[PATCH bpf v2] net, xsk: Avoid taking multiple skbuff references
From: Björn Töpel <hidden>
Date: 2020-11-23 17:56:15
Also in:
bpf
Subsystem:
networking drivers, networking [general], the rest, xdp sockets (af_xdp) · Maintainers:
Andrew Lunn, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds, Magnus Karlsson, Maciej Fijalkowski
From: Björn Töpel <redacted>
Commit 642e450b6b59 ("xsk: Do not discard packet when NETDEV_TX_BUSY")
addressed the problem that packets were discarded from the Tx AF_XDP
ring, when the driver returned NETDEV_TX_BUSY. Part of the fix was
bumping the skbuff reference count, so that the buffer would not be
freed by dev_direct_xmit(). A reference count larger than one means
that the skbuff is "shared", which is not the case.
If the "shared" skbuff is sent to the generic XDP receive path,
netif_receive_generic_xdp(), and pskb_expand_head() is entered the
BUG_ON(skb_shared(skb)) will trigger.
This patch adds a variant to dev_direct_xmit(), __dev_direct_xmit(),
where a user can select the skbuff free policy. This allows AF_XDP to
avoid bumping the reference count, but still keep the NETDEV_TX_BUSY
behavior.
Reported-by: Yonghong Song <redacted>
Fixes: 642e450b6b59 ("xsk: Do not discard packet when NETDEV_TX_BUSY")
Signed-off-by: Björn Töpel <redacted>
---
v2:
Removed the bool parameter, and inlined dev_direct_xmit(). (Daniel)
---
include/linux/netdevice.h | 11 ++++++++++-
net/core/dev.c | 8 ++------
net/xdp/xsk.c | 8 +-------
3 files changed, 13 insertions(+), 14 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 964b494b0e8d..bd841f31dfab 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h@@ -2815,7 +2815,16 @@ u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); +static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +{ + int ret; + + ret = __dev_direct_xmit(skb, queue_id); + if (!dev_xmit_complete(ret)) + kfree_skb(skb); + return ret; +} int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head);
diff --git a/net/core/dev.c b/net/core/dev.c
index 82dc6b48e45f..8588ade790cb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c@@ -4180,7 +4180,7 @@ int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) } EXPORT_SYMBOL(dev_queue_xmit_accel); -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb;
@@ -4210,17 +4210,13 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) dev_xmit_recursion_dec(); local_bh_enable(); - - if (!dev_xmit_complete(ret)) - kfree_skb(skb); - return ret; drop: atomic_long_inc(&dev->tx_dropped); kfree_skb_list(skb); return NET_XMIT_DROP; } -EXPORT_SYMBOL(dev_direct_xmit); +EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5a6cdf7b320d..b7b039bd9d03 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c@@ -411,11 +411,7 @@ static int xsk_generic_xmit(struct sock *sk) skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr; skb->destructor = xsk_destruct_skb; - /* Hinder dev_direct_xmit from freeing the packet and - * therefore completing it in the destructor - */ - refcount_inc(&skb->users); - err = dev_direct_xmit(skb, xs->queue_id); + err = __dev_direct_xmit(skb, xs->queue_id); if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ skb->destructor = sock_wfree;
@@ -429,12 +425,10 @@ static int xsk_generic_xmit(struct sock *sk) /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP) { /* SKB completed but not sent */ - kfree_skb(skb); err = -EBUSY; goto out; } - consume_skb(skb); sent_frame = true; }
base-commit: 178648916e73e00de83150eb0c90c0d3a977a46a -- 2.27.0