8 files changed, 92 insertions, 38 deletions

diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 5b8300a32bf5..4d61ef50b465 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -281,6 +281,17 @@ config I40E_DCB
 
           If unsure, say N.
 
+config I40E_FCOE
+        bool "Fibre Channel over Ethernet (FCoE)"
+        default n
+        depends on I40E && DCB && FCOE
+        ---help---
+          Say Y here if you want to use Fibre Channel over Ethernet (FCoE)
+          in the driver. This will create new netdev for exclusive FCoE
+          use with XL710 FCoE offloads enabled.
+
+          If unsure, say N.
+
 config I40EVF
         tristate "Intel(R) XL710 X710 Virtual Function Ethernet support"
         depends on PCI_MSI
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 781065eb5431..e9c3a87e5b11 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1543,7 +1543,7 @@ static int e100_phy_init(struct nic *nic)
                 mdio_write(netdev, nic->mii.phy_id, MII_BMCR, bmcr);
         } else if ((nic->mac >= mac_82550_D102) || ((nic->flags & ich) &&
            (mdio_read(netdev, nic->mii.phy_id, MII_TPISTATUS) & 0x8000) &&
-                !(nic->eeprom[eeprom_cnfg_mdix] & eeprom_mdix_enabled))) {
+                (nic->eeprom[eeprom_cnfg_mdix] & eeprom_mdix_enabled))) {
                 /* enable/disable MDI/MDI-X auto-switching. */
                 mdio_write(netdev, nic->mii.phy_id, MII_NCONFIG,
                                 nic->mii.force_media ? 0 : NCONFIG_AUTO_SWITCH);
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 4b94ddb29c24..c40581999121 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -44,4 +44,4 @@ i40e-objs := i40e_main.o \
         i40e_virtchnl_pf.o
 
 i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o
-i40e-$(CONFIG_FCOE:m=y) += i40e_fcoe.o
+i40e-$(CONFIG_I40E_FCOE) += i40e_fcoe.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 433a55886ad2..cb0de455683e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -829,7 +829,7 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n,
                 if (desc_n >= ring->count || desc_n < 0) {
                         dev_info(&pf->pdev->dev,
                                  "descriptor %d not found\n", desc_n);
-                        return;
+                        goto out;
                 }
                 if (!is_rx_ring) {
                         txd = I40E_TX_DESC(ring, desc_n);
@@ -855,6 +855,8 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n,
         } else {
                 dev_info(&pf->pdev->dev, "dump desc rx/tx <vsi_seid> <ring_id> [<desc_n>]\n");
         }
+
+out:
         kfree(ring);
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index 045b5c4b98b3..ad802dd0f67a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -78,7 +78,7 @@ do {                                                            \
 } while (0)
 
 typedef enum i40e_status_code i40e_status;
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#ifdef CONFIG_I40E_FCOE
 #define I40E_FCOE
-#endif /* CONFIG_FCOE or CONFIG_FCOE_MODULE */
+#endif
 #endif /* _I40E_OSDEP_H_ */
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])) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index e60d3accb2e2..18b00231d2f1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -241,6 +241,7 @@ struct i40e_ring {
         unsigned long last_rx_timestamp;
 
         bool ring_active;               /* is ring online or not */
+        bool arm_wb;            /* do something to arm write back */
 
         /* stats structs */
         struct i40e_queue_stats stats;
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 051ea94bdcd3..0f69ef81751a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -1125,7 +1125,7 @@ static s32 igb_acquire_swfw_sync_82575(struct e1000_hw *hw, u16 mask)
         u32 swmask = mask;
         u32 fwmask = mask << 16;
         s32 ret_val = 0;
-        s32 i = 0, timeout = 200; /* FIXME: find real value to use here */
+        s32 i = 0, timeout = 200;
 
         while (i < timeout) {
                 if (igb_get_hw_semaphore(hw)) {