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

Pull networking fixes from David Miller:

 1) Several netfilter fixes from Pablo and the crew:
      - Handle fragmented packets properly in netfilter conntrack, from
        Florian Westphal.
      - Fix SCTP ICMP packet handling, from Ying Xue.
      - Fix big-endian bug in nftables, from Liping Zhang.
      - Fix alignment of fake conntrack entry, from Steven Rostedt.

 2) Fix feature flags setting in fjes driver, from Taku Izumi.

 3) Openvswitch ipv6 tunnel source address not set properly, from Or
    Gerlitz.

 4) Fix jumbo MTU handling in amd-xgbe driver, from Thomas Lendacky.

 5) sk->sk_frag.page not released properly in some cases, from Eric
    Dumazet.

 6) Fix RTNL deadlocks in nl80211, from Johannes Berg.

 7) Fix erroneous RTNL lockdep splat in crypto, from Herbert Xu.

 8) Cure improper inflight handling during AF_UNIX GC, from Andrey
    Ulanov.

 9) sch_dsmark doesn't write to packet headers properly, from Eric
    Dumazet.

10) Fix SCM_TIMESTAMPING_OPT_STATS handling in TCP, from Soheil Hassas
    Yeganeh.

11) Add some IDs for Motorola qmi_wwan chips, from Tony Lindgren.

12) Fix nametbl deadlock in tipc, from Ying Xue.

13) GRO and LRO packets not counted correctly in mlx5 driver, from Gal
    Pressman.

14) Fix reset of internal PHYs in bcmgenet, from Doug Berger.

15) Fix hashmap allocation handling, from Alexei Starovoitov.

16) nl_fib_input() needs stronger netlink message length checking, from
    Eric Dumazet.

17) Fix double-free of sk->sk_filter during sock clone, from Daniel
    Borkmann.

18) Fix RX checksum offloading in aquantia driver, from Pavel Belous.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (85 commits)
  net:ethernet:aquantia: Fix for RX checksum offload.
  amd-xgbe: Fix the ECC-related bit position definitions
  sfc: cleanup a condition in efx_udp_tunnel_del()
  Bluetooth: btqcomsmd: fix compile-test dependency
  inet: frag: release spinlock before calling icmp_send()
  tcp: initialize icsk_ack.lrcvtime at session start time
  genetlink: fix counting regression on ctrl_dumpfamily()
  socket, bpf: fix sk_filter use after free in sk_clone_lock
  ipv4: provide stronger user input validation in nl_fib_input()
  bpf: fix hashmap extra_elems logic
  enic: update enic maintainers
  net: bcmgenet: remove bcmgenet_internal_phy_setup()
  ipv6: make sure to initialize sockc.tsflags before first use
  fjes: Do not load fjes driver if extended socket device is not power on.
  fjes: Do not load fjes driver if system does not have extended socket device.
  net/mlx5e: Count LRO packets correctly
  net/mlx5e: Count GSO packets correctly
  net/mlx5: Increase number of max QPs in default profile
  net/mlx5e: Avoid supporting udp tunnel port ndo for VF reps
  net/mlx5e: Use the proper UAPI values when offloading TC vlan actions
  ...

1 files changed, 63 insertions, 39 deletions

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index ffea9859f5a7..a713abd9d03e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1971,13 +1971,12 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 {
 	struct sk_buff *skb;
 	u8 *packet;
-	unsigned int copy_len;
 
 	skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len);
 	if (!skb)
 		return NULL;
 
-	/* Start with the header buffer which may contain just the header
+	/* Pull in the header buffer which may contain just the header
 	 * or the header plus data
 	 */
 	dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.hdr.dma_base,
@@ -1986,30 +1985,49 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 
 	packet = page_address(rdata->rx.hdr.pa.pages) +
 		 rdata->rx.hdr.pa.pages_offset;
-	copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : len;
-	copy_len = min(rdata->rx.hdr.dma_len, copy_len);
-	skb_copy_to_linear_data(skb, packet, copy_len);
-	skb_put(skb, copy_len);
-
-	len -= copy_len;
-	if (len) {
-		/* Add the remaining data as a frag */
-		dma_sync_single_range_for_cpu(pdata->dev,
-					      rdata->rx.buf.dma_base,
-					      rdata->rx.buf.dma_off,
-					      rdata->rx.buf.dma_len,
-					      DMA_FROM_DEVICE);
-
-		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-				rdata->rx.buf.pa.pages,
-				rdata->rx.buf.pa.pages_offset,
-				len, rdata->rx.buf.dma_len);
-		rdata->rx.buf.pa.pages = NULL;
-	}
+	skb_copy_to_linear_data(skb, packet, len);
+	skb_put(skb, len);
 
 	return skb;
 }
 
+static unsigned int xgbe_rx_buf1_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet)
+{
+	/* Always zero if not the first descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, FIRST))
+		return 0;
+
+	/* First descriptor with split header, return header length */
+	if (rdata->rx.hdr_len)
+		return rdata->rx.hdr_len;
+
+	/* First descriptor but not the last descriptor and no split header,
+	 * so the full buffer was used
+	 */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.hdr.dma_len;
+
+	/* First descriptor and last descriptor and no split header, so
+	 * calculate how much of the buffer was used
+	 */
+	return min_t(unsigned int, rdata->rx.hdr.dma_len, rdata->rx.len);
+}
+
+static unsigned int xgbe_rx_buf2_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet,
+				     unsigned int len)
+{
+	/* Always the full buffer if not the last descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.buf.dma_len;
+
+	/* Last descriptor so calculate how much of the buffer was used
+	 * for the last bit of data
+	 */
+	return rdata->rx.len - len;
+}
+
 static int xgbe_tx_poll(struct xgbe_channel *channel)
 {
 	struct xgbe_prv_data *pdata = channel->pdata;
@@ -2092,8 +2110,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	struct napi_struct *napi;
 	struct sk_buff *skb;
 	struct skb_shared_hwtstamps *hwtstamps;
-	unsigned int incomplete, error, context_next, context;
-	unsigned int len, rdesc_len, max_len;
+	unsigned int last, error, context_next, context;
+	unsigned int len, buf1_len, buf2_len, max_len;
 	unsigned int received = 0;
 	int packet_count = 0;
 
@@ -2103,7 +2121,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	if (!ring)
 		return 0;
 
-	incomplete = 0;
+	last = 0;
 	context_next = 0;
 
 	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
@@ -2137,9 +2155,8 @@ read_again:
 		received++;
 		ring->cur++;
 
-		incomplete = XGMAC_GET_BITS(packet->attributes,
-					    RX_PACKET_ATTRIBUTES,
-					    INCOMPLETE);
+		last = XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+				      LAST);
 		context_next = XGMAC_GET_BITS(packet->attributes,
 					      RX_PACKET_ATTRIBUTES,
 					      CONTEXT_NEXT);
@@ -2148,7 +2165,7 @@ read_again:
 					 CONTEXT);
 
 		/* Earlier error, just drain the remaining data */
-		if ((incomplete || context_next) && error)
+		if ((!last || context_next) && error)
 			goto read_again;
 
 		if (error || packet->errors) {
@@ -2160,16 +2177,22 @@ read_again:
 		}
 
 		if (!context) {
-			/* Length is cumulative, get this descriptor's length */
-			rdesc_len = rdata->rx.len - len;
-			len += rdesc_len;
+			/* Get the data length in the descriptor buffers */
+			buf1_len = xgbe_rx_buf1_len(rdata, packet);
+			len += buf1_len;
+			buf2_len = xgbe_rx_buf2_len(rdata, packet, len);
+			len += buf2_len;
 
-			if (rdesc_len && !skb) {
+			if (!skb) {
 				skb = xgbe_create_skb(pdata, napi, rdata,
-						      rdesc_len);
-				if (!skb)
+						      buf1_len);
+				if (!skb) {
 					error = 1;
-			} else if (rdesc_len) {
+					goto skip_data;
+				}
+			}
+
+			if (buf2_len) {
 				dma_sync_single_range_for_cpu(pdata->dev,
 							rdata->rx.buf.dma_base,
 							rdata->rx.buf.dma_off,
@@ -2179,13 +2202,14 @@ read_again:
 				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 						rdata->rx.buf.pa.pages,
 						rdata->rx.buf.pa.pages_offset,
-						rdesc_len,
+						buf2_len,
 						rdata->rx.buf.dma_len);
 				rdata->rx.buf.pa.pages = NULL;
 			}
 		}
 
-		if (incomplete || context_next)
+skip_data:
+		if (!last || context_next)
 			goto read_again;
 
 		if (!skb)
@@ -2243,7 +2267,7 @@ next_packet:
 	}
 
 	/* Check if we need to save state before leaving */
-	if (received && (incomplete || context_next)) {
+	if (received && (!last || context_next)) {
 		rdata = XGBE_GET_DESC_DATA(ring, ring->cur);
 		rdata->state_saved = 1;
 		rdata->state.skb = skb;