Adding upstream version 6.8.9.upstream/6.8.9

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 92 insertions, 10 deletions

diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 06cead2b8..caa340134 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -148,6 +148,11 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
 	return 0;
 }
 
+#define XDP_UMEM_FLAGS_VALID ( \
+		XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
+		XDP_UMEM_TX_SW_CSUM | \
+	0)
+
 static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 {
 	bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
@@ -167,7 +172,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 		return -EINVAL;
 	}
 
-	if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG)
+	if (mr->flags & ~XDP_UMEM_FLAGS_VALID)
 		return -EINVAL;
 
 	if (!unaligned_chunks && !is_power_of_2(chunk_size))
@@ -199,6 +204,9 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
 
+	if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
+		return -EINVAL;
+
 	umem->size = size;
 	umem->headroom = headroom;
 	umem->chunk_size = chunk_size;
@@ -207,6 +215,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
+	umem->tx_metadata_len = mr->tx_metadata_len;
 
 	INIT_LIST_HEAD(&umem->xsk_dma_list);
 	refcount_set(&umem->users, 1);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index da1582de6..7d1c0986f 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -575,6 +575,13 @@ static u32 xsk_get_num_desc(struct sk_buff *skb)
 
 static void xsk_destruct_skb(struct sk_buff *skb)
 {
+	struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta;
+
+	if (compl->tx_timestamp) {
+		/* sw completion timestamp, not a real one */
+		*compl->tx_timestamp = ktime_get_tai_fast_ns();
+	}
+
 	xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb));
 	sock_wfree(skb);
 }
@@ -659,8 +666,10 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				     struct xdp_desc *desc)
 {
+	struct xsk_tx_metadata *meta = NULL;
 	struct net_device *dev = xs->dev;
 	struct sk_buff *skb = xs->skb;
+	bool first_frag = false;
 	int err;
 
 	if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
@@ -691,6 +700,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				kfree_skb(skb);
 				goto free_err;
 			}
+
+			first_frag = true;
 		} else {
 			int nr_frags = skb_shinfo(skb)->nr_frags;
 			struct page *page;
@@ -714,12 +725,45 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 			skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE);
 			refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc);
 		}
+
+		if (first_frag && desc->options & XDP_TX_METADATA) {
+			if (unlikely(xs->pool->tx_metadata_len == 0)) {
+				err = -EINVAL;
+				goto free_err;
+			}
+
+			meta = buffer - xs->pool->tx_metadata_len;
+			if (unlikely(!xsk_buff_valid_tx_metadata(meta))) {
+				err = -EINVAL;
+				goto free_err;
+			}
+
+			if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) {
+				if (unlikely(meta->request.csum_start +
+					     meta->request.csum_offset +
+					     sizeof(__sum16) > len)) {
+					err = -EINVAL;
+					goto free_err;
+				}
+
+				skb->csum_start = hr + meta->request.csum_start;
+				skb->csum_offset = meta->request.csum_offset;
+				skb->ip_summed = CHECKSUM_PARTIAL;
+
+				if (unlikely(xs->pool->tx_sw_csum)) {
+					err = skb_checksum_help(skb);
+					if (err)
+						goto free_err;
+				}
+			}
+		}
 	}
 
 	skb->dev = dev;
 	skb->priority = READ_ONCE(xs->sk.sk_priority);
 	skb->mark = READ_ONCE(xs->sk.sk_mark);
 	skb->destructor = xsk_destruct_skb;
+	xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
 	xsk_set_destructor_arg(skb);
 
 	return skb;
@@ -1287,6 +1331,14 @@ struct xdp_umem_reg_v1 {
 	__u32 headroom;
 };
 
+struct xdp_umem_reg_v2 {
+	__u64 addr; /* Start of packet data area */
+	__u64 len; /* Length of packet data area */
+	__u32 chunk_size;
+	__u32 headroom;
+	__u32 flags;
+};
+
 static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			  sockptr_t optval, unsigned int optlen)
 {
@@ -1330,8 +1382,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 
 		if (optlen < sizeof(struct xdp_umem_reg_v1))
 			return -EINVAL;
-		else if (optlen < sizeof(mr))
+		else if (optlen < sizeof(struct xdp_umem_reg_v2))
 			mr_size = sizeof(struct xdp_umem_reg_v1);
+		else if (optlen < sizeof(mr))
+			mr_size = sizeof(struct xdp_umem_reg_v2);
 
 		if (copy_from_sockptr(&mr, optval, mr_size))
 			return -EFAULT;
@@ -1360,6 +1414,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 		struct xsk_queue **q;
 		int entries;
 
+		if (optlen < sizeof(entries))
+			return -EINVAL;
 		if (copy_from_sockptr(&entries, optval, sizeof(entries)))
 			return -EFAULT;
 
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index b0a611677..ce60ecd48 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -85,6 +85,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		XDP_PACKET_HEADROOM;
 	pool->umem = umem;
 	pool->addrs = umem->addrs;
+	pool->tx_metadata_len = umem->tx_metadata_len;
+	pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM;
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
@@ -123,6 +125,18 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc)
+{
+	u32 i;
+
+	for (i = 0; i < pool->heads_cnt; i++) {
+		struct xdp_buff_xsk *xskb = &pool->heads[i];
+
+		memcpy(xskb->cb + desc->off, desc->src, desc->bytes);
+	}
+}
+EXPORT_SYMBOL(xp_fill_cb);
+
 static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
 {
 	struct netdev_bpf bpf;
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 13354a1e4..6f2d1621c 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -137,21 +137,23 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 
 static inline bool xp_unused_options_set(u32 options)
 {
-	return options & ~XDP_PKT_CONTD;
+	return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA);
 }
 
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 					    struct xdp_desc *desc)
 {
-	u64 offset = desc->addr & (pool->chunk_size - 1);
+	u64 addr = desc->addr - pool->tx_metadata_len;
+	u64 len = desc->len + pool->tx_metadata_len;
+	u64 offset = addr & (pool->chunk_size - 1);
 
 	if (!desc->len)
 		return false;
 
-	if (offset + desc->len > pool->chunk_size)
+	if (offset + len > pool->chunk_size)
 		return false;
 
-	if (desc->addr >= pool->addrs_cnt)
+	if (addr >= pool->addrs_cnt)
 		return false;
 
 	if (xp_unused_options_set(desc->options))
@@ -162,16 +164,17 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 					      struct xdp_desc *desc)
 {
-	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr);
+	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len;
+	u64 len = desc->len + pool->tx_metadata_len;
 
 	if (!desc->len)
 		return false;
 
-	if (desc->len > pool->chunk_size)
+	if (len > pool->chunk_size)
 		return false;
 
-	if (addr >= pool->addrs_cnt || addr + desc->len > pool->addrs_cnt ||
-	    xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
+	if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt ||
+	    xp_desc_crosses_non_contig_pg(pool, addr, len))
 		return false;
 
 	if (xp_unused_options_set(desc->options))