bpf: New approach for BPF MTU handling

.travis.yml

@@ -0,0 +1,33 @@
+sudo: required
+language: bash
+dist: bionic
+services:
+    - docker
+
+env:
+    global:
+        - PROJECT_NAME='libbpf'
+        - AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")"
+        - REPO_ROOT="$TRAVIS_BUILD_DIR"
+        - CI_ROOT="$REPO_ROOT/travis-ci"
+        - VMTEST_ROOT="$CI_ROOT/vmtest"
+
+addons:
+    apt:
+        packages:
+            - qemu-kvm
+            - zstd
+            - binutils-dev
+            - elfutils
+            - libcap-dev
+            - libelf-dev
+            - libdw-dev
+            - python3-docutils
+
+jobs:
+    include:
+        - stage: Builds & Tests
+          name: Kernel LATEST + selftests
+          language: bash
+          env: KERNEL=LATEST
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1

include/linux/netdevice.h

@@ -3891,11 +3891,38 @@ int dev_forward_skb(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;

include/uapi/linux/bpf.h

@@ -2219,6 +2219,9 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
+ *		If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ *		was exceeded and result params->mtu contains the MTU.
+ *
  * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
@@ -3742,6 +3745,63 @@ union bpf_attr {
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
+ *
+ * int bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_result, s32 len_diff, u64 flags)
+ *	Description
+ *		Check ctx packet size against MTU of net device (based on
+ *		*ifindex*).  This helper will likely be used in combination with
+ *		helpers that adjust/change the packet size.  The argument
+ *		*len_diff* can be used for querying with a planned size
+ *		change. This allows to check MTU prior to changing packet ctx.
+ *
+ *		Specifying *ifindex* zero means the MTU check is performed
+ *		against the current net device.  This is practical if this isn't
+ *		used prior to redirect.
+ *
+ *		The Linux kernel route table can configure MTUs on a more
+ *		specific per route level, which is not provided by this helper.
+ *		For route level MTU checks use the **bpf_fib_lookup**\ ()
+ *		helper.
+ *
+ *		*ctx* is either **struct xdp_md** for XDP programs or
+ *		**struct sk_buff** for tc cls_act programs.
+ *
+ *		The *flags* argument can be a combination of one or more of the
+ *		following values:
+ *
+ *              **BPF_MTU_CHK_RELAX**
+ *			This flag relax or increase the MTU with room for one
+ *			VLAN header (4 bytes). This relaxation is also used by
+ *			the kernels own forwarding MTU checks.
+ *
+ *		**BPF_MTU_CHK_SEGS**
+ *			This flag will only works for *ctx* **struct sk_buff**.
+ *			If packet context contains extra packet segment buffers
+ *			(often knows as GSO skb), then MTU check is partly
+ *			skipped, because in transmit path it is possible for the
+ *			skb packet to get re-segmented (depending on net device
+ *			features).  This could still be a MTU violation, so this
+ *			flag enables performing MTU check against segments, with
+ *			a different violation return code to tell it apart.
+ *
+ *		The *mtu_result* pointer contains the MTU value of the net
+ *		device including the L2 header size (usually 14 bytes Ethernet
+ *		header). The net device configured MTU is the L3 size, but as
+ *		XDP and TX length operate at L2 this helper include L2 header
+ *		size in reported MTU.
+ *
+ *	Return
+ *		* 0 on success, and populate MTU value in *mtu_result* pointer.
+ *
+ *		* < 0 if any input argument is invalid (*mtu_result* not updated)
+ *
+ *		MTU violations return positive values, but also populate MTU
+ *		value in *mtu_result* pointer, as this can be needed for
+ *		implementing PMTU handing:
+ *
+ *		* **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ *		* **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3900,6 +3960,7 @@ union bpf_attr {
 	FN(bpf_per_cpu_ptr),            \
 	FN(bpf_this_cpu_ptr),		\
 	FN(redirect_peer),		\
+	FN(check_mtu),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4872,9 +4933,13 @@ struct bpf_fib_lookup {
 	__be16	sport;
 	__be16	dport;
 
-	/* total length of packet from network header - used for MTU check */
-	__u16	tot_len;
+	union {	/* used for MTU check */
+		/* input to lookup */
+		__u16	tot_len; /* total length of packet from network hdr */
 
+		/* output: MTU value (if requested check_mtu) */
+		__u16	mtu;
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */
@@ -4920,6 +4985,18 @@ struct bpf_redir_neigh {
 	};
 };
 
+/* bpf_check_mtu flags*/
+enum  bpf_check_mtu_flags {
+	BPF_MTU_CHK_RELAX = (1U << 0),
+	BPF_MTU_CHK_SEGS  = (1U << 1),
+};
+
+enum bpf_check_mtu_ret {
+	BPF_MTU_CHK_RET_SUCCESS,      /* check and lookup successful */
+	BPF_MTU_CHK_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+	BPF_MTU_CHK_RET_SEGS_TOOBIG,  /* GSO re-segmentation needed to fwd */
+};
+
 enum bpf_task_fd_type {
 	BPF_FD_TYPE_RAW_TRACEPOINT,	/* tp name */
 	BPF_FD_TYPE_TRACEPOINT,		/* tp name */

net/core/dev.c

@@ -2188,28 +2188,13 @@ 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 ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, true);
 
 	if (likely(!ret)) {
 		skb->protocol = eth_type_trans(skb, dev);
@@ -3885,6 +3870,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 		return NULL;
 	case TC_ACT_REDIRECT:
 		/* No need to push/pop skb's mac_header here on egress! */
+		skb_set_redirected(skb, false);
 		skb_do_redirect(skb);
 		*ret = NET_XMIT_SUCCESS;
 		return NULL;
@@ -4974,6 +4960,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		 * redirecting to another netdev
 		 */
 		__skb_push(skb, skb->mac_len);
+		skb_set_redirected(skb, true);
 		if (skb_do_redirect(skb) == -EAGAIN) {
 			__skb_pull(skb, skb->mac_len);
 			*another = true;