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

Pull networking fixes from David Miller:

 1) If an IPVS tunnel is created with a mixed-family destination
    address, it cannot be removed.  Fix from Alexey Andriyanov.

 2) Fix module refcount underflow in netfilter's nft_compat, from Pablo
    Neira Ayuso.

 3) Generic statistics infrastructure can reference variables sitting on
    a released function stack, therefore use dynamic allocation always.
    Fix from Ignacy Gawędzki.

 4) skb_copy_bits() return value test is inverted in ip_check_defrag().

 5) Fix network namespace exit in openvswitch, we have to release all of
    the per-net vports.  From Pravin B Shelar.

 6) Fix signedness bug in CAIF's cfpkt_iterate(), from Dan Carpenter.

 7) Fix rhashtable grow/shrink behavior, only expand during inserts and
    shrink during deletes.  From Daniel Borkmann.

 8) Netdevice names with semicolons should never be allowed, because
    they serve as a separator.  From Matthew Thode.

 9) Use {,__}set_current_state() where appropriate, from Fabian
    Frederick.

10) Revert byte queue limits support in r8169 driver, it's causing
    regressions we can't figure out.

11) tcp_should_expand_sndbuf() erroneously uses tp->packets_out to
    measure packets in flight, properly use tcp_packets_in_flight()
    instead.  From Neal Cardwell.

12) Fix accidental removal of support for bluetooth in CSR based Intel
    wireless cards.  From Marcel Holtmann.

13) We accidently added a behavioral change between native and compat
    tasks, wrt testing the MSG_CMSG_COMPAT bit.  Just ignore it if the
    user happened to set it in a native binary as that was always the
    behavior we had.  From Catalin Marinas.

14) Check genlmsg_unicast() return valud in hwsim netlink tx frame
    handling, from Bob Copeland.

15) Fix stale ->radar_required setting in mac80211 that can prevent
    starting new scans, from Eliad Peller.

16) Fix memory leak in nl80211 monitor, from Johannes Berg.

17) Fix race in TX index handling in xen-netback, from David Vrabel.

18) Don't enable interrupts in amx-xgbe driver until all software et al.
    state is ready for the interrupt handler to run.  From Thomas
    Lendacky.

19) Add missing netlink_ns_capable() checks to rtnl_newlink(), from Eric
    W Biederman.

20) The amount of header space needed in macvtap was not calculated
    properly, fix it otherwise we splat past the beginning of the
    packet.  From Eric Dumazet.

21) Fix bcmgenet TCP TX perf regression, from Jaedon Shin.

22) Don't raw initialize or mod timers, use setup_timer() and
    mod_timer() instead.  From Vaishali Thakkar.

23) Fix software maintained statistics in bcmgenet and systemport
    drivers, from Florian Fainelli.

24) DMA descriptor updates in sh_eth need proper memory barriers, from
    Ben Hutchings.

25) Don't do UDP Fragmentation Offload on RAW sockets, from Michal
    Kubecek.

26) Openvswitch's non-masked set actions aren't constructed properly
    into netlink messages, fix from Joe Stringer.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
  openvswitch: Fix serialization of non-masked set actions.
  gianfar: Reduce logging noise seen due to phy polling if link is down
  ibmveth: Add function to enable live MAC address changes
  net: bridge: add compile-time assert for cb struct size
  udp: only allow UFO for packets from SOCK_DGRAM sockets
  sh_eth: Really fix padding of short frames on TX
  Revert "sh_eth: Enable Rx descriptor word 0 shift for r8a7790"
  sh_eth: Fix RX recovery on R-Car in case of RX ring underrun
  sh_eth: Ensure proper ordering of descriptor active bit write/read
  net/mlx4_en: Disbale GRO for incoming loopback/selftest packets
  net/mlx4_core: Fix wrong mask and error flow for the update-qp command
  net: systemport: fix software maintained statistics
  net: bcmgenet: fix software maintained statistics
  rxrpc: don't multiply with HZ twice
  rxrpc: terminate retrans loop when sending of skb fails
  net/hsr: Fix NULL pointer dereference and refcnt bugs when deleting a HSR interface.
  net: pasemi: Use setup_timer and mod_timer
  net: stmmac: Use setup_timer and mod_timer
  net: 8390: axnet_cs: Use setup_timer and mod_timer
  net: 8390: pcnet_cs: Use setup_timer and mod_timer
  ...

1 files changed, 107 insertions, 36 deletions

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 29004382f462..708891571dae 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -126,6 +126,20 @@ void i40evf_free_tx_resources(struct i40e_ring *tx_ring)
 }
 
 /**
+ * i40e_get_head - Retrieve head from head writeback
+ * @tx_ring:  tx ring to fetch head of
+ *
+ * Returns value of Tx ring head based on value stored
+ * in head write-back location
+ **/
+static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
+{
+	void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
+
+	return le32_to_cpu(*(volatile __le32 *)head);
+}
+
+/**
  * i40e_get_tx_pending - how many tx descriptors not processed
  * @tx_ring: the ring of descriptors
  *
@@ -134,10 +148,16 @@ void i40evf_free_tx_resources(struct i40e_ring *tx_ring)
  **/
 static u32 i40e_get_tx_pending(struct i40e_ring *ring)
 {
-	u32 ntu = ((ring->next_to_clean <= ring->next_to_use)
-			? ring->next_to_use
-			: ring->next_to_use + ring->count);
-	return ntu - ring->next_to_clean;
+	u32 head, tail;
+
+	head = i40e_get_head(ring);
+	tail = readl(ring->tail);
+
+	if (head != tail)
+		return (head < tail) ?
+			tail - head : (tail + ring->count - head);
+
+	return 0;
 }
 
 /**
@@ -146,6 +166,8 @@ static u32 i40e_get_tx_pending(struct i40e_ring *ring)
  **/
 static bool i40e_check_tx_hang(struct i40e_ring *tx_ring)
 {
+	u32 tx_done = tx_ring->stats.packets;
+	u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
 	u32 tx_pending = i40e_get_tx_pending(tx_ring);
 	bool ret = false;
 
@@ -162,36 +184,20 @@ static bool i40e_check_tx_hang(struct i40e_ring *tx_ring)
 	 * run the check_tx_hang logic with a transmit completion
 	 * pending but without time to complete it yet.
 	 */
-	if ((tx_ring->tx_stats.tx_done_old == tx_ring->stats.packets) &&
-	    (tx_pending >= I40E_MIN_DESC_PENDING)) {
+	if ((tx_done_old == tx_done) && tx_pending) {
 		/* make sure it is true for two checks in a row */
 		ret = test_and_set_bit(__I40E_HANG_CHECK_ARMED,
 				       &tx_ring->state);
-	} else if (!(tx_ring->tx_stats.tx_done_old == tx_ring->stats.packets) ||
-		   !(tx_pending < I40E_MIN_DESC_PENDING) ||
-		   !(tx_pending > 0)) {
+	} else if (tx_done_old == tx_done &&
+		   (tx_pending < I40E_MIN_DESC_PENDING) && (tx_pending > 0)) {
 		/* update completed stats and disarm the hang check */
-		tx_ring->tx_stats.tx_done_old = tx_ring->stats.packets;
+		tx_ring->tx_stats.tx_done_old = tx_done;
 		clear_bit(__I40E_HANG_CHECK_ARMED, &tx_ring->state);
 	}
 
 	return ret;
 }
 
-/**
- * i40e_get_head - Retrieve head from head writeback
- * @tx_ring:  tx ring to fetch head of
- *
- * Returns value of Tx ring head based on value stored
- * in head write-back location
- **/
-static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
-{
-	void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
-
-	return le32_to_cpu(*(volatile __le32 *)head);
-}
-
 #define WB_STRIDE 0x3
 
 /**
@@ -1206,17 +1212,16 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	if (protocol == htons(ETH_P_IP)) {
-		iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
+	iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
+	ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
+
+	if (iph->version == 4) {
 		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
 		iph->tot_len = 0;
 		iph->check = 0;
 		tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
 						 0, IPPROTO_TCP, 0);
-	} else if (skb_is_gso_v6(skb)) {
-
-		ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb)
-					   : ipv6_hdr(skb);
+	} else if (ipv6h->version == 6) {
 		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
 		ipv6h->payload_len = 0;
 		tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
@@ -1274,13 +1279,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
 			}
 		} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
-			if (tx_flags & I40E_TX_FLAGS_TSO) {
-				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			if (tx_flags & I40E_TX_FLAGS_TSO)
 				ip_hdr(skb)->check = 0;
-			} else {
-				*cd_tunneling |=
-					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
-			}
 		}
 
 		/* Now set the ctx descriptor fields */
@@ -1290,6 +1291,11 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 				   ((skb_inner_network_offset(skb) -
 					skb_transport_offset(skb)) >> 1) <<
 				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
+		if (this_ip_hdr->version == 6) {
+			tx_flags &= ~I40E_TX_FLAGS_IPV4;
+			tx_flags |= I40E_TX_FLAGS_IPV6;
+		}
+
 
 	} else {
 		network_hdr_len = skb_network_header_len(skb);
@@ -1380,6 +1386,67 @@ static void i40e_create_tx_ctx(struct i40e_ring *tx_ring,
 	context_desc->type_cmd_tso_mss = cpu_to_le64(cd_type_cmd_tso_mss);
 }
 
+ /**
+ * i40e_chk_linearize - Check if there are more than 8 fragments per packet
+ * @skb:      send buffer
+ * @tx_flags: collected send information
+ * @hdr_len:  size of the packet header
+ *
+ * Note: Our HW can't scatter-gather more than 8 fragments to build
+ * a packet on the wire and so we need to figure out the cases where we
+ * need to linearize the skb.
+ **/
+static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
+			       const u8 hdr_len)
+{
+	struct skb_frag_struct *frag;
+	bool linearize = false;
+	unsigned int size = 0;
+	u16 num_frags;
+	u16 gso_segs;
+
+	num_frags = skb_shinfo(skb)->nr_frags;
+	gso_segs = skb_shinfo(skb)->gso_segs;
+
+	if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) {
+		u16 j = 1;
+
+		if (num_frags < (I40E_MAX_BUFFER_TXD))
+			goto linearize_chk_done;
+		/* try the simple math, if we have too many frags per segment */
+		if (DIV_ROUND_UP((num_frags + gso_segs), gso_segs) >
+		    I40E_MAX_BUFFER_TXD) {
+			linearize = true;
+			goto linearize_chk_done;
+		}
+		frag = &skb_shinfo(skb)->frags[0];
+		size = hdr_len;
+		/* we might still have more fragments per segment */
+		do {
+			size += skb_frag_size(frag);
+			frag++; j++;
+			if (j == I40E_MAX_BUFFER_TXD) {
+				if (size < skb_shinfo(skb)->gso_size) {
+					linearize = true;
+					break;
+				}
+				j = 1;
+				size -= skb_shinfo(skb)->gso_size;
+				if (size)
+					j++;
+				size += hdr_len;
+			}
+			num_frags--;
+		} while (num_frags);
+	} else {
+		if (num_frags >= I40E_MAX_BUFFER_TXD)
+			linearize = true;
+	}
+
+linearize_chk_done:
+	return linearize;
+}
+
 /**
  * i40e_tx_map - Build the Tx descriptor
  * @tx_ring:  ring to send buffer on
@@ -1654,6 +1721,10 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (tso)
 		tx_flags |= I40E_TX_FLAGS_TSO;
 
+	if (i40e_chk_linearize(skb, tx_flags, hdr_len))
+		if (skb_linearize(skb))
+			goto out_drop;
+
 	skb_tx_timestamp(skb);
 
 	/* always enable CRC insertion offload */