq_size,
+ .cap.max_send_sge = 1,
+ .sq_sig_type = IB_SIGNAL_ALL_WR,
+ .qp_type = IB_QPT_RC,
+ };
+
return ib_create_qp(priv->pd, &attr);
}
* this packet and reuse the old buffer.
*/
if (unlikely(ipoib_alloc_rx_skb(dev, wr_id))) {
- ++priv->stats.rx_dropped;
+ ++dev->stats.rx_dropped;
goto repost;
}
skb_pull(skb, IPOIB_ENCAP_LEN);
dev->last_rx = jiffies;
- ++priv->stats.rx_packets;
- priv->stats.rx_bytes += skb->len;
+ ++dev->stats.rx_packets;
+ dev->stats.rx_bytes += skb->len;
skb->dev = dev;
/* XXX get correct PACKET_ type here */
ib_dma_unmap_single(priv->ca, tx_req->mapping,
tx_req->skb->len, DMA_TO_DEVICE);
- ++priv->stats.tx_packets;
- priv->stats.tx_bytes += tx_req->skb->len;
+ ++dev->stats.tx_packets;
+ dev->stats.tx_bytes += tx_req->skb->len;
dev_kfree_skb_any(tx_req->skb);
wc->status, wr_id, wc->vendor_err);
}
-int ipoib_poll(struct net_device *dev, int *budget)
+int ipoib_poll(struct napi_struct *napi, int budget)
{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
- int max = min(*budget, dev->quota);
+ struct ipoib_dev_priv *priv = container_of(napi, struct ipoib_dev_priv, napi);
+ struct net_device *dev = priv->dev;
int done;
int t;
- int empty;
int n, i;
done = 0;
- empty = 0;
- while (max) {
+poll_more:
+ while (done < budget) {
+ int max = (budget - done);
+
t = min(IPOIB_NUM_WC, max);
n = ib_poll_cq(priv->cq, t, priv->ibwc);
- for (i = 0; i < n; ++i) {
+ for (i = 0; i < n; i++) {
struct ib_wc *wc = priv->ibwc + i;
if (wc->wr_id & IPOIB_CM_OP_SRQ) {
++done;
- --max;
ipoib_cm_handle_rx_wc(dev, wc);
} else if (wc->wr_id & IPOIB_OP_RECV) {
++done;
- --max;
ipoib_ib_handle_rx_wc(dev, wc);
} else
ipoib_ib_handle_tx_wc(dev, wc);
}
- if (n != t) {
- empty = 1;
+ if (n != t)
break;
- }
}
- dev->quota -= done;
- *budget -= done;
-
- if (empty) {
- netif_rx_complete(dev);
+ if (done < budget) {
+ netif_rx_complete(dev, napi);
if (unlikely(ib_req_notify_cq(priv->cq,
IB_CQ_NEXT_COMP |
IB_CQ_REPORT_MISSED_EVENTS)) &&
- netif_rx_reschedule(dev, 0))
- return 1;
-
- return 0;
+ netif_rx_reschedule(dev, napi))
+ goto poll_more;
}
- return 1;
+ return done;
}
void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr)
{
- netif_rx_schedule(dev_ptr);
+ struct net_device *dev = dev_ptr;
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+ netif_rx_schedule(dev, &priv->napi);
}
static inline int post_send(struct ipoib_dev_priv *priv,
if (unlikely(skb->len > priv->mcast_mtu + IPOIB_ENCAP_LEN)) {
ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
skb->len, priv->mcast_mtu + IPOIB_ENCAP_LEN);
- ++priv->stats.tx_dropped;
- ++priv->stats.tx_errors;
+ ++dev->stats.tx_dropped;
+ ++dev->stats.tx_errors;
ipoib_cm_skb_too_long(dev, skb, priv->mcast_mtu);
return;
}
addr = ib_dma_map_single(priv->ca, skb->data, skb->len,
DMA_TO_DEVICE);
if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
- ++priv->stats.tx_errors;
+ ++dev->stats.tx_errors;
dev_kfree_skb_any(skb);
return;
}
if (unlikely(post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
address->ah, qpn, addr, skb->len))) {
ipoib_warn(priv, "post_send failed\n");
- ++priv->stats.tx_errors;
+ ++dev->stats.tx_errors;
ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE);
dev_kfree_skb_any(skb);
} else {
do {
n = ib_poll_cq(priv->cq, IPOIB_NUM_WC, priv->ibwc);
for (i = 0; i < n; ++i) {
+ /*
+ * Convert any successful completions to flush
+ * errors to avoid passing packets up the
+ * stack after bringing the device down.
+ */
+ if (priv->ibwc[i].status == IB_WC_SUCCESS)
+ priv->ibwc[i].status = IB_WC_WR_FLUSH_ERR;
+
if (priv->ibwc[i].wr_id & IPOIB_CM_OP_SRQ)
ipoib_cm_handle_rx_wc(dev, priv->ibwc + i);
else if (priv->ibwc[i].wr_id & IPOIB_OP_RECV)
int i;
clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags);
- netif_poll_disable(dev);
ipoib_cm_dev_stop(dev);
msleep(1);
}
- netif_poll_enable(dev);
ib_req_notify_cq(priv->cq, IB_CQ_NEXT_COMP);
return 0;
ipoib_dbg(priv, "bringing up interface\n");
+ napi_enable(&priv->napi);
set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
if (ipoib_pkey_dev_delay_open(dev))
return 0;
- if (ipoib_ib_dev_open(dev))
+ if (ipoib_ib_dev_open(dev)) {
+ napi_disable(&priv->napi);
return -EINVAL;
+ }
if (ipoib_ib_dev_up(dev)) {
ipoib_ib_dev_stop(dev, 1);
+ napi_disable(&priv->napi);
return -EINVAL;
}
ipoib_dbg(priv, "stopping interface\n");
clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
+ napi_disable(&priv->napi);
netif_stop_queue(dev);
INIT_LIST_HEAD(&path->neigh_list);
memcpy(path->pathrec.dgid.raw, gid, sizeof (union ib_gid));
- path->pathrec.sgid = priv->local_gid;
- path->pathrec.pkey = cpu_to_be16(priv->pkey);
- path->pathrec.numb_path = 1;
+ path->pathrec.sgid = priv->local_gid;
+ path->pathrec.pkey = cpu_to_be16(priv->pkey);
+ path->pathrec.numb_path = 1;
+ path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class;
return path;
}
IB_SA_PATH_REC_DGID |
IB_SA_PATH_REC_SGID |
IB_SA_PATH_REC_NUMB_PATH |
+ IB_SA_PATH_REC_TRAFFIC_CLASS |
IB_SA_PATH_REC_PKEY,
1000, GFP_ATOMIC,
path_rec_completion,
neigh = ipoib_neigh_alloc(skb->dst->neighbour);
if (!neigh) {
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
return;
}
err_path:
ipoib_neigh_free(dev, neigh);
err_drop:
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
spin_unlock(&priv->lock);
} else
__path_add(dev, path);
} else {
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
skb_push(skb, sizeof *phdr);
__skb_queue_tail(&path->queue, skb);
} else {
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
__skb_queue_tail(&neigh->queue, skb);
spin_unlock(&priv->lock);
} else {
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
} else {
IPOIB_QPN(phdr->hwaddr),
IPOIB_GID_RAW_ARG(phdr->hwaddr + 4));
dev_kfree_skb_any(skb);
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
goto out;
}
return NETDEV_TX_OK;
}
-static struct net_device_stats *ipoib_get_stats(struct net_device *dev)
-{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
-
- return &priv->stats;
-}
-
static void ipoib_timeout(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
static int ipoib_hard_header(struct sk_buff *skb,
struct net_device *dev,
unsigned short type,
- void *daddr, void *saddr, unsigned len)
+ const void *daddr, const void *saddr, unsigned len)
{
struct ipoib_header *header;
void ipoib_neigh_free(struct net_device *dev, struct ipoib_neigh *neigh)
{
- struct ipoib_dev_priv *priv = netdev_priv(dev);
struct sk_buff *skb;
*to_ipoib_neigh(neigh->neighbour) = NULL;
while ((skb = __skb_dequeue(&neigh->queue))) {
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
if (ipoib_cm_get(neigh))
priv->tx_ring = NULL;
}
+static const struct header_ops ipoib_header_ops = {
+ .create = ipoib_hard_header,
+};
+
static void ipoib_setup(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
dev->stop = ipoib_stop;
dev->change_mtu = ipoib_change_mtu;
dev->hard_start_xmit = ipoib_start_xmit;
- dev->get_stats = ipoib_get_stats;
dev->tx_timeout = ipoib_timeout;
- dev->hard_header = ipoib_hard_header;
+ dev->header_ops = &ipoib_header_ops;
dev->set_multicast_list = ipoib_set_mcast_list;
dev->neigh_setup = ipoib_neigh_setup_dev;
- dev->poll = ipoib_poll;
- dev->weight = 100;
+
+ netif_napi_add(dev, &priv->napi, ipoib_poll, 100);
dev->watchdog_timeo = HZ;
netif_carrier_off(dev);
- SET_MODULE_OWNER(dev);
-
priv->dev = dev;
spin_lock_init(&priv->lock);
}
static DEVICE_ATTR(pkey, S_IRUGO, show_pkey, NULL);
+ static ssize_t show_umcast(struct device *dev,
+ struct device_attribute *attr, char *buf)
+ {
+ struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));
+
+ return sprintf(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags));
+ }
+
+ static ssize_t set_umcast(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+ {
+ struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));
+ unsigned long umcast_val = simple_strtoul(buf, NULL, 0);
+
+ if (umcast_val > 0) {
+ set_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+ ipoib_warn(priv, "ignoring multicast groups joined directly "
+ "by userspace\n");
+ } else
+ clear_bit(IPOIB_FLAG_UMCAST, &priv->flags);
+
+ return count;
+ }
+ static DEVICE_ATTR(umcast, S_IWUSR | S_IRUGO, show_umcast, set_umcast);
+
+ int ipoib_add_umcast_attr(struct net_device *dev)
+ {
+ return device_create_file(&dev->dev, &dev_attr_umcast);
+ }
+
static ssize_t create_child(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
if (result) {
printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
hca->name, port, result);
- goto alloc_mem_failed;
+ goto device_init_failed;
}
/*
if (result) {
printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n",
hca->name, port, result);
- goto alloc_mem_failed;
+ goto device_init_failed;
} else
memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
goto sysfs_failed;
if (ipoib_add_pkey_attr(priv->dev))
goto sysfs_failed;
+ if (ipoib_add_umcast_attr(priv->dev))
+ goto sysfs_failed;
if (device_create_file(&priv->dev->dev, &dev_attr_create_child))
goto sysfs_failed;
if (device_create_file(&priv->dev->dev, &dev_attr_delete_child))
static DEFINE_MUTEX(mcast_mutex);
- /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
- struct ipoib_mcast {
- struct ib_sa_mcmember_rec mcmember;
- struct ib_sa_multicast *mc;
- struct ipoib_ah *ah;
-
- struct rb_node rb_node;
- struct list_head list;
-
- unsigned long created;
- unsigned long backoff;
-
- unsigned long flags;
- unsigned char logcount;
-
- struct list_head neigh_list;
-
- struct sk_buff_head pkt_queue;
-
- struct net_device *dev;
- };
-
struct ipoib_mcast_iter {
struct net_device *dev;
union ib_gid mgid;
}
spin_lock_irqsave(&priv->tx_lock, flags);
- priv->stats.tx_dropped += tx_dropped;
+ dev->stats.tx_dropped += tx_dropped;
spin_unlock_irqrestore(&priv->tx_lock, flags);
kfree(mcast);
/* Flush out any queued packets */
spin_lock_irq(&priv->tx_lock);
while (!skb_queue_empty(&mcast->pkt_queue)) {
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));
}
spin_unlock_irq(&priv->tx_lock);
if (!test_bit(IPOIB_MCAST_STARTED, &priv->flags) ||
!priv->broadcast ||
!test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) {
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
goto unlock;
}
if (!mcast) {
ipoib_warn(priv, "unable to allocate memory for "
"multicast structure\n");
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
goto out;
}
if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
skb_queue_tail(&mcast->pkt_queue, skb);
else {
- ++priv->stats.tx_dropped;
+ ++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
struct ipoib_mcast *mcast, *tmcast;
LIST_HEAD(remove_list);
unsigned long flags;
+ struct ib_sa_mcmember_rec rec;
ipoib_dbg_mcast(priv, "restarting multicast task\n");
if (!mcast || test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
struct ipoib_mcast *nmcast;
+ /* ignore group which is directly joined by userspace */
+ if (test_bit(IPOIB_FLAG_UMCAST, &priv->flags) &&
+ !ib_sa_get_mcmember_rec(priv->ca, priv->port, &mgid, &rec)) {
+ ipoib_dbg_mcast(priv, "ignoring multicast entry for mgid "
+ IPOIB_GID_FMT "\n", IPOIB_GID_ARG(mgid));
+ continue;
+ }
+
/* Not found or send-only group, let's add a new entry */
ipoib_dbg_mcast(priv, "adding multicast entry for mgid "
IPOIB_GID_FMT "\n", IPOIB_GID_ARG(mgid));