net: xdp: introduce bpf_xdp_pointer utility routine

Similar to skb_header_pointer, introduce bpf_xdp_pointer utility routine
to return a pointer to a given position in the xdp_buff if the requested
area (offset + len) is contained in a contiguous memory area otherwise it
will be copied in a bounce buffer provided by the caller.
Similar to the tc counterpart, introduce the two following xdp helpers:
- bpf_xdp_load_bytes
- bpf_xdp_store_bytes

Reviewed-by: Eelco Chaudron <echaudro@redhat.com>
Acked-by: Toke Hoiland-Jorgensen <toke@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/r/ab285c1efdd5b7a9d361348b1e7d3ef49f6382b3.1642758637.git.lorenzo@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 138 insertions, 38 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index e4ce138bf925..945ccaaab3cb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3839,6 +3839,138 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
+			     void *buf, unsigned long len, bool flush)
+{
+	unsigned long ptr_len, ptr_off = 0;
+	skb_frag_t *next_frag, *end_frag;
+	struct skb_shared_info *sinfo;
+	void *src, *dst;
+	u8 *ptr_buf;
+
+	if (likely(xdp->data_end - xdp->data >= off + len)) {
+		src = flush ? buf : xdp->data + off;
+		dst = flush ? xdp->data + off : buf;
+		memcpy(dst, src, len);
+		return;
+	}
+
+	sinfo = xdp_get_shared_info_from_buff(xdp);
+	end_frag = &sinfo->frags[sinfo->nr_frags];
+	next_frag = &sinfo->frags[0];
+
+	ptr_len = xdp->data_end - xdp->data;
+	ptr_buf = xdp->data;
+
+	while (true) {
+		if (off < ptr_off + ptr_len) {
+			unsigned long copy_off = off - ptr_off;
+			unsigned long copy_len = min(len, ptr_len - copy_off);
+
+			src = flush ? buf : ptr_buf + copy_off;
+			dst = flush ? ptr_buf + copy_off : buf;
+			memcpy(dst, src, copy_len);
+
+			off += copy_len;
+			len -= copy_len;
+			buf += copy_len;
+		}
+
+		if (!len || next_frag == end_frag)
+			break;
+
+		ptr_off += ptr_len;
+		ptr_buf = skb_frag_address(next_frag);
+		ptr_len = skb_frag_size(next_frag);
+		next_frag++;
+	}
+}
+
+static void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	u32 size = xdp->data_end - xdp->data;
+	void *addr = xdp->data;
+	int i;
+
+	if (unlikely(offset > 0xffff || len > 0xffff))
+		return ERR_PTR(-EFAULT);
+
+	if (offset + len > xdp_get_buff_len(xdp))
+		return ERR_PTR(-EINVAL);
+
+	if (offset < size) /* linear area */
+		goto out;
+
+	offset -= size;
+	for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */
+		u32 frag_size = skb_frag_size(&sinfo->frags[i]);
+
+		if  (offset < frag_size) {
+			addr = skb_frag_address(&sinfo->frags[i]);
+			size = frag_size;
+			break;
+		}
+		offset -= frag_size;
+	}
+out:
+	return offset + len < size ? addr + offset : NULL;
+}
+
+BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset,
+	   void *, buf, u32, len)
+{
+	void *ptr;
+
+	ptr = bpf_xdp_pointer(xdp, offset, len);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	if (!ptr)
+		bpf_xdp_copy_buf(xdp, offset, buf, len, false);
+	else
+		memcpy(buf, ptr, len);
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_load_bytes_proto = {
+	.func		= bpf_xdp_load_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset,
+	   void *, buf, u32, len)
+{
+	void *ptr;
+
+	ptr = bpf_xdp_pointer(xdp, offset, len);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	if (!ptr)
+		bpf_xdp_copy_buf(xdp, offset, buf, len, true);
+	else
+		memcpy(ptr, buf, len);
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_store_bytes_proto = {
+	.func		= bpf_xdp_store_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
 static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
@@ -4677,48 +4809,12 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = {
 };
 #endif
 
-static unsigned long bpf_xdp_copy(void *dst_buff, const void *ctx,
+static unsigned long bpf_xdp_copy(void *dst, const void *ctx,
 				  unsigned long off, unsigned long len)
 {
 	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
-	unsigned long ptr_len, ptr_off = 0;
-	skb_frag_t *next_frag, *end_frag;
-	struct skb_shared_info *sinfo;
-	u8 *ptr_buf;
-
-	if (likely(xdp->data_end - xdp->data >= off + len)) {
-		memcpy(dst_buff, xdp->data + off, len);
-		return 0;
-	}
-
-	sinfo = xdp_get_shared_info_from_buff(xdp);
-	end_frag = &sinfo->frags[sinfo->nr_frags];
-	next_frag = &sinfo->frags[0];
-
-	ptr_len = xdp->data_end - xdp->data;
-	ptr_buf = xdp->data;
-
-	while (true) {
-		if (off < ptr_off + ptr_len) {
-			unsigned long copy_off = off - ptr_off;
-			unsigned long copy_len = min(len, ptr_len - copy_off);
-
-			memcpy(dst_buff, ptr_buf + copy_off, copy_len);
-
-			off += copy_len;
-			len -= copy_len;
-			dst_buff += copy_len;
-		}
-
-		if (!len || next_frag == end_frag)
-			break;
-
-		ptr_off += ptr_len;
-		ptr_buf = skb_frag_address(next_frag);
-		ptr_len = skb_frag_size(next_frag);
-		next_frag++;
-	}
 
+	bpf_xdp_copy_buf(xdp, off, dst, len, false);
 	return 0;
 }
 
@@ -7660,6 +7756,10 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_adjust_tail_proto;
 	case BPF_FUNC_xdp_get_buff_len:
 		return &bpf_xdp_get_buff_len_proto;
+	case BPF_FUNC_xdp_load_bytes:
+		return &bpf_xdp_load_bytes_proto;
+	case BPF_FUNC_xdp_store_bytes:
+		return &bpf_xdp_store_bytes_proto;
 	case BPF_FUNC_fib_lookup:
 		return &bpf_xdp_fib_lookup_proto;
 	case BPF_FUNC_check_mtu: