1 files changed, 158 insertions, 60 deletions

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9c3acecc14b1..7b0c68a70888 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -36,6 +36,20 @@
 #define TX_BATCH_SIZE 32
 #define MAX_PER_SOCKET_BUDGET 32
 
+struct xsk_addr_node {
+	u64 addr;
+	struct list_head addr_node;
+};
+
+struct xsk_addr_head {
+	u32 num_descs;
+	struct list_head addrs_list;
+};
+
+static struct kmem_cache *xsk_tx_generic_cache;
+
+#define XSKCB(skb) ((struct xsk_addr_head *)((skb)->cb))
+
 void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
 	if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
@@ -532,24 +546,43 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 	return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
 }
 
-static int xsk_cq_reserve_addr_locked(struct xsk_buff_pool *pool, u64 addr)
+static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool)
 {
 	unsigned long flags;
 	int ret;
 
 	spin_lock_irqsave(&pool->cq_lock, flags);
-	ret = xskq_prod_reserve_addr(pool->cq, addr);
+	ret = xskq_prod_reserve(pool->cq);
 	spin_unlock_irqrestore(&pool->cq_lock, flags);
 
 	return ret;
 }
 
-static void xsk_cq_submit_locked(struct xsk_buff_pool *pool, u32 n)
+static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool,
+				      struct sk_buff *skb)
 {
+	struct xsk_addr_node *pos, *tmp;
+	u32 descs_processed = 0;
 	unsigned long flags;
+	u32 idx;
 
 	spin_lock_irqsave(&pool->cq_lock, flags);
-	xskq_prod_submit_n(pool->cq, n);
+	idx = xskq_get_prod(pool->cq);
+
+	xskq_prod_write_addr(pool->cq, idx,
+			     (u64)(uintptr_t)skb_shinfo(skb)->destructor_arg);
+	descs_processed++;
+
+	if (unlikely(XSKCB(skb)->num_descs > 1)) {
+		list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) {
+			xskq_prod_write_addr(pool->cq, idx + descs_processed,
+					     pos->addr);
+			descs_processed++;
+			list_del(&pos->addr_node);
+			kmem_cache_free(xsk_tx_generic_cache, pos);
+		}
+	}
+	xskq_prod_submit_n(pool->cq, descs_processed);
 	spin_unlock_irqrestore(&pool->cq_lock, flags);
 }
 
@@ -562,9 +595,14 @@ static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n)
 	spin_unlock_irqrestore(&pool->cq_lock, flags);
 }
 
+static void xsk_inc_num_desc(struct sk_buff *skb)
+{
+	XSKCB(skb)->num_descs++;
+}
+
 static u32 xsk_get_num_desc(struct sk_buff *skb)
 {
-	return skb ? (long)skb_shinfo(skb)->destructor_arg : 0;
+	return XSKCB(skb)->num_descs;
 }
 
 static void xsk_destruct_skb(struct sk_buff *skb)
@@ -576,23 +614,38 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 		*compl->tx_timestamp = ktime_get_tai_fast_ns();
 	}
 
-	xsk_cq_submit_locked(xdp_sk(skb->sk)->pool, xsk_get_num_desc(skb));
+	xsk_cq_submit_addr_locked(xdp_sk(skb->sk)->pool, skb);
 	sock_wfree(skb);
 }
 
-static void xsk_set_destructor_arg(struct sk_buff *skb)
+static void xsk_skb_init_misc(struct sk_buff *skb, struct xdp_sock *xs,
+			      u64 addr)
 {
-	long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1;
-
-	skb_shinfo(skb)->destructor_arg = (void *)num;
+	BUILD_BUG_ON(sizeof(struct xsk_addr_head) > sizeof(skb->cb));
+	INIT_LIST_HEAD(&XSKCB(skb)->addrs_list);
+	skb->dev = xs->dev;
+	skb->priority = READ_ONCE(xs->sk.sk_priority);
+	skb->mark = READ_ONCE(xs->sk.sk_mark);
+	XSKCB(skb)->num_descs = 0;
+	skb->destructor = xsk_destruct_skb;
+	skb_shinfo(skb)->destructor_arg = (void *)(uintptr_t)addr;
 }
 
 static void xsk_consume_skb(struct sk_buff *skb)
 {
 	struct xdp_sock *xs = xdp_sk(skb->sk);
+	u32 num_descs = xsk_get_num_desc(skb);
+	struct xsk_addr_node *pos, *tmp;
+
+	if (unlikely(num_descs > 1)) {
+		list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) {
+			list_del(&pos->addr_node);
+			kmem_cache_free(xsk_tx_generic_cache, pos);
+		}
+	}
 
 	skb->destructor = sock_wfree;
-	xsk_cq_cancel_locked(xs->pool, xsk_get_num_desc(skb));
+	xsk_cq_cancel_locked(xs->pool, num_descs);
 	/* Free skb without triggering the perf drop trace */
 	consume_skb(skb);
 	xs->skb = NULL;
@@ -604,17 +657,60 @@ static void xsk_drop_skb(struct sk_buff *skb)
 	xsk_consume_skb(skb);
 }
 
+static int xsk_skb_metadata(struct sk_buff *skb, void *buffer,
+			    struct xdp_desc *desc, struct xsk_buff_pool *pool,
+			    u32 hr)
+{
+	struct xsk_tx_metadata *meta = NULL;
+
+	if (unlikely(pool->tx_metadata_len == 0))
+		return -EINVAL;
+
+	meta = buffer - pool->tx_metadata_len;
+	if (unlikely(!xsk_buff_valid_tx_metadata(meta)))
+		return -EINVAL;
+
+	if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) {
+		if (unlikely(meta->request.csum_start +
+			     meta->request.csum_offset +
+			     sizeof(__sum16) > desc->len))
+			return -EINVAL;
+
+		skb->csum_start = hr + meta->request.csum_start;
+		skb->csum_offset = meta->request.csum_offset;
+		skb->ip_summed = CHECKSUM_PARTIAL;
+
+		if (unlikely(pool->tx_sw_csum)) {
+			int err;
+
+			err = skb_checksum_help(skb);
+			if (err)
+				return err;
+		}
+	}
+
+	if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
+		skb->skb_mstamp_ns = meta->request.launch_time;
+	xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
+
+	return 0;
+}
+
 static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 					      struct xdp_desc *desc)
 {
 	struct xsk_buff_pool *pool = xs->pool;
 	u32 hr, len, ts, offset, copy, copied;
+	struct xsk_addr_node *xsk_addr;
 	struct sk_buff *skb = xs->skb;
 	struct page *page;
 	void *buffer;
 	int err, i;
 	u64 addr;
 
+	addr = desc->addr;
+	buffer = xsk_buff_raw_get_data(pool, addr);
+
 	if (!skb) {
 		hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
 
@@ -623,13 +719,29 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 			return ERR_PTR(err);
 
 		skb_reserve(skb, hr);
+
+		xsk_skb_init_misc(skb, xs, desc->addr);
+		if (desc->options & XDP_TX_METADATA) {
+			err = xsk_skb_metadata(skb, buffer, desc, pool, hr);
+			if (unlikely(err))
+				return ERR_PTR(err);
+		}
+	} else {
+		xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
+		if (!xsk_addr)
+			return ERR_PTR(-ENOMEM);
+
+		/* in case of -EOVERFLOW that could happen below,
+		 * xsk_consume_skb() will release this node as whole skb
+		 * would be dropped, which implies freeing all list elements
+		 */
+		xsk_addr->addr = desc->addr;
+		list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list);
 	}
 
-	addr = desc->addr;
 	len = desc->len;
 	ts = pool->unaligned ? len : pool->chunk_size;
 
-	buffer = xsk_buff_raw_get_data(pool, addr);
 	offset = offset_in_page(buffer);
 	addr = buffer - pool->addrs;
 
@@ -660,16 +772,15 @@ 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) {
 		skb = xsk_build_skb_zerocopy(xs, desc);
 		if (IS_ERR(skb)) {
 			err = PTR_ERR(skb);
+			skb = NULL;
 			goto free_err;
 		}
 	} else {
@@ -680,8 +791,6 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 		len = desc->len;
 
 		if (!skb) {
-			first_frag = true;
-
 			hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
 			tr = dev->needed_tailroom;
 			skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
@@ -694,8 +803,17 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 			err = skb_store_bits(skb, 0, buffer, len);
 			if (unlikely(err))
 				goto free_err;
+
+			xsk_skb_init_misc(skb, xs, desc->addr);
+			if (desc->options & XDP_TX_METADATA) {
+				err = xsk_skb_metadata(skb, buffer, desc,
+						       xs->pool, hr);
+				if (unlikely(err))
+					goto free_err;
+			}
 		} else {
 			int nr_frags = skb_shinfo(skb)->nr_frags;
+			struct xsk_addr_node *xsk_addr;
 			struct page *page;
 			u8 *vaddr;
 
@@ -710,66 +828,36 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				goto free_err;
 			}
 
+			xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
+			if (!xsk_addr) {
+				__free_page(page);
+				err = -ENOMEM;
+				goto free_err;
+			}
+
 			vaddr = kmap_local_page(page);
 			memcpy(vaddr, buffer, len);
 			kunmap_local(vaddr);
 
 			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;
-				}
-			}
-
-			if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
-				skb->skb_mstamp_ns = meta->request.launch_time;
+			xsk_addr->addr = desc->addr;
+			list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list);
 		}
 	}
 
-	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);
+	xsk_inc_num_desc(skb);
 
 	return skb;
 
 free_err:
-	if (first_frag && skb)
+	if (skb && !skb_shinfo(skb)->nr_frags)
 		kfree_skb(skb);
 
 	if (err == -EOVERFLOW) {
 		/* Drop the packet */
-		xsk_set_destructor_arg(xs->skb);
+		xsk_inc_num_desc(xs->skb);
 		xsk_drop_skb(xs->skb);
 		xskq_cons_release(xs->tx);
 	} else {
@@ -812,7 +900,7 @@ static int __xsk_generic_xmit(struct sock *sk)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
-		err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr);
+		err = xsk_cq_reserve_locked(xs->pool);
 		if (err) {
 			err = -EAGAIN;
 			goto out;
@@ -1815,8 +1903,18 @@ static int __init xsk_init(void)
 	if (err)
 		goto out_pernet;
 
+	xsk_tx_generic_cache = kmem_cache_create("xsk_generic_xmit_cache",
+						 sizeof(struct xsk_addr_node),
+						 0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!xsk_tx_generic_cache) {
+		err = -ENOMEM;
+		goto out_unreg_notif;
+	}
+
 	return 0;
 
+out_unreg_notif:
+	unregister_netdevice_notifier(&xsk_netdev_notifier);
 out_pernet:
 	unregister_pernet_subsys(&xsk_net_ops);
 out_sk: