3 files changed, 35 insertions, 17 deletions

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 0a5dca2b2b3f..40085afd9160 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -126,8 +126,8 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 	if (likely(!xdp_buff_has_frags(xdp)))
 		goto out;
 
-	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
-		list_del(&pos->xskb_list_node);
+	list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
+		list_del(&pos->list_node);
 		xp_free(pos);
 	}
 
@@ -140,7 +140,7 @@ static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
 {
 	struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp);
 
-	list_add_tail(&frag->xskb_list_node, &frag->pool->xskb_list);
+	list_add_tail(&frag->list_node, &frag->pool->xskb_list);
 }
 
 static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
@@ -150,9 +150,9 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
 	struct xdp_buff_xsk *frag;
 
 	frag = list_first_entry_or_null(&xskb->pool->xskb_list,
-					struct xdp_buff_xsk, xskb_list_node);
+					struct xdp_buff_xsk, list_node);
 	if (frag) {
-		list_del(&frag->xskb_list_node);
+		list_del(&frag->list_node);
 		ret = &frag->xdp;
 	}
 
@@ -163,7 +163,7 @@ static inline void xsk_buff_del_tail(struct xdp_buff *tail)
 {
 	struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp);
 
-	list_del(&xskb->xskb_list_node);
+	list_del(&xskb->list_node);
 }
 
 static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
@@ -172,7 +172,7 @@ static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
 	struct xdp_buff_xsk *frag;
 
 	frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk,
-			       xskb_list_node);
+			       list_node);
 	return &frag->xdp;
 }
 
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index bacb33f1e3e5..bb03cee716b3 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -28,9 +28,7 @@ struct xdp_buff_xsk {
 	dma_addr_t dma;
 	dma_addr_t frame_dma;
 	struct xsk_buff_pool *pool;
-	u64 orig_addr;
-	struct list_head free_list_node;
-	struct list_head xskb_list_node;
+	struct list_head list_node;
 };
 
 #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
@@ -78,6 +76,7 @@ struct xsk_buff_pool {
 	u32 chunk_size;
 	u32 chunk_shift;
 	u32 frame_len;
+	u32 xdp_zc_max_segs;
 	u8 tx_metadata_len; /* inherited from umem */
 	u8 cached_need_wakeup;
 	bool uses_need_wakeup;
@@ -120,7 +119,6 @@ void xp_free(struct xdp_buff_xsk *xskb);
 static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool,
 				     u64 addr)
 {
-	xskb->orig_addr = addr;
 	xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom;
 }
 
@@ -222,14 +220,19 @@ static inline void xp_release(struct xdp_buff_xsk *xskb)
 		xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb;
 }
 
-static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb)
+static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb,
+				struct xsk_buff_pool *pool)
 {
-	u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start;
+	u64 orig_addr = xskb->xdp.data - pool->addrs;
+	u64 offset;
 
-	offset += xskb->pool->headroom;
-	if (!xskb->pool->unaligned)
-		return xskb->orig_addr + offset;
-	return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
+	if (!pool->unaligned)
+		return orig_addr;
+
+	offset = xskb->xdp.data - xskb->xdp.data_hard_start;
+	orig_addr -= offset;
+	offset += pool->headroom;
+	return orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
 }
 
 static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool)
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 506ba9c80e83..8516c1ccd57a 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1293,6 +1293,19 @@ enum netkit_mode {
 	NETKIT_L3,
 };
 
+/* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to
+ * the BPF program if attached. This also means the latter can
+ * consume the two fields if they were populated earlier.
+ *
+ * NETKIT_SCRUB_DEFAULT zeroes skb->{mark,priority} fields before
+ * invoking the attached BPF program when the peer device resides
+ * in a different network namespace. This is the default behavior.
+ */
+enum netkit_scrub {
+	NETKIT_SCRUB_NONE,
+	NETKIT_SCRUB_DEFAULT,
+};
+
 enum {
 	IFLA_NETKIT_UNSPEC,
 	IFLA_NETKIT_PEER_INFO,
@@ -1300,6 +1313,8 @@ enum {
 	IFLA_NETKIT_POLICY,
 	IFLA_NETKIT_PEER_POLICY,
 	IFLA_NETKIT_MODE,
+	IFLA_NETKIT_SCRUB,
+	IFLA_NETKIT_PEER_SCRUB,
 	__IFLA_NETKIT_MAX,
 };
 #define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)