diff mbox series

[bpf-next,V14,5/7] bpf: drop MTU check when doing TC-BPF redirect to ingress

Message ID 161217675170.494501.11194096254681150724.stgit@firesoul (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series bpf: New approach for BPF MTU handling | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for bpf-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 12 maintainers not CCed: davem@davemloft.net songliubraving@fb.com andrii@kernel.org daniel@iogearbox.net bjorn@kernel.org edumazet@google.com ap420073@gmail.com kpsingh@kernel.org ast@kernel.org xiyou.wangcong@gmail.com kafai@fb.com yhs@fb.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit fail Errors and warnings before: 7149 this patch: 7151
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning CHECK: Alignment should match open parenthesis
netdev/build_allmodconfig_warn fail Errors and warnings before: 7549 this patch: 7551
netdev/header_inline success Link
netdev/stable success Stable not CCed

Commit Message

Jesper Dangaard Brouer Feb. 1, 2021, 10:52 a.m. UTC 
The use-case for dropping the MTU check when TC-BPF does redirect to
ingress, is described by Eyal Birger in email[0]. The summary is the
ability to increase packet size (e.g. with IPv6 headers for NAT64) and
ingress redirect packet and let normal netstack fragment packet as needed.

[0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/

V9:
 - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect

V4:
 - Keep net_device "up" (IFF_UP) check.
 - Adjustment to handle bpf_redirect_peer() helper

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
---
 include/linux/netdevice.h |   32 ++++++++++++++++++++++++++++++--
 net/core/dev.c            |   32 ++++++++++++++------------------
 net/core/filter.c         |    6 +++---
 3 files changed, 47 insertions(+), 23 deletions(-)

Comments

kernel test robot Feb. 1, 2021, 7:58 p.m. UTC | #1 
Hi Jesper,

I love your patch! Perhaps something to improve:

[auto build test WARNING on bpf-next/master]

url:    https://github.com/0day-ci/linux/commits/Jesper-Dangaard-Brouer/bpf-New-approach-for-BPF-MTU-handling/20210201-185654
base:   https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git master
config: x86_64-randconfig-r014-20210201 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project 275c6af7d7f1ed63a03d05b4484413e447133269)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install x86_64 cross compiling tool for clang build
        # apt-get install binutils-x86-64-linux-gnu
        # https://github.com/0day-ci/linux/commit/8d1404896e0346004412f5ffd64ef92ac578e5de
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Jesper-Dangaard-Brouer/bpf-New-approach-for-BPF-MTU-handling/20210201-185654
        git checkout 8d1404896e0346004412f5ffd64ef92ac578e5de
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

>> net/core/dev.c:2201:5: warning: no previous prototype for function '__dev_forward_skb2' [-Wmissing-prototypes]
   int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb,
       ^
   net/core/dev.c:2201:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
   int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb,
   ^
   static 
   net/core/dev.c:4937:1: warning: unused function 'sch_handle_ingress' [-Wunused-function]
   sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
   ^
   net/core/dev.c:5086:19: warning: unused function 'nf_ingress' [-Wunused-function]
   static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
                     ^
   3 warnings generated.


vim +/__dev_forward_skb2 +2201 net/core/dev.c

  2200	
> 2201	int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb,
  2202			     bool check_mtu)
  2203	{
  2204		int ret = ____dev_forward_skb(dev, skb, check_mtu);
  2205	
  2206		if (likely(!ret)) {
  2207			skb->protocol = eth_type_trans(skb, dev);
  2208			skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
  2209		}
  2210	
  2211		return ret;
  2212	}
  2213	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
diff mbox series

Patch

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5b949076ed23..b7915484369c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3926,14 +3926,42 @@  int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
+int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb);
 bool is_skb_forwardable(const struct net_device *dev,
 			const struct sk_buff *skb);
 
+static __always_inline bool __is_skb_forwardable(const struct net_device *dev,
+						 const struct sk_buff *skb,
+						 const bool check_mtu)
+{
+	const u32 vlan_hdr_len = 4; /* VLAN_HLEN */
+	unsigned int len;
+
+	if (!(dev->flags & IFF_UP))
+		return false;
+
+	if (!check_mtu)
+		return true;
+
+	len = dev->mtu + dev->hard_header_len + vlan_hdr_len;
+	if (skb->len <= len)
+		return true;
+
+	/* if TSO is enabled, we don't care about the length as the packet
+	 * could be forwarded without being segmented before
+	 */
+	if (skb_is_gso(skb))
+		return true;
+
+	return false;
+}
+
 static __always_inline int ____dev_forward_skb(struct net_device *dev,
-					       struct sk_buff *skb)
+					       struct sk_buff *skb,
+					       const bool check_mtu)
 {
 	if (skb_orphan_frags(skb, GFP_ATOMIC) ||
-	    unlikely(!is_skb_forwardable(dev, skb))) {
+	    unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) {
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
 		return NET_RX_DROP;
diff --git a/net/core/dev.c b/net/core/dev.c
index bae35c1ae192..87bb2cd62189 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2194,28 +2194,14 @@  static inline void net_timestamp_set(struct sk_buff *skb)
 
 bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
 {
-	unsigned int len;
-
-	if (!(dev->flags & IFF_UP))
-		return false;
-
-	len = dev->mtu + dev->hard_header_len + VLAN_HLEN;
-	if (skb->len <= len)
-		return true;
-
-	/* if TSO is enabled, we don't care about the length as the packet
-	 * could be forwarded without being segmented before
-	 */
-	if (skb_is_gso(skb))
-		return true;
-
-	return false;
+	return __is_skb_forwardable(dev, skb, true);
 }
 EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
-int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb,
+		     bool check_mtu)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, check_mtu);
 
 	if (likely(!ret)) {
 		skb->protocol = eth_type_trans(skb, dev);
@@ -2224,6 +2210,11 @@  int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 
 	return ret;
 }
+
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	return __dev_forward_skb2(dev, skb, true);
+}
 EXPORT_SYMBOL_GPL(__dev_forward_skb);
 
 /**
@@ -2250,6 +2241,11 @@  int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
 
+int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb)
+{
+	return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb);
+}
+
 static inline int deliver_skb(struct sk_buff *skb,
 			      struct packet_type *pt_prev,
 			      struct net_device *orig_dev)
diff --git a/net/core/filter.c b/net/core/filter.c
index f6777e8f9ff7..28735dbb7059 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2083,13 +2083,13 @@  static const struct bpf_func_proto bpf_csum_level_proto = {
 
 static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	return dev_forward_skb(dev, skb);
+	return dev_forward_skb_nomtu(dev, skb);
 }
 
 static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
 				      struct sk_buff *skb)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, false);
 
 	if (likely(!ret)) {
 		skb->dev = dev;
@@ -2480,7 +2480,7 @@  int skb_do_redirect(struct sk_buff *skb)
 			goto out_drop;
 		dev = ops->ndo_get_peer_dev(dev);
 		if (unlikely(!dev ||
-			     !is_skb_forwardable(dev, skb) ||
+			     !(dev->flags & IFF_UP) ||
 			     net_eq(net, dev_net(dev))))
 			goto out_drop;
 		skb->dev = dev;