4.9-stable review patch. If anyone has any objections, please let me know.
------------------
From: Erez Shitrit <erezsh@xxxxxxxxxxxx>
commit 2b0841766a898aba84630fb723989a77a9d3b4e6 upstream.
When sending packet to destination that was not resolved yet
via path query, the driver keeps the skb and tries to re-send it
again when the path is resolved.
But when re-sending via dev_queue_xmit the kernel doesn't call
to dev_hard_header, so IPoIB needs to keep 20 bytes in the skb
and to put the destination address inside them.
In that way the dev_start_xmit will have the correct destination,
and the driver won't take the destination from the skb->data, while
nothing exists there, which causes to packet be be dropped.
The test flow is:
1. Run the SM on remote node,
2. Restart the driver.
4. Ping some destination,
3. Observe that first ICMP request will be dropped.
Fixes: fc791b633515 ("IB/ipoib: move back IB LL address into the hard header")
Signed-off-by: Erez Shitrit <erezsh@xxxxxxxxxxxx>
Signed-off-by: Noa Osherovich <noaos@xxxxxxxxxxxx>
Signed-off-by: Leon Romanovsky <leon@xxxxxxxxxx>
Tested-by: Yuval Shaia <yuval.shaia@xxxxxxxxxx>
Signed-off-by: Doug Ledford <dledford@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/infiniband/ulp/ipoib/ipoib_main.c | 30 +++++++++++++++++-------------
1 file changed, 17 insertions(+), 13 deletions(-)
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -701,6 +701,14 @@ int ipoib_check_sm_sendonly_fullmember_s
return ret;
}
+static void push_pseudo_header(struct sk_buff *skb, const char *daddr)
+{
+ struct ipoib_pseudo_header *phdr;
+
+ phdr = (struct ipoib_pseudo_header *)skb_push(skb, sizeof(*phdr));
+ memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
+}
+
void ipoib_flush_paths(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -925,8 +933,7 @@ static void neigh_add_path(struct sk_buf
}
if (skb_queue_len(&neigh->queue) <
IPOIB_MAX_PATH_REC_QUEUE) {
- /* put pseudoheader back on for next time */
- skb_push(skb, IPOIB_PSEUDO_LEN);
+ push_pseudo_header(skb, neigh->daddr);
__skb_queue_tail(&neigh->queue, skb);
} else {
ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
@@ -944,10 +951,12 @@ static void neigh_add_path(struct sk_buf
if (!path->query && path_rec_start(dev, path))
goto err_path;
- if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+ if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ push_pseudo_header(skb, neigh->daddr);
__skb_queue_tail(&neigh->queue, skb);
- else
+ } else {
goto err_drop;
+ }
}
spin_unlock_irqrestore(&priv->lock, flags);
@@ -983,8 +992,7 @@ static void unicast_arp_send(struct sk_b
}
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);
+ push_pseudo_header(skb, phdr->hwaddr);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1016,8 +1024,7 @@ static void unicast_arp_send(struct sk_b
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);
+ push_pseudo_header(skb, phdr->hwaddr);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1098,8 +1105,7 @@ send_using_neigh:
}
if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
- /* put pseudoheader back on for next time */
- skb_push(skb, sizeof(*phdr));
+ push_pseudo_header(skb, phdr->hwaddr);
spin_lock_irqsave(&priv->lock, flags);
__skb_queue_tail(&neigh->queue, skb);
spin_unlock_irqrestore(&priv->lock, flags);
@@ -1131,7 +1137,6 @@ static int ipoib_hard_header(struct sk_b
unsigned short type,
const void *daddr, const void *saddr, unsigned len)
{
- struct ipoib_pseudo_header *phdr;
struct ipoib_header *header;
header = (struct ipoib_header *) skb_push(skb, sizeof *header);
@@ -1144,8 +1149,7 @@ static int ipoib_hard_header(struct sk_b
* destination address into skb hard header so we can figure out where
* to send the packet later.
*/
- phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr));
- memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
+ push_pseudo_header(skb, daddr);
return IPOIB_HARD_LEN;
}