Merge branch 'xdp-head-adjustment'

Martin KaFai Lau says:

====================
Allow head adjustment in XDP prog

This series adds a helper to allow head adjusting in XDP prog.  mlx4
driver has been modified to support this feature.  An example is written
to encapsulate a packet with an IPv4/v6 header and then XDP_TX it
out.

v4:
1. Remove XDP_QUERY_FEATURES command.  Instead, check
   the prog->xdp_adjust_head bit inside the driver itself
   during XDP_SETUP_PROG in patch 1of4.
   Thanks for everybody's ideas.
2. Nit changes on sample code per Jesper

v3:
1. Check if the driver supports head adjustment before
   setting the xdp_prog fd to the device in patch 1of4.
2. Remove the page alignment assumption on the data_hard_start.
   Instead, add data_hard_start to the struct xdp_buff and the
   driver has to fill it if it supports head adjustment.
3. Keep the wire MTU as before in mlx4
4. Set map0_byte_count to PAGE_SIZE in patch 3of4

v2:
1. Make a variable name change in bpf_xdp_adjust_head() in patch 1
2. Ensure no less than ETH_HLEN data in bpf_xdp_adjust_head() in patch 1
3. Some clarifications in commit log messages of patch 2 and 3
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/powerpc/net/bpf_jit_comp64.c

@@ -766,7 +766,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			func = (u8 *) __bpf_call_base + imm;
 
 			/* Save skb pointer if we need to re-cache skb data */
-			if (bpf_helper_changes_skb_data(func))
+			if (bpf_helper_changes_pkt_data(func))
 				PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
 
 			bpf_jit_emit_func_call(image, ctx, (u64)func);
@@ -775,7 +775,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			PPC_MR(b2p[BPF_REG_0], 3);
 
 			/* refresh skb cache */
-			if (bpf_helper_changes_skb_data(func)) {
+			if (bpf_helper_changes_pkt_data(func)) {
 				/* reload skb pointer to r3 */
 				PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
 				bpf_jit_emit_skb_loads(image, ctx);

arch/s390/net/bpf_jit_comp.c

@@ -981,7 +981,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
-		if (bpf_helper_changes_skb_data((void *)func)) {
+		if (bpf_helper_changes_pkt_data((void *)func)) {
 			jit->seen |= SEEN_SKB_CHANGE;
 			/* lg %b1,ST_OFF_SKBP(%r15) */
 			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,

arch/x86/net/bpf_jit_comp.c

@@ -853,7 +853,7 @@ xadd:			if (is_imm8(insn->off))
 			func = (u8 *) __bpf_call_base + imm32;
 			jmp_offset = func - (image + addrs[i]);
 			if (seen_ld_abs) {
-				reload_skb_data = bpf_helper_changes_skb_data(func);
+				reload_skb_data = bpf_helper_changes_pkt_data(func);
 				if (reload_skb_data) {
 					EMIT1(0x57); /* push %rdi */
 					jmp_offset += 22; /* pop, mov, sub, mov */

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -51,6 +51,9 @@
 #include "mlx4_en.h"
 #include "en_port.h"
 
+#define MLX4_EN_MAX_XDP_MTU ((int)(PAGE_SIZE - ETH_HLEN - (2 * VLAN_HLEN) - \
+				   XDP_PACKET_HEADROOM))
+
 int mlx4_en_setup_tc(struct net_device *dev, u8 up)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -2249,6 +2252,19 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 	free_netdev(dev);
 }
 
+static bool mlx4_en_check_xdp_mtu(struct net_device *dev, int mtu)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	if (mtu > MLX4_EN_MAX_XDP_MTU) {
+		en_err(priv, "mtu:%d > max:%d when XDP prog is attached\n",
+		       mtu, MLX4_EN_MAX_XDP_MTU);
+		return false;
+	}
+
+	return true;
+}
+
 static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -2258,11 +2274,10 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 	en_dbg(DRV, priv, "Change MTU called - current:%d new:%d\n",
 		 dev->mtu, new_mtu);
 
-	if (priv->tx_ring_num[TX_XDP] && MLX4_EN_EFF_MTU(new_mtu) > FRAG_SZ0) {
-		en_err(priv, "MTU size:%d requires frags but XDP running\n",
-		       new_mtu);
-		return -EOPNOTSUPP;
-	}
+	if (priv->tx_ring_num[TX_XDP] &&
+	    !mlx4_en_check_xdp_mtu(dev, new_mtu))
+		return -ENOTSUPP;
+
 	dev->mtu = new_mtu;
 
 	if (netif_running(dev)) {
@@ -2710,10 +2725,8 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 		return 0;
 	}
 
-	if (priv->num_frags > 1) {
-		en_err(priv, "Cannot set XDP if MTU requires multiple frags\n");
+	if (!mlx4_en_check_xdp_mtu(dev, dev->mtu))
 		return -EOPNOTSUPP;
-	}
 
 	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
 	if (!tmp)

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -96,7 +96,6 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
 	struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS];
 	const struct mlx4_en_frag_info *frag_info;
 	struct page *page;
-	dma_addr_t dma;
 	int i;
 
 	for (i = 0; i < priv->num_frags; i++) {
@@ -115,9 +114,10 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
 
 	for (i = 0; i < priv->num_frags; i++) {
 		frags[i] = ring_alloc[i];
-		dma = ring_alloc[i].dma + ring_alloc[i].page_offset;
+		frags[i].page_offset += priv->frag_info[i].rx_headroom;
+		rx_desc->data[i].addr = cpu_to_be64(frags[i].dma +
+						    frags[i].page_offset);
 		ring_alloc[i] = page_alloc[i];
-		rx_desc->data[i].addr = cpu_to_be64(dma);
 	}
 
 	return 0;
@@ -250,7 +250,8 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 
 	if (ring->page_cache.index > 0) {
 		frags[0] = ring->page_cache.buf[--ring->page_cache.index];
-		rx_desc->data[0].addr = cpu_to_be64(frags[0].dma);
+		rx_desc->data[0].addr = cpu_to_be64(frags[0].dma +
+						    frags[0].page_offset);
 		return 0;
 	}
 
@@ -889,6 +890,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		if (xdp_prog) {
 			struct xdp_buff xdp;
 			dma_addr_t dma;
+			void *orig_data;
 			u32 act;
 
 			dma = be64_to_cpu(rx_desc->data[0].addr);
@@ -896,11 +898,19 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 						priv->frag_info[0].frag_size,
 						DMA_FROM_DEVICE);
 
-			xdp.data = page_address(frags[0].page) +
-							frags[0].page_offset;
+			xdp.data_hard_start = page_address(frags[0].page);
+			xdp.data = xdp.data_hard_start + frags[0].page_offset;
 			xdp.data_end = xdp.data + length;
+			orig_data = xdp.data;
 
 			act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+			if (xdp.data != orig_data) {
+				length = xdp.data_end - xdp.data;
+				frags[0].page_offset = xdp.data -
+					xdp.data_hard_start;
+			}
+
 			switch (act) {
 			case XDP_PASS:
 				break;
@@ -1164,38 +1174,42 @@ static const int frag_sizes[] = {
 
 void mlx4_en_calc_rx_buf(struct net_device *dev)
 {
-	enum dma_data_direction dma_dir = PCI_DMA_FROMDEVICE;
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	int eff_mtu = MLX4_EN_EFF_MTU(dev->mtu);
-	int order = MLX4_EN_ALLOC_PREFER_ORDER;
-	u32 align = SMP_CACHE_BYTES;
-	int buf_size = 0;
 	int i = 0;
 
 	/* bpf requires buffers to be set up as 1 packet per page.
 	 * This only works when num_frags == 1.
 	 */
 	if (priv->tx_ring_num[TX_XDP]) {
-		dma_dir = PCI_DMA_BIDIRECTIONAL;
-		/* This will gain efficient xdp frame recycling at the expense
-		 * of more costly truesize accounting
+		priv->frag_info[0].order = 0;
+		priv->frag_info[0].frag_size = eff_mtu;
+		priv->frag_info[0].frag_prefix_size = 0;
+		/* This will gain efficient xdp frame recycling at the
+		 * expense of more costly truesize accounting
 		 */
-		align = PAGE_SIZE;
-		order = 0;
-	}
+		priv->frag_info[0].frag_stride = PAGE_SIZE;
+		priv->frag_info[0].dma_dir = PCI_DMA_BIDIRECTIONAL;
+		priv->frag_info[0].rx_headroom = XDP_PACKET_HEADROOM;
+		i = 1;
+	} else {
+		int buf_size = 0;
 
 		while (buf_size < eff_mtu) {
-		priv->frag_info[i].order = order;
+			priv->frag_info[i].order = MLX4_EN_ALLOC_PREFER_ORDER;
 			priv->frag_info[i].frag_size =
 				(eff_mtu > buf_size + frag_sizes[i]) ?
 					frag_sizes[i] : eff_mtu - buf_size;
 			priv->frag_info[i].frag_prefix_size = buf_size;
 			priv->frag_info[i].frag_stride =
-				ALIGN(priv->frag_info[i].frag_size, align);
-		priv->frag_info[i].dma_dir = dma_dir;
+				ALIGN(priv->frag_info[i].frag_size,
+				      SMP_CACHE_BYTES);
+			priv->frag_info[i].dma_dir = PCI_DMA_FROMDEVICE;
+			priv->frag_info[i].rx_headroom = 0;
 			buf_size += priv->frag_info[i].frag_size;
 			i++;
 		}
+	}
 
 	priv->num_frags = i;
 	priv->rx_skb_size = eff_mtu;

drivers/net/ethernet/mellanox/mlx4/en_tx.c

@@ -354,7 +354,7 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 	struct mlx4_en_rx_alloc frame = {
 		.page = tx_info->page,
 		.dma = tx_info->map0_dma,
-		.page_offset = 0,
+		.page_offset = XDP_PACKET_HEADROOM,
 		.page_size = PAGE_SIZE,
 	};
 
@@ -1132,7 +1132,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 	tx_info->page = frame->page;
 	frame->page = NULL;
 	tx_info->map0_dma = dma;
-	tx_info->map0_byte_count = length;
+	tx_info->map0_byte_count = PAGE_SIZE;
 	tx_info->nr_txbb = nr_txbb;
 	tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN);
 	tx_info->data_offset = (void *)data - (void *)tx_desc;
@@ -1141,9 +1141,10 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 	tx_info->linear = 1;
 	tx_info->inl = 0;
 
-	dma_sync_single_for_device(priv->ddev, dma, length, PCI_DMA_TODEVICE);
+	dma_sync_single_range_for_device(priv->ddev, dma, frame->page_offset,
+					 length, PCI_DMA_TODEVICE);
 
-	data->addr = cpu_to_be64(dma);
+	data->addr = cpu_to_be64(dma + frame->page_offset);
 	data->lkey = ring->mr_key;
 	dma_wmb();
 	data->byte_count = cpu_to_be32(length);

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -475,7 +475,8 @@ struct mlx4_en_frag_info {
 	u16 frag_prefix_size;
 	u32 frag_stride;
 	enum dma_data_direction dma_dir;
-	int order;
+	u16 order;
+	u16 rx_headroom;
 };
 
 #ifdef CONFIG_MLX4_EN_DCB

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -3183,6 +3183,11 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	bool reset, was_opened;
 	int i;
 
+	if (prog && prog->xdp_adjust_head) {
+		netdev_err(netdev, "Does not support bpf_xdp_adjust_head()\n");
+		return -EOPNOTSUPP;
+	}
+
 	mutex_lock(&priv->state_lock);
 
 	if ((netdev->features & NETIF_F_LRO) && prog) {

drivers/net/ethernet/netronome/nfp/nfp_net_common.c

@@ -2946,6 +2946,10 @@ static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog)
 	};
 	int err;
 
+	if (prog && prog->xdp_adjust_head) {
+		nn_err(nn, "Does not support bpf_xdp_adjust_head()\n");
+		return -EOPNOTSUPP;
+	}
 	if (!prog && !nn->xdp_prog)
 		return 0;
 	if (prog && nn->xdp_prog) {

drivers/net/ethernet/qlogic/qede/qede_main.c

@@ -2507,6 +2507,11 @@ static int qede_xdp_set(struct qede_dev *edev, struct bpf_prog *prog)
 {
 	struct qede_reload_args args;
 
+	if (prog && prog->xdp_adjust_head) {
+		DP_ERR(edev, "Does not support bpf_xdp_adjust_head()\n");
+		return -EOPNOTSUPP;
+	}
+
 	/* If we're called, there was already a bpf reference increment */
 	args.func = &qede_xdp_reload_func;
 	args.u.new_prog = prog;

include/linux/filter.h

@@ -406,7 +406,8 @@ struct bpf_prog {
 	u16			jited:1,	/* Is our filter JIT'ed? */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
-				dst_needed:1;	/* Do we need dst entry? */
+				dst_needed:1,	/* Do we need dst entry? */
+				xdp_adjust_head:1; /* Adjusting pkt head? */
 	kmemcheck_bitfield_end(meta);
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	u32			len;		/* Number of filter blocks */
@@ -440,6 +441,7 @@ struct bpf_skb_data_end {
 struct xdp_buff {
 	void *data;
 	void *data_end;
+	void *data_hard_start;
 };
 
 /* compute the linear packet data range [data, data_end) which
@@ -595,7 +597,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
-bool bpf_helper_changes_skb_data(void *func);
+bool bpf_helper_changes_pkt_data(void *func);
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);

include/uapi/linux/bpf.h

@@ -424,6 +424,12 @@ union bpf_attr {
  *     @len: length of header to be pushed in front
  *     @flags: Flags (unused for now)
  *     Return: 0 on success or negative error
+ *
+ * int bpf_xdp_adjust_head(xdp_md, delta)
+ *     Adjust the xdp_md.data by delta
+ *     @xdp_md: pointer to xdp_md
+ *     @delta: An positive/negative integer to be added to xdp_md.data
+ *     Return: 0 on success or negative on error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -469,7 +475,8 @@ union bpf_attr {
 	FN(csum_update),		\
 	FN(set_hash_invalid),		\
 	FN(get_numa_node_id),		\
-	FN(skb_change_head),
+	FN(skb_change_head),		\
+	FN(xdp_adjust_head),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -576,6 +583,8 @@ struct bpf_sock {
 	__u32 protocol;
 };
 
+#define XDP_PACKET_HEADROOM 256
+
 /* User return codes for XDP prog type.
  * A valid XDP program must return one of these defined values. All other
  * return codes are reserved for future use. Unknown return codes will result

kernel/bpf/core.c

@@ -1143,7 +1143,7 @@ struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog)
 	return prog;
 }
 
-bool __weak bpf_helper_changes_skb_data(void *func)
+bool __weak bpf_helper_changes_pkt_data(void *func)
 {
 	return false;
 }

kernel/bpf/syscall.c

@@ -579,6 +579,8 @@ static void fixup_bpf_calls(struct bpf_prog *prog)
 				prog->dst_needed = 1;
 			if (insn->imm == BPF_FUNC_get_prandom_u32)
 				bpf_user_rnd_init_once();
+			if (insn->imm == BPF_FUNC_xdp_adjust_head)
+				prog->xdp_adjust_head = 1;
 			if (insn->imm == BPF_FUNC_tail_call) {
 				/* mark bpf_tail_call as different opcode
 				 * to avoid conditional branch in

kernel/bpf/verifier.c

@@ -1216,7 +1216,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 		return -EINVAL;
 	}
 
-	changes_data = bpf_helper_changes_skb_data(fn->func);
+	changes_data = bpf_helper_changes_pkt_data(fn->func);
 
 	memset(&meta, 0, sizeof(meta));
 	meta.pkt_access = fn->pkt_access;

net/core/filter.c

@@ -2234,7 +2234,28 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-bool bpf_helper_changes_skb_data(void *func)
+BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset)
+{
+	void *data = xdp->data + offset;
+
+	if (unlikely(data < xdp->data_hard_start ||
+		     data > xdp->data_end - ETH_HLEN))
+		return -EINVAL;
+
+	xdp->data = data;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
+	.func		= bpf_xdp_adjust_head,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
+bool bpf_helper_changes_pkt_data(void *func)
 {
 	if (func == bpf_skb_vlan_push ||
 	    func == bpf_skb_vlan_pop ||
@@ -2244,7 +2265,8 @@ bool bpf_helper_changes_skb_data(void *func)
 	    func == bpf_skb_change_tail ||
 	    func == bpf_skb_pull_data ||
 	    func == bpf_l3_csum_replace ||
-	    func == bpf_l4_csum_replace)
+	    func == bpf_l4_csum_replace ||
+	    func == bpf_xdp_adjust_head)
 		return true;
 
 	return false;
@@ -2670,6 +2692,8 @@ xdp_func_proto(enum bpf_func_id func_id)
 		return &bpf_xdp_event_output_proto;
 	case BPF_FUNC_get_smp_processor_id:
 		return &bpf_get_smp_processor_id_proto;
+	case BPF_FUNC_xdp_adjust_head:
+		return &bpf_xdp_adjust_head_proto;
 	default:
 		return sk_filter_func_proto(func_id);
 	}

samples/bpf/Makefile

@@ -33,6 +33,7 @@ hostprogs-y += trace_event
 hostprogs-y += sampleip
 hostprogs-y += tc_l2_redirect
 hostprogs-y += lwt_len_hist
+hostprogs-y += xdp_tx_iptunnel
 
 test_lru_dist-objs := test_lru_dist.o libbpf.o
 sock_example-objs := sock_example.o libbpf.o
@@ -67,6 +68,7 @@ trace_event-objs := bpf_load.o libbpf.o trace_event_user.o
 sampleip-objs := bpf_load.o libbpf.o sampleip_user.o
 tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o
 lwt_len_hist-objs := bpf_load.o libbpf.o lwt_len_hist_user.o
+xdp_tx_iptunnel-objs := bpf_load.o libbpf.o xdp_tx_iptunnel_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -99,6 +101,7 @@ always += test_current_task_under_cgroup_kern.o
 always += trace_event_kern.o
 always += sampleip_kern.o
 always += lwt_len_hist_kern.o
+always += xdp_tx_iptunnel_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
@@ -129,6 +132,7 @@ HOSTLOADLIBES_trace_event += -lelf
 HOSTLOADLIBES_sampleip += -lelf
 HOSTLOADLIBES_tc_l2_redirect += -l elf
 HOSTLOADLIBES_lwt_len_hist += -l elf
+HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang

samples/bpf/bpf_helpers.h

@@ -57,6 +57,8 @@ static int (*bpf_skb_set_tunnel_opt)(void *ctx, void *md, int size) =
 	(void *) BPF_FUNC_skb_set_tunnel_opt;
 static unsigned long long (*bpf_get_prandom_u32)(void) =
 	(void *) BPF_FUNC_get_prandom_u32;
+static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
+	(void *) BPF_FUNC_xdp_adjust_head;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions

samples/bpf/bpf_load.c

@@ -12,6 +12,10 @@
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/perf_event.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <sys/types.h>
+#include <sys/socket.h>
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
@@ -450,3 +454,93 @@ struct ksym *ksym_search(long key)
 	/* out of range. return _stext */
 	return &syms[0];
 }
+
+int set_link_xdp_fd(int ifindex, int fd)
+{
+	struct sockaddr_nl sa;
+	int sock, seq = 0, len, ret = -1;
+	char buf[4096];
+	struct nlattr *nla, *nla_xdp;
+	struct {
+		struct nlmsghdr  nh;
+		struct ifinfomsg ifinfo;
+		char             attrbuf[64];
+	} req;
+	struct nlmsghdr *nh;
+	struct nlmsgerr *err;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		printf("open netlink socket: %s\n", strerror(errno));
+		return -1;
+	}
+
+	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+		printf("bind to netlink: %s\n", strerror(errno));
+		goto cleanup;
+	}
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type = RTM_SETLINK;
+	req.nh.nlmsg_pid = 0;
+	req.nh.nlmsg_seq = ++seq;
+	req.ifinfo.ifi_family = AF_UNSPEC;
+	req.ifinfo.ifi_index = ifindex;
+	nla = (struct nlattr *)(((char *)&req)
+				+ NLMSG_ALIGN(req.nh.nlmsg_len));
+	nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
+
+	nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN);
+	nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
+	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+	nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len;
+
+	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		printf("send to netlink: %s\n", strerror(errno));
+		goto cleanup;
+	}
+
+	len = recv(sock, buf, sizeof(buf), 0);
+	if (len < 0) {
+		printf("recv from netlink: %s\n", strerror(errno));
+		goto cleanup;
+	}
+
+	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+	     nh = NLMSG_NEXT(nh, len)) {
+		if (nh->nlmsg_pid != getpid()) {
+			printf("Wrong pid %d, expected %d\n",
+			       nh->nlmsg_pid, getpid());
+			goto cleanup;
+		}
+		if (nh->nlmsg_seq != seq) {
+			printf("Wrong seq %d, expected %d\n",
+			       nh->nlmsg_seq, seq);
+			goto cleanup;
+		}
+		switch (nh->nlmsg_type) {
+		case NLMSG_ERROR:
+			err = (struct nlmsgerr *)NLMSG_DATA(nh);
+			if (!err->error)
+				continue;
+			printf("nlmsg error %s\n", strerror(-err->error));
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}

samples/bpf/bpf_load.h

@@ -31,4 +31,5 @@ struct ksym {
 
 int load_kallsyms(void);
 struct ksym *ksym_search(long key);
+int set_link_xdp_fd(int ifindex, int fd);
 #endif

samples/bpf/xdp1_user.c

@@ -5,111 +5,18 @@
  * License as published by the Free Software Foundation.
  */
 #include <linux/bpf.h>
-#include <linux/netlink.h>
-#include <linux/rtnetlink.h>
 #include <assert.h>
 #include <errno.h>
 #include <signal.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <sys/socket.h>
 #include <unistd.h>
 
 #include "bpf_load.h"
 #include "bpf_util.h"
 #include "libbpf.h"
 
-static int set_link_xdp_fd(int ifindex, int fd)
-{
-	struct sockaddr_nl sa;
-	int sock, seq = 0, len, ret = -1;
-	char buf[4096];
-	struct nlattr *nla, *nla_xdp;
-	struct {
-		struct nlmsghdr  nh;
-		struct ifinfomsg ifinfo;
-		char             attrbuf[64];
-	} req;
-	struct nlmsghdr *nh;
-	struct nlmsgerr *err;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.nl_family = AF_NETLINK;
-
-	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
-	if (sock < 0) {
-		printf("open netlink socket: %s\n", strerror(errno));
-		return -1;
-	}
-
-	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
-		printf("bind to netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	memset(&req, 0, sizeof(req));
-	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
-	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
-	req.nh.nlmsg_type = RTM_SETLINK;
-	req.nh.nlmsg_pid = 0;
-	req.nh.nlmsg_seq = ++seq;
-	req.ifinfo.ifi_family = AF_UNSPEC;
-	req.ifinfo.ifi_index = ifindex;
-	nla = (struct nlattr *)(((char *)&req)
-				+ NLMSG_ALIGN(req.nh.nlmsg_len));
-	nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
-
-	nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN);
-	nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
-	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
-	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len;
-
-	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
-	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
-		printf("send to netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	len = recv(sock, buf, sizeof(buf), 0);
-	if (len < 0) {
-		printf("recv from netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
-	     nh = NLMSG_NEXT(nh, len)) {
-		if (nh->nlmsg_pid != getpid()) {
-			printf("Wrong pid %d, expected %d\n",
-			       nh->nlmsg_pid, getpid());
-			goto cleanup;
-		}
-		if (nh->nlmsg_seq != seq) {
-			printf("Wrong seq %d, expected %d\n",
-			       nh->nlmsg_seq, seq);
-			goto cleanup;
-		}
-		switch (nh->nlmsg_type) {
-		case NLMSG_ERROR:
-			err = (struct nlmsgerr *)NLMSG_DATA(nh);
-			if (!err->error)
-				continue;
-			printf("nlmsg error %s\n", strerror(-err->error));
-			goto cleanup;
-		case NLMSG_DONE:
-			break;
-		}
-	}
-
-	ret = 0;
-
-cleanup:
-	close(sock);
-	return ret;
-}
-
 static int ifindex;
 
 static void int_exit(int sig)

samples/bpf/xdp_tx_iptunnel_common.h

+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _SAMPLES_BPF_XDP_TX_IPTNL_COMMON_H
+#define _SAMPLES_BPF_XDP_TX_IPTNL_COMMON_H
+
+#include <linux/types.h>
+
+#define MAX_IPTNL_ENTRIES 256U
+
+struct vip {
+	union {
+		__u32 v6[4];
+		__u32 v4;
+	} daddr;
+	__u16 dport;
+	__u16 family;
+	__u8 protocol;
+};
+
+struct iptnl_info {
+	union {
+		__u32 v6[4];
+		__u32 v4;
+	} saddr;
+	union {
+		__u32 v6[4];
+		__u32 v4;
+	} daddr;
+	__u16 family;
+	__u8 dmac[6];
+};
+
+#endif

samples/bpf/xdp_tx_iptunnel_kern.c

+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program shows how to use bpf_xdp_adjust_head() by
+ * encapsulating the incoming packet in an IPv4/v6 header
+ * and then XDP_TX it out.
+ */
+#include <uapi/linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include "bpf_helpers.h"
+#include "xdp_tx_iptunnel_common.h"
+
+struct bpf_map_def SEC("maps") rxcnt = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64),
+	.max_entries = 256,
+};
+
+struct bpf_map_def SEC("maps") vip2tnl = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct vip),
+	.value_size = sizeof(struct iptnl_info),
+	.max_entries = MAX_IPTNL_ENTRIES,
+};
+
+static __always_inline void count_tx(u32 protocol)
+{
+	u64 *rxcnt_count;
+
+	rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
+	if (rxcnt_count)
+		*rxcnt_count += 1;
+}
+
+static __always_inline int get_dport(void *trans_data, void *data_end,
+				     u8 protocol)
+{
+	struct tcphdr *th;
+	struct udphdr *uh;
+
+	switch (protocol) {
+	case IPPROTO_TCP:
+		th = (struct tcphdr *)trans_data;
+		if (th + 1 > data_end)
+			return -1;
+		return th->dest;
+	case IPPROTO_UDP:
+		uh = (struct udphdr *)trans_data;
+		if (uh + 1 > data_end)
+			return -1;
+		return uh->dest;
+	default:
+		return 0;
+	}
+}
+
+static __always_inline void set_ethhdr(struct ethhdr *new_eth,
+				       const struct ethhdr *old_eth,
+				       const struct iptnl_info *tnl,
+				       __be16 h_proto)
+{
+	memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
+	memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
+	new_eth->h_proto = h_proto;
+}
+
+static __always_inline int handle_ipv4(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct iphdr *iph = data + sizeof(struct ethhdr);
+	u16 *next_iph_u16;
+	u16 payload_len;
+	struct vip vip = {};
+	int dport;
+	u32 csum = 0;
+	int i;
+
+	if (iph + 1 > data_end)
+		return XDP_DROP;
+
+	dport = get_dport(iph + 1, data_end, iph->protocol);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = iph->protocol;
+	vip.family = AF_INET;
+	vip.daddr.v4 = iph->daddr;
+	vip.dport = dport;
+	payload_len = ntohs(iph->tot_len);
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v4-in-v4 */
+	if (!tnl || tnl->family != AF_INET)
+		return XDP_PASS;
+
+	/* The vip key is found.  Add an IP header and send it out */
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
+		return XDP_DROP;
+
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+
+	new_eth = data;
+	iph = data + sizeof(*new_eth);
+	old_eth = data + sizeof(*iph);
+
+	if (new_eth + 1 > data_end ||
+	    old_eth + 1 > data_end ||
+	    iph + 1 > data_end)
+		return XDP_DROP;
+
+	set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IP));
+
+	iph->version = 4;
+	iph->ihl = sizeof(*iph) >> 2;
+	iph->frag_off =	0;
+	iph->protocol = IPPROTO_IPIP;
+	iph->check = 0;
+	iph->tos = 0;
+	iph->tot_len = htons(payload_len + sizeof(*iph));
+	iph->daddr = tnl->daddr.v4;
+	iph->saddr = tnl->saddr.v4;
+	iph->ttl = 8;
+
+	next_iph_u16 = (u16 *)iph;
+#pragma clang loop unroll(full)
+	for (i = 0; i < sizeof(*iph) >> 1; i++)
+		csum += *next_iph_u16++;
+
+	iph->check = ~((csum & 0xffff) + (csum >> 16));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+static __always_inline int handle_ipv6(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct ipv6hdr *ip6h = data + sizeof(struct ethhdr);
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+
+	if (ip6h + 1 > data_end)
+		return XDP_DROP;
+
+	dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = ip6h->nexthdr;
+	vip.family = AF_INET6;
+	memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
+	vip.dport = dport;
+	payload_len = ip6h->payload_len;
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v6-in-v6 */
+	if (!tnl || tnl->family != AF_INET6)
+		return XDP_PASS;
+
+	/* The vip key is found.  Add an IP header and send it out */
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
+		return XDP_DROP;
+
+	data = (void *)(long)xdp->data;
+	data_end = (void *)(long)xdp->data_end;
+
+	new_eth = data;
+	ip6h = data + sizeof(*new_eth);
+	old_eth = data + sizeof(*ip6h);
+
+	if (new_eth + 1 > data_end ||
+	    old_eth + 1 > data_end ||
+	    ip6h + 1 > data_end)
+		return XDP_DROP;
+
+	set_ethhdr(new_eth, old_eth, tnl, htons(ETH_P_IPV6));
+
+	ip6h->version = 6;
+	ip6h->priority = 0;
+	memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+	ip6h->payload_len = htons(ntohs(payload_len) + sizeof(*ip6h));
+	ip6h->nexthdr = IPPROTO_IPV6;
+	ip6h->hop_limit = 8;
+	memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
+	memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+SEC("xdp_tx_iptunnel")
+int _xdp_tx_iptunnel(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eth = data;
+	__u16 h_proto;
+
+	if (eth + 1 > data_end)
+		return XDP_DROP;
+
+	h_proto = eth->h_proto;
+
+	if (h_proto == htons(ETH_P_IP))
+		return handle_ipv4(xdp);
+	else if (h_proto == htons(ETH_P_IPV6))
+
+		return handle_ipv6(xdp);
+	else
+		return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";

samples/bpf/xdp_tx_iptunnel_user.c

+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/bpf.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <arpa/inet.h>
+#include <netinet/ether.h>
+#include <unistd.h>
+#include <time.h>
+#include "bpf_load.h"
+#include "libbpf.h"
+#include "bpf_util.h"
+#include "xdp_tx_iptunnel_common.h"
+
+#define STATS_INTERVAL_S 2U
+
+static int ifindex = -1;
+
+static void int_exit(int sig)
+{
+	if (ifindex > -1)
+		set_link_xdp_fd(ifindex, -1);
+	exit(0);
+}
+
+/* simple per-protocol drop counter
+ */
+static void poll_stats(unsigned int kill_after_s)
+{
+	const unsigned int nr_protos = 256;
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	time_t started_at = time(NULL);
+	__u64 values[nr_cpus], prev[nr_protos][nr_cpus];
+	__u32 proto;
+	int i;
+
+	memset(prev, 0, sizeof(prev));
+
+	while (!kill_after_s || time(NULL) - started_at <= kill_after_s) {
+		sleep(STATS_INTERVAL_S);
+
+		for (proto = 0; proto < nr_protos; proto++) {
+			__u64 sum = 0;
+
+			assert(bpf_lookup_elem(map_fd[0], &proto, values) == 0);
+			for (i = 0; i < nr_cpus; i++)
+				sum += (values[i] - prev[proto][i]);
+
+			if (sum)
+				printf("proto %u: sum:%10llu pkts, rate:%10llu pkts/s\n",
+				       proto, sum, sum / STATS_INTERVAL_S);
+			memcpy(prev[proto], values, sizeof(values));
+		}
+	}
+}
+
+static void usage(const char *cmd)
+{
+	printf("Start a XDP prog which encapsulates incoming packets\n"
+	       "in an IPv4/v6 header and XDP_TX it out.  The dst <VIP:PORT>\n"
+	       "is used to select packets to encapsulate\n\n");
+	printf("Usage: %s [...]\n", cmd);
+	printf("    -i <ifindex> Interface Index\n");
+	printf("    -a <vip-service-address> IPv4 or IPv6\n");
+	printf("    -p <vip-service-port> A port range (e.g. 433-444) is also allowed\n");
+	printf("    -s <source-ip> Used in the IPTunnel header\n");
+	printf("    -d <dest-ip> Used in the IPTunnel header\n");
+	printf("    -m <dest-MAC> Used in sending the IP Tunneled pkt\n");
+	printf("    -T <stop-after-X-seconds> Default: 0 (forever)\n");
+	printf("    -P <IP-Protocol> Default is TCP\n");
+	printf("    -h Display this help\n");
+}
+
+static int parse_ipstr(const char *ipstr, unsigned int *addr)
+{
+	if (inet_pton(AF_INET6, ipstr, addr) == 1) {
+		return AF_INET6;
+	} else if (inet_pton(AF_INET, ipstr, addr) == 1) {
+		addr[1] = addr[2] = addr[3] = 0;
+		return AF_INET;
+	}
+
+	fprintf(stderr, "%s is an invalid IP\n", ipstr);
+	return AF_UNSPEC;
+}
+
+static int parse_ports(const char *port_str, int *min_port, int *max_port)
+{
+	char *end;
+	long tmp_min_port;
+	long tmp_max_port;
+
+	tmp_min_port = strtol(optarg, &end, 10);
+	if (tmp_min_port < 1 || tmp_min_port > 65535) {
+		fprintf(stderr, "Invalid port(s):%s\n", optarg);
+		return 1;
+	}
+
+	if (*end == '-') {
+		end++;
+		tmp_max_port = strtol(end, NULL, 10);
+		if (tmp_max_port < 1 || tmp_max_port > 65535) {
+			fprintf(stderr, "Invalid port(s):%s\n", optarg);
+			return 1;
+		}
+	} else {
+		tmp_max_port = tmp_min_port;
+	}
+
+	if (tmp_min_port > tmp_max_port) {
+		fprintf(stderr, "Invalid port(s):%s\n", optarg);
+		return 1;
+	}
+
+	if (tmp_max_port - tmp_min_port + 1 > MAX_IPTNL_ENTRIES) {
+		fprintf(stderr, "Port range (%s) is larger than %u\n",
+			port_str, MAX_IPTNL_ENTRIES);
+		return 1;
+	}
+	*min_port = tmp_min_port;
+	*max_port = tmp_max_port;
+
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	unsigned char opt_flags[256] = {};
+	unsigned int kill_after_s = 0;
+	const char *optstr = "i:a:p:s:d:m:T:P:h";
+	int min_port = 0, max_port = 0;
+	struct iptnl_info tnl = {};
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	struct vip vip = {};
+	char filename[256];
+	int opt;
+	int i;
+
+	tnl.family = AF_UNSPEC;
+	vip.protocol = IPPROTO_TCP;
+
+	for (i = 0; i < strlen(optstr); i++)
+		if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z')
+			opt_flags[(unsigned char)optstr[i]] = 1;
+
+	while ((opt = getopt(argc, argv, optstr)) != -1) {
+		unsigned short family;
+		unsigned int *v6;
+
+		switch (opt) {
+		case 'i':
+			ifindex = atoi(optarg);
+			break;
+		case 'a':
+			vip.family = parse_ipstr(optarg, vip.daddr.v6);
+			if (vip.family == AF_UNSPEC)
+				return 1;
+			break;
+		case 'p':
+			if (parse_ports(optarg, &min_port, &max_port))
+				return 1;
+			break;
+		case 'P':
+			vip.protocol = atoi(optarg);
+			break;
+		case 's':
+		case 'd':
+			if (opt == 's')
+				v6 = tnl.saddr.v6;
+			else
+				v6 = tnl.daddr.v6;
+
+			family = parse_ipstr(optarg, v6);
+			if (family == AF_UNSPEC)
+				return 1;
+			if (tnl.family == AF_UNSPEC) {
+				tnl.family = family;
+			} else if (tnl.family != family) {
+				fprintf(stderr,
+					"The IP version of the src and dst addresses used in the IP encapsulation does not match\n");
+				return 1;
+			}
+			break;
+		case 'm':
+			if (!ether_aton_r(optarg,
+					  (struct ether_addr *)tnl.dmac)) {
+				fprintf(stderr, "Invalid mac address:%s\n",
+					optarg);
+				return 1;
+			}
+			break;
+		case 'T':
+			kill_after_s = atoi(optarg);
+			break;
+		default:
+			usage(argv[0]);
+			return 1;
+		}
+		opt_flags[opt] = 0;
+	}
+
+	for (i = 0; i < strlen(optstr); i++) {
+		if (opt_flags[(unsigned int)optstr[i]]) {
+			fprintf(stderr, "Missing argument -%c\n", optstr[i]);
+			usage(argv[0]);
+			return 1;
+		}
+	}
+
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)");
+		return 1;
+	}
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	if (!prog_fd[0]) {
+		printf("load_bpf_file: %s\n", strerror(errno));
+		return 1;
+	}
+
+	signal(SIGINT, int_exit);
+
+	while (min_port <= max_port) {
+		vip.dport = htons(min_port++);
+		if (bpf_update_elem(map_fd[1], &vip, &tnl, BPF_NOEXIST)) {
+			perror("bpf_update_elem(&vip2tnl)");
+			return 1;
+		}
+	}
+
+	if (set_link_xdp_fd(ifindex, prog_fd[0]) < 0) {
+		printf("link set xdp fd failed\n");
+		return 1;
+	}
+
+	poll_stats(kill_after_s);
+
+	set_link_xdp_fd(ifindex, -1);
+
+	return 0;
+}