diff mbox series

[v7,bpf-next,08/14] bpf: add multi-buff support to the bpf_xdp_adjust_tail() API

Message ID 6da4e8a314e7fbdeb0a6790a920a4ae554fb3742.1616179034.git.lorenzo@kernel.org (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series mvneta: introduce XDP multi-buffer support | 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 6 maintainers not CCed: yhs@fb.com kpsingh@kernel.org hawk@kernel.org andrii@kernel.org kafai@fb.com songliubraving@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 success Errors and warnings before: 6941 this patch: 6941
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 85 lines checked
netdev/build_allmodconfig_warn success Errors and warnings before: 7155 this patch: 7155
netdev/header_inline success Link

Commit Message

lorenzo@kernel.org March 19, 2021, 9:47 p.m. UTC
From: Eelco Chaudron <echaudro@redhat.com>

This change adds support for tail growing and shrinking for XDP multi-buff.

Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 include/net/xdp.h |  5 ++++
 net/core/filter.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 68 insertions(+)
diff mbox series

Patch

diff --git a/include/net/xdp.h b/include/net/xdp.h
index 8be1b5e5a08a..19cd6642e087 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -157,6 +157,11 @@  static inline void xdp_set_frag_size(skb_frag_t *frag, u32 size)
 	frag->bv_len = size;
 }
 
+static inline unsigned int xdp_get_frag_tailroom(const skb_frag_t *frag)
+{
+	return PAGE_SIZE - xdp_get_frag_size(frag) - xdp_get_frag_offset(frag);
+}
+
 struct xdp_frame {
 	void *data;
 	u16 len;
diff --git a/net/core/filter.c b/net/core/filter.c
index 10dac9dd5086..18b2c9bacba1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3855,11 +3855,74 @@  static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static int bpf_xdp_mb_adjust_tail(struct xdp_buff *xdp, int offset)
+{
+	struct xdp_shared_info *xdp_sinfo = xdp_get_shared_info_from_buff(xdp);
+
+	if (unlikely(xdp_sinfo->nr_frags == 0))
+		return -EINVAL;
+
+	if (offset >= 0) {
+		skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags - 1];
+		int size;
+
+		if (unlikely(offset > xdp_get_frag_tailroom(frag)))
+			return -EINVAL;
+
+		size = xdp_get_frag_size(frag);
+		memset(xdp_get_frag_address(frag) + size, 0, offset);
+		xdp_set_frag_size(frag, size + offset);
+		xdp_sinfo->data_length += offset;
+	} else {
+		int i, frags_to_free = 0;
+
+		offset = abs(offset);
+
+		if (unlikely(offset > ((int)(xdp->data_end - xdp->data) +
+				       xdp_sinfo->data_length -
+				       ETH_HLEN)))
+			return -EINVAL;
+
+		for (i = xdp_sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) {
+			skb_frag_t *frag = &xdp_sinfo->frags[i];
+			int size = xdp_get_frag_size(frag);
+			int shrink = min_t(int, offset, size);
+
+			offset -= shrink;
+			if (likely(size - shrink > 0)) {
+				/* When updating the final fragment we have
+				 * to adjust the data_length in line.
+				 */
+				xdp_sinfo->data_length -= shrink;
+				xdp_set_frag_size(frag, size - shrink);
+				break;
+			}
+
+			/* When we free the fragments,
+			 * xdp_return_frags_from_buff() will take care
+			 * of updating the xdp share info data_length.
+			 */
+			frags_to_free++;
+		}
+
+		if (unlikely(frags_to_free))
+			xdp_return_num_frags_from_buff(xdp, frags_to_free);
+
+		if (unlikely(offset > 0))
+			xdp->data_end -= offset;
+	}
+
+	return 0;
+}
+
 BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
 {
 	void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */
 	void *data_end = xdp->data_end + offset;
 
+	if (unlikely(xdp->mb))
+		return bpf_xdp_mb_adjust_tail(xdp, offset);
+
 	/* Notice that xdp_data_hard_end have reserved some tailroom */
 	if (unlikely(data_end > data_hard_end))
 		return -EINVAL;