bpf: xdp: Allow head adjustment in XDP prog

This patch allows XDP prog to extend/remove the packet
data at the head (like adding or removing header).  It is
done by adding a new XDP helper bpf_xdp_adjust_head().

It also renames bpf_helper_changes_skb_data() to
bpf_helper_changes_pkt_data() to better reflect
that XDP prog does not work on skb.

This patch adds one "xdp_adjust_head" bit to bpf_prog for the
XDP-capable driver to check if the XDP prog requires
bpf_xdp_adjust_head() support.  The driver can then decide
to error out during XDP_SETUP_PROG.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/powerpc/net/bpf_jit_comp64.c

@@ -766,7 +766,7 @@ emit_clear:
 			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 @@ emit_clear:
 			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

@@ -2686,6 +2686,11 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 	int err;
 	int i;
 
+	if (prog && prog->xdp_adjust_head) {
+		en_err(priv, "Does not support bpf_xdp_adjust_head()\n");
+		return -EOPNOTSUPP;
+	}
+
 	xdp_ring_num = prog ? priv->rx_ring_num : 0;
 
 	/* No need to reconfigure buffers when simply swapping the

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);
 	}