1 files changed, 72 insertions, 32 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 04b441460bbd..cecb340898fe 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -658,6 +658,8 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
         return le32_to_cpu(*(volatile __le32 *)head);
 }
 
+#define WB_STRIDE 0x3
+
 /**
  * i40e_clean_tx_irq - Reclaim resources after transmit completes
  * @tx_ring:  tx ring to clean
@@ -759,6 +761,18 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
         tx_ring->q_vector->tx.total_bytes += total_bytes;
         tx_ring->q_vector->tx.total_packets += total_packets;
 
+        /* check to see if there are any non-cache aligned descriptors
+         * waiting to be written back, and kick the hardware to force
+         * them to be written back in case of napi polling
+         */
+        if (budget &&
+            !((i & WB_STRIDE) == WB_STRIDE) &&
+            !test_bit(__I40E_DOWN, &tx_ring->vsi->state) &&
+            (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
+                tx_ring->arm_wb = true;
+        else
+                tx_ring->arm_wb = false;
+
         if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) {
                 /* schedule immediate reset if we believe we hung */
                 dev_info(tx_ring->dev, "Detected Tx Unit Hang\n"
@@ -777,13 +791,16 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
                 netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 
                 dev_info(tx_ring->dev,
-                         "tx hang detected on queue %d, resetting adapter\n",
+                         "tx hang detected on queue %d, reset requested\n",
                          tx_ring->queue_index);
 
-                tx_ring->netdev->netdev_ops->ndo_tx_timeout(tx_ring->netdev);
+                /* do not fire the reset immediately, wait for the stack to
+                 * decide we are truly stuck, also prevents every queue from
+                 * simultaneously requesting a reset
+                 */
 
-                /* the adapter is about to reset, no point in enabling stuff */
-                return true;
+                /* the adapter is about to reset, no point in enabling polling */
+                budget = 1;
         }
 
         netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev,
@@ -806,7 +823,25 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
                 }
         }
 
-        return budget > 0;
+        return !!budget;
+}
+
+/**
+ * i40e_force_wb - Arm hardware to do a wb on noncache aligned descriptors
+ * @vsi: the VSI we care about
+ * @q_vector: the vector  on which to force writeback
+ *
+ **/
+static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
+{
+        u32 val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
+                  I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
+                  I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK
+                  /* allow 00 to be written to the index */;
+
+        wr32(&vsi->back->hw,
+             I40E_PFINT_DYN_CTLN(q_vector->v_idx + vsi->base_vector - 1),
+             val);
 }
 
 /**
@@ -1290,9 +1325,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
          * so the total length of IPv4 header is IHL*4 bytes
          * The UDP_0 bit *may* bet set if the *inner* header is UDP
          */
-        if (ipv4_tunnel &&
-            (decoded.inner_prot != I40E_RX_PTYPE_INNER_PROT_UDP) &&
-            !(rx_status & (1 << I40E_RX_DESC_STATUS_UDP_0_SHIFT))) {
+        if (ipv4_tunnel) {
                 skb->transport_header = skb->mac_header +
                                         sizeof(struct ethhdr) +
                                         (ip_hdr(skb)->ihl * 4);
@@ -1302,15 +1335,19 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
                                           skb->protocol == htons(ETH_P_8021AD))
                                           ? VLAN_HLEN : 0;
 
-                rx_udp_csum = udp_csum(skb);
-                iph = ip_hdr(skb);
-                csum = csum_tcpudp_magic(
-                                iph->saddr, iph->daddr,
-                                (skb->len - skb_transport_offset(skb)),
-                                IPPROTO_UDP, rx_udp_csum);
+                if ((ip_hdr(skb)->protocol == IPPROTO_UDP) &&
+                    (udp_hdr(skb)->check != 0)) {
+                        rx_udp_csum = udp_csum(skb);
+                        iph = ip_hdr(skb);
+                        csum = csum_tcpudp_magic(
+                                        iph->saddr, iph->daddr,
+                                        (skb->len - skb_transport_offset(skb)),
+                                        IPPROTO_UDP, rx_udp_csum);
 
-                if (udp_hdr(skb)->check != csum)
-                        goto checksum_fail;
+                        if (udp_hdr(skb)->check != csum)
+                                goto checksum_fail;
+
+                } /* else its GRE and so no outer UDP header */
         }
 
         skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1581,6 +1618,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
         struct i40e_vsi *vsi = q_vector->vsi;
         struct i40e_ring *ring;
         bool clean_complete = true;
+        bool arm_wb = false;
         int budget_per_ring;
 
         if (test_bit(__I40E_DOWN, &vsi->state)) {
@@ -1591,8 +1629,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
         /* Since the actual Tx work is minimal, we can give the Tx a larger
          * budget and be more aggressive about cleaning up the Tx descriptors.
          */
-        i40e_for_each_ring(ring, q_vector->tx)
+        i40e_for_each_ring(ring, q_vector->tx) {
                 clean_complete &= i40e_clean_tx_irq(ring, vsi->work_limit);
+                arm_wb |= ring->arm_wb;
+        }
 
         /* We attempt to distribute budget to each Rx queue fairly, but don't
          * allow the budget to go below 1 because that would exit polling early.
@@ -1603,8 +1643,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
                 clean_complete &= i40e_clean_rx_irq(ring, budget_per_ring);
 
         /* If work not completed, return budget and polling will return */
-        if (!clean_complete)
+        if (!clean_complete) {
+                if (arm_wb)
+                        i40e_force_wb(vsi, q_vector);
                 return budget;
+        }
 
         /* Work is done so exit the polling mode and re-enable the interrupt */
         napi_complete(napi);
@@ -1840,17 +1883,16 @@ 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,
@@ -1946,13 +1988,9 @@ 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 */
@@ -1962,7 +2000,10 @@ 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);
                 this_ip_hdr = ip_hdr(skb);
@@ -2198,7 +2239,6 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
         /* Place RS bit on last descriptor of any packet that spans across the
          * 4th descriptor (WB_STRIDE aka 0x3) in a 64B cacheline.
          */
-#define WB_STRIDE 0x3
         if (((i & WB_STRIDE) != WB_STRIDE) &&
             (first <= &tx_ring->tx_bi[i]) &&
             (first >= &tx_ring->tx_bi[i & ~WB_STRIDE])) {