unsigned int send_only;
};
+/*
+ * This should be called with the mcast_mutex held
+ */
+static void __ipoib_mcast_schedule_join_thread(struct ipoib_dev_priv *priv,
+ struct ipoib_mcast *mcast,
+ bool delay)
+{
+ if (!test_bit(IPOIB_MCAST_RUN, &priv->flags))
+ return;
+
+ /*
+ * We will be scheduling *something*, so cancel whatever is
+ * currently scheduled first
+ */
+ cancel_delayed_work(&priv->mcast_task);
+ if (mcast && delay) {
+ /*
+ * We had a failure and want to schedule a retry later
+ */
+ mcast->backoff *= 2;
+ if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
+ mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
+ mcast->delay_until = jiffies + (mcast->backoff * HZ);
+ /*
+ * Mark this mcast for its delay, but restart the
+ * task immediately. The join task will make sure to
+ * clear out all entries without delays, and then
+ * schedule itself to run again when the earliest
+ * delay expires
+ */
+ queue_delayed_work(priv->wq, &priv->mcast_task, 0);
+ } else if (delay) {
+ /*
+ * Special case of retrying after a failure to
+ * allocate the broadcast multicast group, wait
+ * 1 second and try again
+ */
+ queue_delayed_work(priv->wq, &priv->mcast_task, HZ);
+ } else
+ queue_delayed_work(priv->wq, &priv->mcast_task, 0);
+}
+
static void ipoib_mcast_free(struct ipoib_mcast *mcast)
{
struct net_device *dev = mcast->dev;
mcast->dev = dev;
mcast->created = jiffies;
+ mcast->delay_until = jiffies;
mcast->backoff = 1;
INIT_LIST_HEAD(&mcast->list);
{
struct ipoib_mcast *mcast = multicast->context;
struct net_device *dev = mcast->dev;
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+ /*
+ * We have to take the mutex to force mcast_sendonly_join to
+ * return from ib_sa_multicast_join and set mcast->mc to a
+ * valid value. Otherwise we were racing with ourselves in
+ * that we might fail here, but get a valid return from
+ * ib_sa_multicast_join after we had cleared mcast->mc here,
+ * resulting in mis-matched joins and leaves and a deadlock
+ */
+ mutex_lock(&mcast_mutex);
/* We trap for port events ourselves. */
- if (status == -ENETRESET)
- return 0;
+ if (status == -ENETRESET) {
+ status = 0;
+ goto out;
+ }
if (!status)
status = ipoib_mcast_join_finish(mcast, &multicast->rec);
if (status) {
if (mcast->logcount++ < 20)
- ipoib_dbg_mcast(netdev_priv(dev), "multicast join failed for %pI6, status %d\n",
+ ipoib_dbg_mcast(netdev_priv(dev), "sendonly multicast "
+ "join failed for %pI6, status %d\n",
mcast->mcmember.mgid.raw, status);
/* Flush out any queued packets */
dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));
}
netif_tx_unlock_bh(dev);
-
- /* Clear the busy flag so we try again */
- status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY,
- &mcast->flags);
+ __ipoib_mcast_schedule_join_thread(priv, mcast, 1);
+ } else {
+ mcast->backoff = 1;
+ mcast->delay_until = jiffies;
+ __ipoib_mcast_schedule_join_thread(priv, NULL, 0);
}
+out:
+ clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+ if (status)
+ mcast->mc = NULL;
+ complete(&mcast->done);
+ mutex_unlock(&mcast_mutex);
return status;
}
int ret = 0;
if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) {
- ipoib_dbg_mcast(priv, "device shutting down, no multicast joins\n");
+ ipoib_dbg_mcast(priv, "device shutting down, no sendonly "
+ "multicast joins\n");
+ clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+ complete(&mcast->done);
return -ENODEV;
}
- if (test_and_set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) {
- ipoib_dbg_mcast(priv, "multicast entry busy, skipping\n");
- return -EBUSY;
- }
-
rec.mgid = mcast->mcmember.mgid;
rec.port_gid = priv->local_gid;
rec.pkey = cpu_to_be16(priv->pkey);
+ mutex_lock(&mcast_mutex);
mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca,
priv->port, &rec,
IB_SA_MCMEMBER_REC_MGID |
if (IS_ERR(mcast->mc)) {
ret = PTR_ERR(mcast->mc);
clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
- ipoib_warn(priv, "ib_sa_join_multicast failed (ret = %d)\n",
- ret);
+ ipoib_warn(priv, "ib_sa_join_multicast for sendonly join "
+ "failed (ret = %d)\n", ret);
+ complete(&mcast->done);
} else {
- ipoib_dbg_mcast(priv, "no multicast record for %pI6, starting join\n",
- mcast->mcmember.mgid.raw);
+ ipoib_dbg_mcast(priv, "no multicast record for %pI6, starting "
+ "sendonly join\n", mcast->mcmember.mgid.raw);
}
+ mutex_unlock(&mcast_mutex);
return ret;
}
ipoib_dbg_mcast(priv, "join completion for %pI6 (status %d)\n",
mcast->mcmember.mgid.raw, status);
+ /*
+ * We have to take the mutex to force mcast_join to
+ * return from ib_sa_multicast_join and set mcast->mc to a
+ * valid value. Otherwise we were racing with ourselves in
+ * that we might fail here, but get a valid return from
+ * ib_sa_multicast_join after we had cleared mcast->mc here,
+ * resulting in mis-matched joins and leaves and a deadlock
+ */
+ mutex_lock(&mcast_mutex);
+
/* We trap for port events ourselves. */
if (status == -ENETRESET) {
status = 0;
if (!status) {
mcast->backoff = 1;
- mutex_lock(&mcast_mutex);
- if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
- queue_delayed_work(priv->wq, &priv->mcast_task, 0);
- mutex_unlock(&mcast_mutex);
+ mcast->delay_until = jiffies;
+ __ipoib_mcast_schedule_join_thread(priv, NULL, 0);
/*
* Defer carrier on work to priv->wq to avoid a
*/
if (mcast == priv->broadcast)
queue_work(priv->wq, &priv->carrier_on_task);
-
- status = 0;
- goto out;
- }
-
- if (mcast->logcount++ < 20) {
- if (status == -ETIMEDOUT || status == -EAGAIN) {
- ipoib_dbg_mcast(priv, "multicast join failed for %pI6, status %d\n",
- mcast->mcmember.mgid.raw, status);
- } else {
- ipoib_warn(priv, "multicast join failed for %pI6, status %d\n",
- mcast->mcmember.mgid.raw, status);
+ } else {
+ if (mcast->logcount++ < 20) {
+ if (status == -ETIMEDOUT || status == -EAGAIN) {
+ ipoib_dbg_mcast(priv, "multicast join failed for %pI6, status %d\n",
+ mcast->mcmember.mgid.raw, status);
+ } else {
+ ipoib_warn(priv, "multicast join failed for %pI6, status %d\n",
+ mcast->mcmember.mgid.raw, status);
+ }
}
- }
-
- mcast->backoff *= 2;
- if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
- mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
- /* Clear the busy flag so we try again */
- status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-
- mutex_lock(&mcast_mutex);
- spin_lock_irq(&priv->lock);
- if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
- queue_delayed_work(priv->wq, &priv->mcast_task,
- mcast->backoff * HZ);
- spin_unlock_irq(&priv->lock);
- mutex_unlock(&mcast_mutex);
+ /* Requeue this join task with a backoff delay */
+ __ipoib_mcast_schedule_join_thread(priv, mcast, 1);
+ }
out:
+ clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+ if (status)
+ mcast->mc = NULL;
complete(&mcast->done);
+ mutex_unlock(&mcast_mutex);
return status;
}
rec.hop_limit = priv->broadcast->mcmember.hop_limit;
}
- set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
- init_completion(&mcast->done);
- set_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags);
-
+ mutex_lock(&mcast_mutex);
mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
&rec, comp_mask, GFP_KERNEL,
ipoib_mcast_join_complete, mcast);
if (IS_ERR(mcast->mc)) {
clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
- complete(&mcast->done);
ret = PTR_ERR(mcast->mc);
ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret);
-
- mcast->backoff *= 2;
- if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
- mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
-
- mutex_lock(&mcast_mutex);
- if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
- queue_delayed_work(priv->wq, &priv->mcast_task,
- mcast->backoff * HZ);
- mutex_unlock(&mcast_mutex);
+ __ipoib_mcast_schedule_join_thread(priv, mcast, 1);
+ complete(&mcast->done);
}
+ mutex_unlock(&mcast_mutex);
}
void ipoib_mcast_join_task(struct work_struct *work)
container_of(work, struct ipoib_dev_priv, mcast_task.work);
struct net_device *dev = priv->dev;
struct ib_port_attr port_attr;
+ unsigned long delay_until = 0;
+ struct ipoib_mcast *mcast = NULL;
+ int create = 1;
if (!test_bit(IPOIB_MCAST_RUN, &priv->flags))
return;
else
memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
+ /*
+ * We have to hold the mutex to keep from racing with the join
+ * completion threads on setting flags on mcasts, and we have
+ * to hold the priv->lock because dev_flush will remove entries
+ * out from underneath us, so at a minimum we need the lock
+ * through the time that we do the for_each loop of the mcast
+ * list or else dev_flush can make us oops.
+ */
+ mutex_lock(&mcast_mutex);
+ spin_lock_irq(&priv->lock);
+ if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
+ goto out;
+
if (!priv->broadcast) {
struct ipoib_mcast *broadcast;
- if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
- return;
-
- broadcast = ipoib_mcast_alloc(dev, 1);
+ broadcast = ipoib_mcast_alloc(dev, 0);
if (!broadcast) {
ipoib_warn(priv, "failed to allocate broadcast group\n");
- mutex_lock(&mcast_mutex);
- if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
- queue_delayed_work(priv->wq, &priv->mcast_task,
- HZ);
- mutex_unlock(&mcast_mutex);
- return;
+ /*
+ * Restart us after a 1 second delay to retry
+ * creating our broadcast group and attaching to
+ * it. Until this succeeds, this ipoib dev is
+ * completely stalled (multicast wise).
+ */
+ __ipoib_mcast_schedule_join_thread(priv, NULL, 1);
+ goto out;
}
- spin_lock_irq(&priv->lock);
memcpy(broadcast->mcmember.mgid.raw, priv->dev->broadcast + 4,
sizeof (union ib_gid));
priv->broadcast = broadcast;
__ipoib_mcast_add(dev, priv->broadcast);
- spin_unlock_irq(&priv->lock);
}
if (!test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) {
- if (!test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags))
- ipoib_mcast_join(dev, priv->broadcast, 0);
- return;
+ if (IS_ERR_OR_NULL(priv->broadcast->mc) &&
+ !test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags)) {
+ mcast = priv->broadcast;
+ create = 0;
+ if (mcast->backoff > 1 &&
+ time_before(jiffies, mcast->delay_until)) {
+ delay_until = mcast->delay_until;
+ mcast = NULL;
+ }
+ }
+ goto out;
}
- while (1) {
- struct ipoib_mcast *mcast = NULL;
-
- spin_lock_irq(&priv->lock);
- list_for_each_entry(mcast, &priv->multicast_list, list) {
- if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)
- && !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)
- && !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
+ /*
+ * We'll never get here until the broadcast group is both allocated
+ * and attached
+ */
+ list_for_each_entry(mcast, &priv->multicast_list, list) {
+ if (IS_ERR_OR_NULL(mcast->mc) &&
+ !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags) &&
+ !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
+ if (mcast->backoff == 1 ||
+ time_after_eq(jiffies, mcast->delay_until))
/* Found the next unjoined group */
break;
- }
+ else if (!delay_until ||
+ time_before(mcast->delay_until, delay_until))
+ delay_until = mcast->delay_until;
}
- spin_unlock_irq(&priv->lock);
-
- if (&mcast->list == &priv->multicast_list) {
- /* All done */
- break;
- }
-
- ipoib_mcast_join(dev, mcast, 1);
- return;
}
- ipoib_dbg_mcast(priv, "successfully joined all multicast groups\n");
+ if (&mcast->list == &priv->multicast_list) {
+ /*
+ * All done, unless we have delayed work from
+ * backoff retransmissions, but we will get
+ * restarted when the time is right, so we are
+ * done for now
+ */
+ mcast = NULL;
+ ipoib_dbg_mcast(priv, "successfully joined all "
+ "multicast groups\n");
+ }
- clear_bit(IPOIB_MCAST_RUN, &priv->flags);
+out:
+ if (mcast) {
+ init_completion(&mcast->done);
+ set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+ }
+ spin_unlock_irq(&priv->lock);
+ mutex_unlock(&mcast_mutex);
+ if (mcast) {
+ if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
+ ipoib_mcast_sendonly_join(mcast);
+ else
+ ipoib_mcast_join(dev, mcast, create);
+ }
+ if (delay_until)
+ queue_delayed_work(priv->wq, &priv->mcast_task,
+ delay_until - jiffies);
}
int ipoib_mcast_start_thread(struct net_device *dev)
ipoib_dbg_mcast(priv, "starting multicast thread\n");
mutex_lock(&mcast_mutex);
- if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags))
- queue_delayed_work(priv->wq, &priv->mcast_task, 0);
+ set_bit(IPOIB_MCAST_RUN, &priv->flags);
+ __ipoib_mcast_schedule_join_thread(priv, NULL, 0);
mutex_unlock(&mcast_mutex);
return 0;
int ret = 0;
if (test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
+ ipoib_warn(priv, "ipoib_mcast_leave on an in-flight join\n");
+
+ if (!IS_ERR_OR_NULL(mcast->mc))
ib_sa_free_multicast(mcast->mc);
+ else
+ ipoib_dbg(priv, "ipoib_mcast_leave with mcast->mc invalid\n");
if (test_and_clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
ipoib_dbg_mcast(priv, "leaving MGID %pI6\n",
be16_to_cpu(mcast->mcmember.mlid));
if (ret)
ipoib_warn(priv, "ib_detach_mcast failed (result = %d)\n", ret);
- }
+ } else if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
+ ipoib_dbg(priv, "leaving with no mcmember but not a "
+ "SENDONLY join\n");
return 0;
}
memcpy(mcast->mcmember.mgid.raw, mgid, sizeof (union ib_gid));
__ipoib_mcast_add(dev, mcast);
list_add_tail(&mcast->list, &priv->multicast_list);
+ __ipoib_mcast_schedule_join_thread(priv, NULL, 0);
}
if (!mcast->ah) {
++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
-
- if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
- ipoib_dbg_mcast(priv, "no address vector, "
- "but multicast join already started\n");
- else if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
- ipoib_mcast_sendonly_join(mcast);
-
/*
* If lookup completes between here and out:, don't
* want to send packet twice.
spin_unlock_irqrestore(&priv->lock, flags);
- /* seperate between the wait to the leave*/
+ /*
+ * make sure the in-flight joins have finished before we attempt
+ * to leave
+ */
list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
- if (test_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags))
+ if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
wait_for_completion(&mcast->done);
list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
unsigned long flags;
struct ib_sa_mcmember_rec rec;
- ipoib_dbg_mcast(priv, "restarting multicast task\n");
+ if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
+ /*
+ * shortcut...on shutdown flush is called next, just
+ * let it do all the work
+ */
+ return;
- /*
- * We're running on the priv->wq right now, so we can't call
- * mcast_stop_thread as it wants to flush the wq and that
- * will deadlock. We don't actually *need* to stop the
- * thread here anyway, so just clear the run flag, cancel
- * any delayed work, do our work, remove the old entries,
- * then restart the thread.
- */
- mutex_lock(&mcast_mutex);
- clear_bit(IPOIB_MCAST_RUN, &priv->flags);
- cancel_delayed_work(&priv->mcast_task);
- mutex_unlock(&mcast_mutex);
+ ipoib_dbg_mcast(priv, "restarting multicast task\n");
local_irq_save(flags);
netif_addr_lock(dev);
netif_addr_unlock(dev);
local_irq_restore(flags);
- /* We have to cancel outside of the spinlock */
+ /*
+ * make sure the in-flight joins have finished before we attempt
+ * to leave
+ */
+ list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
+ if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
+ wait_for_completion(&mcast->done);
+
list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
ipoib_mcast_leave(mcast->dev, mcast);
ipoib_mcast_free(mcast);
}
- if (test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
- ipoib_mcast_start_thread(dev);
+ /*
+ * Double check that we are still up
+ */
+ if (test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) {
+ spin_lock_irqsave(&priv->lock, flags);
+ __ipoib_mcast_schedule_join_thread(priv, NULL, 0);
+ spin_unlock_irqrestore(&priv->lock, flags);
+ }
}
#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
projects / cascardo / linux.git / commitdiff