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

Conflicts:

tools/testing/selftests/net/config
  62199e3f1658 ("selftests: net: Add VXLAN MDB test")
  3a0385be133e ("selftests: add the missing CONFIG_IP_SCTP in net config")

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

4 files changed, 28 insertions, 12 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 480600a075ce..c7f13742b56c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3197,6 +3197,7 @@ static u16 skb_tx_hash(const struct net_device *dev,
 	}
 
 	if (skb_rx_queue_recorded(skb)) {
+		DEBUG_NET_WARN_ON_ONCE(qcount == 0);
 		hash = skb_get_rx_queue(skb);
 		if (hash >= qoffset)
 			hash -= qoffset;
@@ -10870,7 +10871,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
 			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
 						     GFP_KERNEL, NULL, 0,
-						     portid, nlmsg_seq(nlh));
+						     portid, nlh);
 
 		/*
 		 *	Flush the unicast and multicast chains
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 906aebdc566b..e844d75220fb 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3975,16 +3975,23 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
 				       unsigned int change,
 				       u32 event, gfp_t flags, int *new_nsid,
-				       int new_ifindex, u32 portid, u32 seq)
+				       int new_ifindex, u32 portid,
+				       const struct nlmsghdr *nlh)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
+	u32 seq = 0;
 
 	skb = nlmsg_new(if_nlmsg_size(dev, 0), flags);
 	if (skb == NULL)
 		goto errout;
 
+	if (nlmsg_report(nlh))
+		seq = nlmsg_seq(nlh);
+	else
+		portid = 0;
+
 	err = rtnl_fill_ifinfo(skb, dev, dev_net(dev),
 			       type, portid, seq, change, 0, 0, event,
 			       new_nsid, new_ifindex, -1, flags);
@@ -4020,7 +4027,7 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev,
 		return;
 
 	skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid,
-				     new_ifindex, portid, nlmsg_seq(nlh));
+				     new_ifindex, portid, nlh);
 	if (skb)
 		rtmsg_ifinfo_send(skb, dev, flags, portid, nlh);
 }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 050a875d09c5..78238a13dbcf 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5597,18 +5597,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	if (skb_cloned(to))
 		return false;
 
-	/* In general, avoid mixing slab allocated and page_pool allocated
-	 * pages within the same SKB. However when @to is not pp_recycle and
-	 * @from is cloned, we can transition frag pages from page_pool to
-	 * reference counted.
-	 *
-	 * On the other hand, don't allow coalescing two pp_recycle SKBs if
-	 * @from is cloned, in case the SKB is using page_pool fragment
+	/* In general, avoid mixing page_pool and non-page_pool allocated
+	 * pages within the same SKB. Additionally avoid dealing with clones
+	 * with page_pool pages, in case the SKB is using page_pool fragment
 	 * references (PP_FLAG_PAGE_FRAG). Since we only take full page
 	 * references for cloned SKBs at the moment that would result in
 	 * inconsistent reference counts.
+	 * In theory we could take full references if @from is cloned and
+	 * !@to->pp_recycle but its tricky (due to potential race with
+	 * the clone disappearing) and rare, so not worth dealing with.
 	 */
-	if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from)))
+	if (to->pp_recycle != from->pp_recycle ||
+	    (from->pp_recycle && skb_cloned(from)))
 		return false;
 
 	if (len <= skb_tailroom(to)) {
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 528d4b37983d..fb85aca81961 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -734,13 +734,21 @@ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *tim
  * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash.
  * @ctx: XDP context pointer.
  * @hash: Return value pointer.
+ * @rss_type: Return value pointer for RSS type.
+ *
+ * The RSS hash type (@rss_type) specifies what portion of packet headers NIC
+ * hardware used when calculating RSS hash value.  The RSS type can be decoded
+ * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits
+ * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types*
+ * ``XDP_RSS_TYPE_L*``.
  *
  * Return:
  * * Returns 0 on success or ``-errno`` on error.
  * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc
  * * ``-ENODATA``    : means no RX-hash available for this frame
  */
-__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash)
+__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
+					 enum xdp_rss_hash_type *rss_type)
 {
 	return -EOPNOTSUPP;
 }