Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 80 insertions, 39 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 267c4a8daa55..0a31d4ea6f4d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9648,9 +9648,15 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		}
 	}
 
-	if ((features & NETIF_F_HW_TLS_TX) && !(features & NETIF_F_HW_CSUM)) {
-		netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
-		features &= ~NETIF_F_HW_TLS_TX;
+	if (features & NETIF_F_HW_TLS_TX) {
+		bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) ==
+			(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+		bool hw_csum = features & NETIF_F_HW_CSUM;
+
+		if (!ip_csum && !hw_csum) {
+			netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+			features &= ~NETIF_F_HW_TLS_TX;
+		}
 	}
 
 	return features;
@@ -10064,17 +10070,11 @@ int register_netdevice(struct net_device *dev)
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
 	ret = notifier_to_errno(ret);
 	if (ret) {
+		/* Expect explicit free_netdev() on failure */
+		dev->needs_free_netdev = false;
 		rollback_registered(dev);
-		rcu_barrier();
-
-		dev->reg_state = NETREG_UNREGISTERED;
-		/* We should put the kobject that hold in
-		 * netdev_unregister_kobject(), otherwise
-		 * the net device cannot be freed when
-		 * driver calls free_netdev(), because the
-		 * kobject is being hold.
-		 */
-		kobject_put(&dev->dev.kobj);
+		net_set_todo(dev);
+		goto out;
 	}
 	/*
 	 *	Prevent userspace races by waiting until the network
@@ -10618,6 +10618,17 @@ void free_netdev(struct net_device *dev)
 	struct napi_struct *p, *n;
 
 	might_sleep();
+
+	/* When called immediately after register_netdevice() failed the unwind
+	 * handling may still be dismantling the device. Handle that case by
+	 * deferring the free.
+	 */
+	if (dev->reg_state == NETREG_UNREGISTERING) {
+		ASSERT_RTNL();
+		dev->needs_free_netdev = true;
+		return;
+	}
+
 	netif_free_tx_queues(dev);
 	netif_free_rx_queues(dev);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bb0596c41b3e..3d6ab194d0f5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3439,26 +3439,15 @@ replay:
 
 	dev->ifindex = ifm->ifi_index;
 
-	if (ops->newlink) {
+	if (ops->newlink)
 		err = ops->newlink(link_net ? : net, dev, tb, data, extack);
-		/* Drivers should call free_netdev() in ->destructor
-		 * and unregister it on failure after registration
-		 * so that device could be finally freed in rtnl_unlock.
-		 */
-		if (err < 0) {
-			/* If device is not registered at all, free it now */
-			if (dev->reg_state == NETREG_UNINITIALIZED ||
-			    dev->reg_state == NETREG_UNREGISTERED)
-				free_netdev(dev);
-			goto out;
-		}
-	} else {
+	else
 		err = register_netdevice(dev);
-		if (err < 0) {
-			free_netdev(dev);
-			goto out;
-		}
+	if (err < 0) {
+		free_netdev(dev);
+		goto out;
 	}
+
 	err = rtnl_configure_link(dev, ifm);
 	if (err < 0)
 		goto out_unregister;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7626a33cce59..60390696e184 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -501,13 +501,17 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
 struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 				 gfp_t gfp_mask)
 {
-	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+	struct napi_alloc_cache *nc;
 	struct sk_buff *skb;
 	void *data;
 
 	len += NET_SKB_PAD + NET_IP_ALIGN;
 
-	if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
+	/* If requested length is either too small or too big,
+	 * we use kmalloc() for skb->head allocation.
+	 */
+	if (len <= SKB_WITH_OVERHEAD(1024) ||
+	    len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
 	    (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
 		skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
 		if (!skb)
@@ -515,6 +519,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 		goto skb_success;
 	}
 
+	nc = this_cpu_ptr(&napi_alloc_cache);
 	len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	len = SKB_DATA_ALIGN(len);
 
@@ -3439,6 +3444,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
 	st->root_skb = st->cur_skb = skb;
 	st->frag_idx = st->stepped_offset = 0;
 	st->frag_data = NULL;
+	st->frag_off = 0;
 }
 EXPORT_SYMBOL(skb_prepare_seq_read);
 
@@ -3493,14 +3499,27 @@ next_skb:
 		st->stepped_offset += skb_headlen(st->cur_skb);
 
 	while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
+		unsigned int pg_idx, pg_off, pg_sz;
+
 		frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
-		block_limit = skb_frag_size(frag) + st->stepped_offset;
 
+		pg_idx = 0;
+		pg_off = skb_frag_off(frag);
+		pg_sz = skb_frag_size(frag);
+
+		if (skb_frag_must_loop(skb_frag_page(frag))) {
+			pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT;
+			pg_off = offset_in_page(pg_off + st->frag_off);
+			pg_sz = min_t(unsigned int, pg_sz - st->frag_off,
+						    PAGE_SIZE - pg_off);
+		}
+
+		block_limit = pg_sz + st->stepped_offset;
 		if (abs_offset < block_limit) {
 			if (!st->frag_data)
-				st->frag_data = kmap_atomic(skb_frag_page(frag));
+				st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx);
 
-			*data = (u8 *) st->frag_data + skb_frag_off(frag) +
+			*data = (u8 *)st->frag_data + pg_off +
 				(abs_offset - st->stepped_offset);
 
 			return block_limit - abs_offset;
@@ -3511,8 +3530,12 @@ next_skb:
 			st->frag_data = NULL;
 		}
 
-		st->frag_idx++;
-		st->stepped_offset += skb_frag_size(frag);
+		st->stepped_offset += pg_sz;
+		st->frag_off += pg_sz;
+		if (st->frag_off == skb_frag_size(frag)) {
+			st->frag_off = 0;
+			st->frag_idx++;
+		}
 	}
 
 	if (st->frag_data) {
@@ -3652,7 +3675,8 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 	unsigned int delta_truesize = 0;
 	unsigned int delta_len = 0;
 	struct sk_buff *tail = NULL;
-	struct sk_buff *nskb;
+	struct sk_buff *nskb, *tmp;
+	int err;
 
 	skb_push(skb, -skb_network_offset(skb) + offset);
 
@@ -3662,11 +3686,28 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 		nskb = list_skb;
 		list_skb = list_skb->next;
 
+		err = 0;
+		if (skb_shared(nskb)) {
+			tmp = skb_clone(nskb, GFP_ATOMIC);
+			if (tmp) {
+				consume_skb(nskb);
+				nskb = tmp;
+				err = skb_unclone(nskb, GFP_ATOMIC);
+			} else {
+				err = -ENOMEM;
+			}
+		}
+
 		if (!tail)
 			skb->next = nskb;
 		else
 			tail->next = nskb;
 
+		if (unlikely(err)) {
+			nskb->next = list_skb;
+			goto err_linearize;
+		}
+
 		tail = nskb;
 
 		delta_len += nskb->len;
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index bbdd3c7b6cb5..b065f0a103ed 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -293,7 +293,7 @@ select_by_hash:
 			i = j = reciprocal_scale(hash, socks);
 			while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
 				i++;
-				if (i >= reuse->num_socks)
+				if (i >= socks)
 					i = 0;
 				if (i == j)
 					goto out;