netdev - [PATCH bpf] net, xsk: Avoid taking multiple skbuff references

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 23 Nov 2020 14:12:15 +0100
From:   Björn Töpel <bjorn.topel@...il.com>
To:     ast@...nel.org, daniel@...earbox.net, netdev@...r.kernel.org,
        bpf@...r.kernel.org
Cc:     Björn Töpel <bjorn.topel@...el.com>,
        jonathan.lemon@...il.com, yhs@...com, weqaar.janjua@...il.com,
        magnus.karlsson@...el.com, weqaar.a.janjua@...el.com
Subject: [PATCH bpf] net, xsk: Avoid taking multiple skbuff references

From: Björn Töpel <bjorn.topel@...el.com>

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 <yhs@...com>
Fixes: 642e450b6b59 ("xsk: Do not discard packet when NETDEV_TX_BUSY")
Signed-off-by: Björn Töpel <bjorn.topel@...el.com>
---
 include/linux/netdevice.h | 1 +
 net/core/dev.c            | 9 +++++++--
 net/xdp/xsk.c             | 8 +-------
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 964b494b0e8d..e7402fca7752 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2815,6 +2815,7 @@ 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, bool free_on_busy);
 int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
diff --git a/net/core/dev.c b/net/core/dev.c
index 82dc6b48e45f..2af79a4253bb 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, bool free_on_busy)
 {
 	struct net_device *dev = skb->dev;
 	struct sk_buff *orig_skb = skb;
@@ -4211,7 +4211,7 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	local_bh_enable();
 
-	if (!dev_xmit_complete(ret))
+	if (free_on_busy && !dev_xmit_complete(ret))
 		kfree_skb(skb);
 
 	return ret;
@@ -4220,6 +4220,11 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
+
+int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+{
+	return __dev_direct_xmit(skb, queue_id, true);
+}
 EXPORT_SYMBOL(dev_direct_xmit);
 
 /*************************************************************************
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5a6cdf7b320d..c6ad31b374b7 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, false);
 		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